Merge pull request 'netrans 251204 更新' (#2) from dev into master
This commit is contained in:
commit
969eb090f2
381
README.md
381
README.md
|
|
@ -1,19 +1,20 @@
|
|||
# Netrans 简介
|
||||
|
||||
Netrans 是Pnna NPU 配套的AI编译器，提供命令行工具 netrans_cli 和 python api netrans_py， 其功能是将模型权重转换成在 Pnna NPU 上运行的 nbg（network binary graph）格式文件（.nb 后缀）。
|
||||
Netrans 是 Pnna NPU 配套的AI编译器，提供命令行工具 Netrans_cli 和 python API, 其功能是将模型权重转换成在 Pnna NPU 上运行的 nbg（network binary graph）格式文件（.nb 后缀）。 Nbg 文件用于后续模型部署和推理工程的交叉编译。
|
||||
|
||||
## 工程结构
|
||||
|
||||
Netrans 目录结构如下：
|
||||
|
||||
```text
|
||||
netrans-ai-compiler/
|
||||
├── bin/ # 编译器可执行文件
|
||||
├── netrans_cli/ # 命令行工具
|
||||
├── netrans_py/ # Python接口
|
||||
├── examples/ # 示例代码
|
||||
└── setup.sh # 安装脚本
|
||||
|
||||
netrans/
|
||||
├── bin # binary file
|
||||
├── docs # 文档，包括用户指南和命令行工具的详细说明
|
||||
├── examples # 示例代码，展示不同框架如何使用netrans进行模型转换
|
||||
├── README.md # 说明文档，通常包含项目概述、安装指南等
|
||||
├── script # 命令行工具
|
||||
├── setup.sh # 用于设置环境或安装依赖的Shell脚本
|
||||
└── test # 测试代码
|
||||
```
|
||||
|
||||
## 安装指南
|
||||
|
|
@ -23,7 +24,7 @@ netrans-ai-compiler/
|
|||
- CPU ： Intel® Core™ i5-6500 CPU @ 3.2 GHz x4 支持 the Intel® Advanced Vector Extensions.
|
||||
- RAM ： 至少8GB
|
||||
- 硬盘 ： 160GB
|
||||
- 操作系统 ： Ubuntu 20.04 LTS 64-bit with Python 3.8，不推荐使用其他版本
|
||||
- 操作系统 ： Ubuntu 20.04 LTS 64-bit with Python 3.10，不推荐使用其他版本
|
||||
|
||||
### 安装步骤
|
||||
|
||||
|
|
@ -32,25 +33,29 @@ netrans-ai-compiler/
|
|||
```shell
|
||||
sudo apt update
|
||||
sudo apt install build-essential
|
||||
```
|
||||
|
||||
- 创建 python3.8 环境
|
||||
# 安装 mamba ，本项目使用 mamba 创建虚拟环境，演示安装过程
|
||||
|
||||
```bash
|
||||
wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
|
||||
mkdir -p ~/app
|
||||
INSTALL_PATH="${HOME}/app/miniforge3"
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${INSTALL_PATH}
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/conda.sh"" >> ${HOME}/.bashrc
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
source ${HOME}/.bashrc
|
||||
mamba create -n netrans python=3.8 -y
|
||||
mamba activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.10
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
- 下载 Netrans
|
||||
|
||||
```bash
|
||||
# 下载 Netrans 到 ～/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
|
@ -59,26 +64,36 @@ git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
|||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
bash setup.sh
|
||||
```
|
||||
|
||||
## Netrans 使用说明
|
||||
|
||||
Netrans 提供 tensorflow、caffe、darknet、onnx 和 pytorch 的模型转换示例，请参考 [示例](./examples/index.rst)
|
||||
Netrans 提供 Tensorflow、Caffe、Darknet、ONNX 和 Pytorch 的模型转换示例，请参考目录 `~/app/netrans/examples`
|
||||
|
||||
|
||||
### 命令行工具
|
||||
|
||||
Netrans CLI 提供了简单的命令行接口，用于编译和优化模型。
|
||||
基本用法
|
||||
Netrans 提供了简单的命令行接口，用于编译和优化模型。
|
||||
|
||||
```bash
|
||||
load.sh model_path # 模型导入
|
||||
config.sh model_path # 参数配置
|
||||
quantize.sh model_path quantize_type # 模型量化
|
||||
export.sh model_path quantize_type # 模型导出
|
||||
# 以 转成 ONNX 格式的 YOLOv8s 模型为例，演示使用 Netrans 命令行工具完成转换的全过程。
|
||||
# 1. 定义模型路径，模型路径默认为工作路径。
|
||||
work_path='~/app/netrans/examples/infer_with_pre_post_process/yolov8s'
|
||||
cd ${work_path}
|
||||
# 2. 激活环境
|
||||
mamba activate netrans
|
||||
# 3. 模型导入
|
||||
netrans load ./ --mean 0 0 0 --scale 1 1 1
|
||||
# 4. 模型量化
|
||||
netrans quantize ./ asymu8
|
||||
# 5. 将前后处理加入推理网络
|
||||
netrans add_pre_post ./ asymu8
|
||||
# 6. 导出 nbg 文件
|
||||
netrans export ./ asymu8
|
||||
```
|
||||
|
||||
详细说明请参考[netrans_cli 使用](netrans_cli.md)。
|
||||
详细说明请参考[netrans 命令行使用说明](docs/netrans_cli.md)。
|
||||
|
||||
### Python接口
|
||||
|
||||
|
|
@ -86,301 +101,23 @@ export.sh model_path quantize_type # 模型导出
|
|||
示例代码：
|
||||
|
||||
```py3
|
||||
from nertans import Netrans
|
||||
model_path = 'example/darknet/yolov4_tiny'
|
||||
netrans_path = "netrans/bin" # 如果进行了export定义申明，这一步可以不用
|
||||
from netrans import Netrans
|
||||
|
||||
# 定义模型路径，模型路径默认为工作路径。
|
||||
model_path='~/app/netrans/examples/infer_with_pre_post_process/yolov8s'
|
||||
import sys
|
||||
model_path=sys.argv[1]
|
||||
|
||||
# 初始化netrans
|
||||
net = Netrans(model_path,netrans=netrans_path)
|
||||
# 模型载入
|
||||
net.load()
|
||||
# 配置预处理 normlize 的参数
|
||||
net.config(scale=1,mean=0)
|
||||
net = Netrans()
|
||||
# 模型载入,同时配置 mean 和 scale
|
||||
net.load(model_path, mean=[128,128,128] ,scale=[1,1,1] )
|
||||
# 模型量化
|
||||
net.quantize("uint8")
|
||||
net.quantize("asymu8", pre = False, post= False)
|
||||
# 前后处理添加进推理
|
||||
net.add_pre_post("asymu8")
|
||||
# 模型导出
|
||||
net.export()
|
||||
|
||||
# 模型直接量化成 int16 并导出, 直接复用刚配置好的 inputmeta
|
||||
net.model2nbg(quantize_type = "int16", inputmeta=True)
|
||||
net.export("asymu8")
|
||||
```
|
||||
|
||||
详细说明请参考[netrans_py 使用](netrans_py.md)。
|
||||
|
||||
## 模型支持
|
||||
|
||||
Netrans 支持主流框架见下表。
|
||||
|
||||
|输入支持|描述|
|
||||
|:---|---|
|
||||
| caffe|支持所有的Caffe 模型 |
|
||||
| Tensorflow|支持版本1.4.x, 2.0.x, 2.3.x, 2.6.x, 2.8.x, 2.10.x, 2.12.x 以tf.io.write_graph()保存的模型 |
|
||||
| ONNX|支持 ONNX 至 1.14.0， opset支持至19 |
|
||||
| Pytorch | 支持 Pytorch 至 1.5.1 |
|
||||
| Darknet |支持[官网](https://pjreddie.com/darknet/)列出 darknet 模型|
|
||||
|
||||
<font color="#dd0000">注意：</font> Pytorch 动态图的特性，建议将 Pytorch 模型导出成 onnx ，再使用 Netrans 进行转换。
|
||||
|
||||
## 算子支持
|
||||
|
||||
### 支持的Caffe算子
|
||||
|
||||
```{table}
|
||||
absval | innerproduct | reorg
|
||||
axpy | lrn | roipooling
|
||||
batchnorm/bn | l2normalizescale | relu
|
||||
convolution | leakyrelu | reshape
|
||||
concat | lstm | reverse
|
||||
convolutiondepthwise | normalize | swish
|
||||
dropout | poolwithargmax | slice
|
||||
depthwiseconvolution | premute | scale
|
||||
deconvolution | prelu | shufflechannel
|
||||
elu | pooling | softmax
|
||||
eltwise | priorbox | sigmoid
|
||||
flatten | proposal | tanh
|
||||
```
|
||||
|
||||
### 支持的TensorFlow算子
|
||||
|
||||
```{table}
|
||||
tf.abs | tf.nn.rnn_cell_GRUCell | tf.negative
|
||||
tf.add | tf.nn.dynamic_rnn | tf.pad
|
||||
tf.nn.bias_add | tf.nn.rnn_cell_GRUCell | tf.transpose
|
||||
tf.add_n | tf.greater | tf.nn.avg_pool
|
||||
tf.argmin | tf.greater_equal | tf.nn.max_pool
|
||||
tf.argmax | tf.image.resize_bilinear | tf.reduce_mean
|
||||
tf.batch_to_space_nd | tf.image.resize_nearest_neighbor | tf.nn.max_pool_with_argmax
|
||||
tf.nn.batch_normalization | tf.contrib.layers.instance_norm | tf.pow
|
||||
tf.nn.fused_batchnorm | tf.nn.fused_batch_norm | tf.reduce_mean
|
||||
tf.cast | tf.stack | tf.reduce_sum
|
||||
tf.clip_by_value | tf.nn.sigmoid | tf.reverse
|
||||
tf.concat | tf.signal.frame | tf.reverse_sequence
|
||||
tf.nn.conv1d | tf.slice | tf.nn.relu
|
||||
tf.nn.conv2d | tf.nn.softmax | tf.nn.relu6
|
||||
tf.nn.depthwise_conv2d | tf.space_to_batch_nd | tf.rsqrt
|
||||
tf.nn.conv1d | tf.space_to_depth | tf.realdiv
|
||||
tf.nn.conv3d | tf.nn.local_response_normalization | tf.reshape
|
||||
tf.image.crop_and_resize | tf.nn.l2_normalize | tf.expand_dims
|
||||
tf.nn.conv2d_transposed | tf.nn.rnn_cell_LSTMCelltf.nn_dynamic_rnn | tf.squeeze
|
||||
tf.depth_to_space | tf.rnn_cell.LSTMCell | tf.strided_slice
|
||||
tf.equal | tf.less | tf.sqrt
|
||||
tf.exp | tf.less_equal | tf.square
|
||||
tf.nn.elu | tf.logical_or | tf.subtract
|
||||
tf.nn.embedding_lookup | tf.logical_add | tf.scatter_nd
|
||||
tf.maximum | tf.nn.leaky_relu | tf.split
|
||||
tf.floor | tf.multiply | tf.nn.swish
|
||||
tf.matmul | tf.nn.moments | tf.tile
|
||||
tf.floordiv | tf.minimum | tf.nn.tanh
|
||||
tf.gather_nd | tf.matmul | tf.unstack
|
||||
tf.gather | tf.batch_matmul | tf.where
|
||||
tf.nn.embedding_lookup | tf.not_equal | tf.select
|
||||
```
|
||||
|
||||
### 支持的ONNX算子
|
||||
|
||||
```{table}
|
||||
ArgMin | LeakyRelu | ReverseSequence
|
||||
ArgMax | Less | ReduceMax
|
||||
Add | LSTM | ReduceMin
|
||||
Abs | MatMul | ReduceL1
|
||||
And | Max | ReduceL2
|
||||
BatchNormalization | Min | ReduceLogSum
|
||||
Clip | MaxPool | ReduceLogSumExp
|
||||
Cast | AveragePool | ReduceSumSquare
|
||||
Concat | Globa | Reciprocal
|
||||
ConvTranspose | lAveragePool | Resize
|
||||
Conv | GlobalMaxPool | Sum
|
||||
Div | MaxPool | SpaceToDepth
|
||||
Dropout | AveragePool | Sqrt
|
||||
DepthToSpace | Mul | Split
|
||||
DequantizeLinear | Neg | Slice
|
||||
Equal | Or | Squeeze
|
||||
Exp | Prelu | Softmax
|
||||
Elu | Pad | Sub
|
||||
Expand | POW | Sigmoid
|
||||
Floor | QuantizeLinear | Softsign
|
||||
InstanceNormalization | QLinearMatMul | Softplus
|
||||
Gemm | QLinearConv | Sin
|
||||
Gather | Relu | Tile
|
||||
Greater | Reshape | Transpose
|
||||
GatherND | Squeeze | Tanh
|
||||
GRU | Unsqueeze | Upsample
|
||||
Logsoftmax | Flatten | Where
|
||||
LRN | ReduceSum | Xor
|
||||
Log | ReduceMean | |
|
||||
```
|
||||
|
||||
### 支持的Darknet算子
|
||||
|
||||
```{table}
|
||||
avgpool | maxpool | softmax
|
||||
batch_normalize | mish | shortcut
|
||||
connected | region | scale_channels
|
||||
convolutional | reorg | swish
|
||||
depthwise_convolutional | relu | upsample
|
||||
leaky | route | yolo
|
||||
logistic
|
||||
```
|
||||
|
||||
<!-- ## 数据准备
|
||||
|
||||
对于不同框架下训练的模型，需要准备不同的数据，所有的数据都需要放在同一个文件夹下。
|
||||
模型名和文件名需要保持一致。
|
||||
|
||||
### caffe
|
||||
|
||||
转换 caffe 模型时，模型工程目录应包含以下文件：
|
||||
|
||||
- 以 .prototxt 结尾的模型结构定义文件
|
||||
- 以 .caffemode 结尾的模型权重文件
|
||||
- dataset.txt 包含数据路径的文本文件（支持图像和NPY格式）
|
||||
|
||||
以 lenet_caffe 为例，初始目录为：
|
||||
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg # 校准数据
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
├── lenet_caffe.caffemodel # caffe 模型权重
|
||||
└── lenet_caffe.prototxt # caffe 模型结构
|
||||
```
|
||||
|
||||
### tensorflow
|
||||
|
||||
转换 tenrsorflow 模型时，模型工程目录应包含以下文件：
|
||||
|
||||
- .pb 文件：冻结图模型文件
|
||||
- inputs_outputs.txt：输入输出节点定义文件
|
||||
- dataset.txt：数据路径配置文件
|
||||
|
||||
以 lenet 为例，初始目录为：
|
||||
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg # 校准数据
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
├── inputs_outputs.txt # 输入输出节点定义文件
|
||||
└── lenet.pb # 冻结图模型文件
|
||||
```
|
||||
|
||||
### darknet
|
||||
|
||||
转换Darknet模型需准备：
|
||||
|
||||
- .cfg 文件：网络结构配置文件
|
||||
- .weights 文件：训练权重文件
|
||||
- .dataset.txt：数据路径配置文件
|
||||
|
||||
以 yolov4_tiny 为例，初始目录为：
|
||||
|
||||
```bash
|
||||
yolov4_tiny/
|
||||
├── 0.jpg # 校准数据
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
├── yolov4_tiny.cfg # 网络结构配置文件
|
||||
└── yolov4_tiny.weights # 预训练权重文件
|
||||
```
|
||||
|
||||
### onnx
|
||||
|
||||
转换ONNX模型需准备：
|
||||
|
||||
- .onnx 文件：网络模型
|
||||
- dataset.txt：数据路径配置文件
|
||||
|
||||
以 yolov5s 为例，初始目录为：
|
||||
|
||||
```bash
|
||||
yolov5s/
|
||||
├── 0.jpg # 校准数据
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
└── yolov5s.onnx # 网络模型
|
||||
``` -->
|
||||
|
||||
## 配置文件说明
|
||||
|
||||
Inputmeta.yml 是 config 生成的配置文件模版，该文件用于为Netrans中间模型配置输入层数据集合。
|
||||
Netrans中的量化、推理、导出和图片转dat的操作都需要用到这个文件。
|
||||
Inputmeta.yml内容如下：
|
||||
|
||||
```yaml
|
||||
%YAML 1.2
|
||||
---
|
||||
# !!!This file disallow TABs!!!
|
||||
# "category" allowed values: "image, undefined"
|
||||
# "database" allowed types: "H5FS, SQLITE, TEXT, LMDB, NPY, GENERATOR"
|
||||
# "tensor_name" only support in H5FS database
|
||||
# "preproc_type" allowed types:"IMAGE_RGB, IMAGE_RGB888_PLANAR, IMAGE_RGB888_PLANAR_SEP,
|
||||
IMAGE_I420,
|
||||
# IMAGE_NV12, IMAGE_YUV444, IMAGE_GRAY, IMAGE_BGRA, TENSOR"
|
||||
input_meta:
|
||||
databases:
|
||||
- path: dataset.txt
|
||||
type: TEXT
|
||||
ports:
|
||||
- lid: data_0
|
||||
category: image
|
||||
dtype: float32
|
||||
sparse: false
|
||||
tensor_name:
|
||||
layout: nhwc
|
||||
shape:
|
||||
- 50
|
||||
- 224
|
||||
- 224
|
||||
- 3
|
||||
preprocess:
|
||||
reverse_channel: false
|
||||
mean:
|
||||
- 103.94
|
||||
- 116.78
|
||||
- 123.67
|
||||
scale: 0.017
|
||||
preproc_node_params:
|
||||
preproc_type: IMAGE_RGB
|
||||
add_preproc_node: false
|
||||
preproc_perm:
|
||||
- 0
|
||||
- 1
|
||||
- 2
|
||||
- 3
|
||||
- lid: label_0
|
||||
redirect_to_output: true
|
||||
category: undefined
|
||||
tensor_name:
|
||||
dtype: float32
|
||||
shape:
|
||||
- 1
|
||||
- 1
|
||||
```
|
||||
|
||||
参数说明：
|
||||
|
||||
```{table}
|
||||
| 参数 | 说明 |
|
||||
| :--- | ---
|
||||
| input_meta | 预处理参数配置申明。 |
|
||||
| databases | 数据配置，包括设置 path、type 和 ports 。|
|
||||
| path | 数据集文件的相对（执行目录）或绝对路径。默认为 dataset.txt, 不建议修改。 |
|
||||
| type | 数据集文件格式，固定为TEXT。 |
|
||||
| ports | 指向网络中的输入或重定向的输入，目前只支持一个输入，如果网络存在多个输入，请与@ccyh联系。 |
|
||||
| lid | 输入层的lid |
|
||||
| category | 输入的类别。将此参数设置为以下值之一：image（图像输入）或 undefined（其他类型的输入）。 |
|
||||
| dtype | 输入张量的数据类型，用于将数据发送到 pnna 网络的输入端口。支持的数据类型包括 float32 和 quantized。 |
|
||||
| sparse | 指定网络张量是否以稀疏格式存在。将此参数设置为以下值之一：true（稀疏格式）或 false（压缩格式）。 |
|
||||
| tensor_name | 留空此参数 |
|
||||
| layout | 输入张量的格式，使用 nchw 用于 Caffe、Darknet、ONNX 和 PyTorch 模型。使用 nhwc 用于 TensorFlow、TensorFlow Lite 和 Keras 模型。 |
|
||||
| shape | 此张量的形状。第一维，shape[0]，表示每批的输入数量，允许在一次推理操作之前将多个输入发送到网络。如果batch维度设置为0，则需要从命令行指定--batch-size。如果 batch维度设置为大于1的值，则直接使用inputmeta.yml中的batch size并忽略命令行中的--batch-size。 |
|
||||
| fitting | 保留字段 |
|
||||
| preprocess | 预处理步骤和顺序。预处理支持下面的四个参数，参数的顺序代表预处理的顺序。 |
|
||||
| reverse_channel | 指定是否保留通道顺序。将此参数设置为以下值之一：true（保留通道顺序）或 false（不保留通道顺序）。对于 TensorFlow 和 TensorFlow Lite 框架的模型使用 true。 |
|
||||
| mean | 用于每个通道的均值。 |
|
||||
| scale | 张量的缩放值。均值和缩放值用于根据公式 (inputTensor - mean) × scale 归一化输入张量。|
|
||||
| preproc_node_params | 预处理节点参数，在 OVxlib C 项目案例中启用预处理任务 |
|
||||
| add_preproc_node | 用于处理 OVxlib C 项目案例中预处理节点的插入。[true, false] 中的布尔值，表示通过配置以下参数将预处理层添加到导出的应用程序中。此参数仅在 add_preproc_node 参数设置为 true 时有效。|
|
||||
| preproc_type | 预处理节点输入类型。 [IMAGE_RGB, IMAGE_RGB888_PLANAR,IMAGE_YUV420, IMAGE_GRAY, IMAGE_BGRA, TENSOR] 中的字符串值 |
|
||||
| preproc_perm | 预处理节点输入的置换参数。 |
|
||||
| redirect_to_output | 将database张量重定向到图形输出的特殊属性。如果为该属性设置了一个port，网络构建器将自动为该port生成一个输出层，以便后处理文件可以直接处理来自database的张量。 如果使用网络进行分类，则上例中的lid“input_0”表示输入数据集的标签lid。 请注意，redirect_to_output 必须设置为 true，以便后处理文件可以直接处理来自database的张量。 标签的lid必须与后处理文件中定义的 labels_tensor 的lid相同。 [true, false] 中的布尔值。 指定是否将由张量表示的输入端口的数据直接发送到网络输出。true（直接发送到网络输出）或 false（不直接发送到网络输出）|
|
||||
```
|
||||
|
||||
需要根据具体模型的参数对生成的inputmeta文件进行修改。
|
||||
详细说明请参考[netrans api 使用说明](docs/netrans_py.md)。
|
||||
|
|
|
|||
|
|
@ -1,4 +0,0 @@
|
|||
# Sphinx build info version 1
|
||||
# This file records the configuration used when building these files. When it is not found, a full rebuild will be done.
|
||||
config: c457bdf30d2a3c56394067910656aaac
|
||||
tags: 645f666f9bcd5a90fca523b33c5a78b7
|
||||
|
|
@ -1,166 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>config — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>config 源代码</h1><div class="highlight"><pre>
|
||||
<span></span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">subprocess</span>
|
||||
|
||||
<div class="viewcode-block" id="Config">
|
||||
<a class="viewcode-back" href="../config.html#config.Config">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">Config</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数,并基于pnnacc 生成配置文件模板</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> </span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">inputmeta_gen</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""生成配置文件模板</span>
|
||||
|
||||
<span class="sd"> Return:</span>
|
||||
<span class="sd"> None</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="n">network_name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="c1"># 进入网络名称指定的目录</span>
|
||||
<span class="c1"># os.chdir(network_name)</span>
|
||||
<span class="c1"># check_env(network_name)</span>
|
||||
|
||||
<span class="c1"># 执行 pegasus 命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> generate inputmeta --model </span><span class="si">{</span><span class="n">network_name</span><span class="si">}</span><span class="s2">.json --separated-database"</span>
|
||||
<span class="k">try</span> <span class="p">:</span>
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="k">except</span> <span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s1">'config failed'</span><span class="p">)</span></div>
|
||||
|
||||
<span class="c1"># os.chdir("..")</span>
|
||||
|
||||
<span class="c1"># def main():</span>
|
||||
|
||||
<span class="c1"># # 检查命令行参数数量是否正确</span>
|
||||
<span class="c1"># if len(sys.argv) != 2:</span>
|
||||
<span class="c1"># print("Enter a network name!")</span>
|
||||
<span class="c1"># sys.exit(2)</span>
|
||||
|
||||
<span class="c1"># # 检查提供的目录是否存在</span>
|
||||
<span class="c1"># network_name = sys.argv[1]</span>
|
||||
<span class="c1"># # 构建 netrans 可执行文件的路径</span>
|
||||
<span class="c1"># netrans_path =os.getenv('NETRANS_PATH')</span>
|
||||
<span class="c1"># cla = create_cls(netrans_path, network_name)</span>
|
||||
<span class="c1"># func = InputmetaGen(cla)</span>
|
||||
<span class="c1"># func.inputmeta_gen()</span>
|
||||
|
||||
|
||||
<span class="c1"># if __name__ == '__main__':</span>
|
||||
<span class="c1"># main()</span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,173 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>example — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>example 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="ch">#!/usr/bin/env python3</span>
|
||||
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">argparse</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">netrans</span><span class="w"> </span><span class="kn">import</span> <span class="n">Netrans</span>
|
||||
|
||||
<div class="viewcode-block" id="main">
|
||||
<a class="viewcode-back" href="../example.html#example.main">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
|
||||
<span class="c1"># 创建参数解析器</span>
|
||||
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">(</span>
|
||||
<span class="n">description</span><span class="o">=</span><span class="s1">'神经网络模型转换工具'</span><span class="p">,</span>
|
||||
<span class="n">formatter_class</span><span class="o">=</span><span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentDefaultsHelpFormatter</span> <span class="c1"># 自动显示默认值</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># 必填位置参数</span>
|
||||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||||
<span class="s1">'model_path'</span><span class="p">,</span>
|
||||
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
|
||||
<span class="n">help</span><span class="o">=</span><span class="s1">'输入模型路径（必须参数）'</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
<span class="c1"># 可选参数组</span>
|
||||
<span class="n">quant_group</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">add_argument_group</span><span class="p">(</span><span class="s1">'量化参数'</span><span class="p">)</span>
|
||||
<span class="n">quant_group</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||||
<span class="s1">'-q'</span><span class="p">,</span> <span class="s1">'--quantize_type'</span><span class="p">,</span>
|
||||
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
|
||||
<span class="n">choices</span><span class="o">=</span><span class="p">[</span><span class="s1">'uint8'</span><span class="p">,</span> <span class="s1">'int8'</span><span class="p">,</span> <span class="s1">'int16'</span><span class="p">,</span> <span class="s1">'float'</span><span class="p">],</span>
|
||||
<span class="n">default</span><span class="o">=</span><span class="s1">'uint8'</span><span class="p">,</span>
|
||||
<span class="n">metavar</span><span class="o">=</span><span class="s1">'TYPE'</span><span class="p">,</span>
|
||||
<span class="n">help</span><span class="o">=</span><span class="s1">'量化类型（可选值：</span><span class="si">%(choices)s</span><span class="s1">）'</span>
|
||||
<span class="p">)</span>
|
||||
<span class="n">quant_group</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||||
<span class="s1">'-m'</span><span class="p">,</span> <span class="s1">'--mean'</span><span class="p">,</span>
|
||||
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span>
|
||||
<span class="n">default</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
|
||||
<span class="n">help</span><span class="o">=</span><span class="s1">'归一化均值（默认：</span><span class="si">%(default)s</span><span class="s1">）'</span>
|
||||
<span class="p">)</span>
|
||||
<span class="n">quant_group</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||||
<span class="s1">'-s'</span><span class="p">,</span> <span class="s1">'--scale'</span><span class="p">,</span>
|
||||
<span class="nb">type</span><span class="o">=</span><span class="nb">float</span><span class="p">,</span>
|
||||
<span class="n">default</span><span class="o">=</span><span class="mf">1.0</span><span class="p">,</span>
|
||||
<span class="n">help</span><span class="o">=</span><span class="s1">'量化缩放系数（默认：</span><span class="si">%(default)s</span><span class="s1">）'</span>
|
||||
<span class="p">)</span>
|
||||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||||
<span class="s1">'-p'</span><span class="p">,</span> <span class="s1">'--profile'</span><span class="p">,</span>
|
||||
<span class="n">action</span><span class="o">=</span><span class="s1">'store_true'</span><span class="p">,</span> <span class="c1"># 设置为True当参数存在时</span>
|
||||
<span class="n">help</span><span class="o">=</span><span class="s1">'启用性能分析模式（默认：</span><span class="si">%(default)s</span><span class="s1">）'</span>
|
||||
<span class="p">)</span>
|
||||
|
||||
|
||||
<span class="c1"># 解析参数</span>
|
||||
<span class="n">args</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># 执行模型转换</span>
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="n">model</span> <span class="o">=</span> <span class="n">Netrans</span><span class="p">(</span><span class="n">model_path</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">model_path</span><span class="p">)</span>
|
||||
<span class="n">model</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span>
|
||||
<span class="n">quantize_type</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">quantize_type</span><span class="p">,</span>
|
||||
<span class="n">mean</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">mean</span><span class="p">,</span>
|
||||
<span class="n">scale</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">scale</span><span class="p">,</span>
|
||||
<span class="n">profile</span><span class="o">=</span><span class="n">args</span><span class="o">.</span><span class="n">profile</span>
|
||||
<span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"模型 </span><span class="si">{</span><span class="n">args</span><span class="o">.</span><span class="n">model_path</span><span class="si">}</span><span class="s2"> 转换成功"</span><span class="p">)</span>
|
||||
<span class="k">except</span> <span class="ne">FileNotFoundError</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"错误：模型文件 </span><span class="si">{</span><span class="n">args</span><span class="o">.</span><span class="n">model_path</span><span class="si">}</span><span class="s2"> 不存在"</span><span class="p">)</span>
|
||||
<span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
|
||||
<span class="n">main</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,285 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>export — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>export 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">subprocess</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">shutil</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
<span class="c1"># 检查 NETRANS_PATH 环境变量是否设置</span>
|
||||
|
||||
<span class="c1"># 定义数据集文件路径</span>
|
||||
<span class="n">dataset</span> <span class="o">=</span> <span class="s1">'dataset.txt'</span>
|
||||
|
||||
<div class="viewcode-block" id="Export">
|
||||
<a class="viewcode-back" href="../export.html#export.Export">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">Export</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导出模型ngb文件</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> </span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">export_network</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""基于 pnnacc 导出模型</span>
|
||||
<span class="sd"> """</span>
|
||||
|
||||
<span class="n">netrans</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="n">quantized</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantize_type</span>
|
||||
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans_path</span>
|
||||
|
||||
<span class="n">ovxgenerator</span> <span class="o">=</span> <span class="n">netrans</span> <span class="o">+</span> <span class="s2">" export ovxlib"</span>
|
||||
<span class="c1"># 进入模型目录</span>
|
||||
<span class="c1"># os.chdir(name)</span>
|
||||
|
||||
<span class="c1"># 根据量化类型设置参数</span>
|
||||
<span class="k">if</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'float'</span><span class="p">:</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'float'</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'none_quantized'</span>
|
||||
<span class="n">generate_path</span> <span class="o">=</span> <span class="s1">'./wksp/none_quantized'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'uint8'</span><span class="p">:</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'asymmetric_affine'</span>
|
||||
<span class="n">generate_path</span> <span class="o">=</span> <span class="s1">'./wksp/asymmetric_affine'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'int8'</span><span class="p">:</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'dynamic_fixed_point-8'</span>
|
||||
<span class="n">generate_path</span> <span class="o">=</span> <span class="s1">'./wksp/dynamic_fixed_point-8'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'int16'</span><span class="p">:</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'dynamic_fixed_point-16'</span>
|
||||
<span class="n">generate_path</span> <span class="o">=</span> <span class="s1">'./wksp/dynamic_fixed_point-16'</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== wrong quantization_type ! ( float / uint8 / int8 / int16 )==========="</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 创建输出目录</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">makedirs</span><span class="p">(</span><span class="n">generate_path</span><span class="p">,</span> <span class="n">exist_ok</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建命令</span>
|
||||
<span class="k">if</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'float'</span><span class="p">:</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">ovxgenerator</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --dtype </span><span class="si">{</span><span class="n">type_</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --pack-nbg-viplite </span><span class="se">\</span>
|
||||
<span class="s2"> --optimize 'VIP8000NANOQI_PLUS_PID0XB1'</span><span class="se">\</span>
|
||||
<span class="s2"> --target-ide-project 'linux64' </span><span class="se">\</span>
|
||||
<span class="s2"> --viv-sdk </span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2">/pnna_sdk </span><span class="se">\</span>
|
||||
<span class="s2"> --output-path </span><span class="si">{</span><span class="n">generate_path</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize"</span><span class="p">):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m Can not find </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
||||
<span class="k">else</span> <span class="p">:</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_postprocess_file.yml"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">ovxgenerator</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --dtype </span><span class="si">{</span><span class="n">type_</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --pack-nbg-viplite </span><span class="se">\</span>
|
||||
<span class="s2"> --optimize 'VIP8000NANOQI_PLUS_PID0XB1'</span><span class="se">\</span>
|
||||
<span class="s2"> --viv-sdk </span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2">/pnna_sdk </span><span class="se">\</span>
|
||||
<span class="s2"> --model-quantize </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize </span><span class="se">\</span>
|
||||
<span class="s2"> --with-input-meta </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_inputmeta.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --target-ide-project 'linux64' </span><span class="se">\</span>
|
||||
<span class="s2"> --output-path </span><span class="si">{</span><span class="n">generate_path</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">ovxgenerator</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --dtype </span><span class="si">{</span><span class="n">type_</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --pack-nbg-viplite </span><span class="se">\</span>
|
||||
<span class="s2"> --optimize 'VIP8000NANOQI_PLUS_PID0XB1'</span><span class="se">\</span>
|
||||
<span class="s2"> --viv-sdk </span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2">/pnna_sdk </span><span class="se">\</span>
|
||||
<span class="s2"> --model-quantize </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize </span><span class="se">\</span>
|
||||
<span class="s2"> --with-input-meta </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_inputmeta.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --target-ide-project 'linux64' </span><span class="se">\</span>
|
||||
<span class="s2"> --postprocess-file </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_postprocess_file.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --output-path </span><span class="si">{</span><span class="n">generate_path</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="k">if</span> <span class="n">result</span><span class="o">.</span><span class="n">returncode</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m SUCCESS </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m ERROR ! </span><span class="si">{</span><span class="n">result</span><span class="o">.</span><span class="n">stderr</span><span class="si">}</span><span class="s2"> </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
|
||||
|
||||
<span class="c1"># temp='wksp/temp'</span>
|
||||
<span class="c1"># os.makedirs(temp, exist_ok=True)</span>
|
||||
|
||||
<span class="n">source_dir</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">generate_path</span><span class="si">}</span><span class="s2">_nbg_viplite"</span>
|
||||
<span class="n">target_dir</span> <span class="o">=</span> <span class="n">generate_path</span>
|
||||
<span class="n">src_ngb</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">source_dir</span><span class="si">}</span><span class="s2">/network_binary.nb"</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">profile</span><span class="p">:</span>
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="c1"># 如果目标路径已存在，先删除（确保移动操作能成功）</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">target_dir</span><span class="p">):</span>
|
||||
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">target_dir</span><span class="p">)</span>
|
||||
<span class="c1"># 移动整个目录到目标位置</span>
|
||||
<span class="n">shutil</span><span class="o">.</span><span class="n">move</span><span class="p">(</span><span class="n">source_dir</span><span class="p">,</span> <span class="n">target_dir</span><span class="p">)</span>
|
||||
<span class="c1"># print(f"Successfully moved directory {source_dir} to {target_dir}")</span>
|
||||
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># 非零退出码表示错误</span>
|
||||
<span class="c1"># print(f"Error moving directory: {e}")</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="c1"># 仅复制network_binary.nb文件</span>
|
||||
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">generate_path</span><span class="p">)</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">mkdir</span><span class="p">(</span><span class="n">generate_path</span><span class="p">)</span>
|
||||
<span class="n">shutil</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span><span class="n">src_ngb</span><span class="p">,</span> <span class="n">generate_path</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># print(f"Successfully copied {src_ngb} to {generate_path}")</span>
|
||||
<span class="k">except</span> <span class="ne">FileNotFoundError</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Error: </span><span class="si">{</span><span class="n">src_ngb</span><span class="si">}</span><span class="s2"> is not found"</span><span class="p">)</span>
|
||||
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Error occurred: </span><span class="si">{</span><span class="n">e</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||||
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="c1"># 清理源目录</span>
|
||||
<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">source_dir</span><span class="p">)</span>
|
||||
<span class="c1"># print(f"Removed source directory {source_dir}")</span>
|
||||
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||||
<span class="c1"># print(f"Error removing directory: {e}")</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="c1"># 非零退出码表示错误</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="main">
|
||||
<a class="viewcode-back" href="../export.html#export.main">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
|
||||
<span class="c1"># 检查命令行参数数量</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Input a network name and quantized type ( float / uint8 / int8 / int16 )"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
||||
<span class="c1"># 检查网络目录是否存在</span>
|
||||
<span class="n">network_name</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="c1"># check_env(network_name)</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">network_name</span><span class="p">)):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Directory </span><span class="si">{</span><span class="n">network_name</span><span class="si">}</span><span class="s2"> does not exist !"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||||
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'NETRANS_PATH'</span><span class="p">]</span>
|
||||
<span class="c1"># netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')</span>
|
||||
<span class="c1"># 调用导出函数ss</span>
|
||||
<span class="n">cla</span> <span class="o">=</span> <span class="n">create_cls</span><span class="p">(</span><span class="n">netrans_path</span><span class="p">,</span> <span class="n">network_name</span><span class="p">,</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">])</span>
|
||||
<span class="n">func</span> <span class="o">=</span> <span class="n">Export</span><span class="p">(</span><span class="n">cla</span><span class="p">)</span>
|
||||
<span class="n">func</span><span class="o">.</span><span class="n">export_network</span><span class="p">()</span></div>
|
||||
|
||||
|
||||
<span class="c1"># export_network(netrans, network_name, sys.argv[2])</span>
|
||||
|
||||
|
||||
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="n">main</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,443 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>import_model — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>import_model 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">subprocess</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
|
||||
<div class="viewcode-block" id="check_status">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.check_status">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">check_status</span><span class="p">(</span><span class="n">result</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""解析命令执行情况</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> result (return of subprocrss.run): subprocess.run的返回值</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="n">result</span><span class="o">.</span><span class="n">returncode</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m LOAD MODEL SUCCESS </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m ERROR: </span><span class="si">{</span><span class="n">result</span><span class="o">.</span><span class="n">stderr</span><span class="si">}</span><span class="s2"> </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
|
||||
<div class="viewcode-block" id="import_caffe_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_caffe_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_caffe_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 caffe 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的路径</span>
|
||||
<span class="n">convert_caffe</span> <span class="o">=</span><span class="n">netrans_path</span> <span class="o">+</span> <span class="s2">" import caffe"</span>
|
||||
|
||||
<span class="c1"># 定义模型文件路径</span>
|
||||
<span class="n">model_json_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json"</span>
|
||||
<span class="n">model_data_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span>
|
||||
<span class="n">model_prototxt_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.prototxt"</span>
|
||||
<span class="n">model_caffemodel_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.caffemodel"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> Caffe model ==========="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">model_caffemodel_path</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_caffe</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">model_prototxt_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --weights </span><span class="si">{</span><span class="n">model_caffemodel_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">model_json_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">model_data_path</span><span class="si">}</span><span class="s2">"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== fake Caffe model data file ============="</span><span class="p">)</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_caffe</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">model_prototxt_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">model_json_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">model_data_path</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="c1"># os.system(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="import_tensorflow_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_tensorflow_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_tensorflow_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 tensorflow 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的命令</span>
|
||||
<span class="n">convertf_cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> import tensorflow"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> Tensorflow model ==========="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 读取 inputs_outputs.txt 文件中的参数</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s1">'inputs_outputs.txt'</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
|
||||
<span class="n">inputs_outputs_params</span> <span class="o">=</span> <span class="n">f</span><span class="o">.</span><span class="n">read</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convertf_cmd</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.pb </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> </span><span class="si">{</span><span class="n">inputs_outputs_params</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span></div>
|
||||
|
||||
|
||||
<span class="c1"># result = subprocess.run(cmd, shell=True, capture_output=True, text=True)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="c1"># check_status(result)</span>
|
||||
|
||||
<div class="viewcode-block" id="import_onnx_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_onnx_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_onnx_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 onnx 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的命令</span>
|
||||
<span class="n">convert_onnx_cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> import onnx"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> ONNX model ==========="</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_outputs.txt"</span><span class="p">):</span>
|
||||
<span class="n">output_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">(),</span> <span class="n">name</span><span class="o">+</span><span class="s2">"_outputs.txt"</span><span class="p">)</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">output_path</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf-8'</span><span class="p">)</span> <span class="k">as</span> <span class="n">file</span><span class="p">:</span>
|
||||
<span class="n">outputs</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">file</span><span class="o">.</span><span class="n">readline</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
|
||||
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_onnx_cmd</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.onnx </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --outputs '</span><span class="si">{</span><span class="n">outputs</span><span class="si">}</span><span class="s2">'"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_onnx_cmd</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.onnx </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span></div>
|
||||
|
||||
|
||||
<span class="c1"># result = subprocess.run(cmd, shell=True, capture_output=True, text=True)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="c1"># check_status(result)</span>
|
||||
|
||||
<span class="c1">####### TFLITE</span>
|
||||
<div class="viewcode-block" id="import_tflite_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_tflite_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_tflite_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 tflite 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的路径或命令 </span>
|
||||
<span class="n">convert_tflite</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> import tflite"</span>
|
||||
|
||||
<span class="c1"># 定义模型文件路径</span>
|
||||
<span class="n">model_json_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json"</span>
|
||||
<span class="n">model_data_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span>
|
||||
<span class="n">model_tflite_path</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.tflite"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> TFLite model ==========="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_tflite</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">model_tflite_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">model_json_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">model_data_path</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span></div>
|
||||
|
||||
|
||||
<span class="c1"># result = subprocess.run(cmd, shell=True, capture_output=True, text=True)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="c1"># check_status(result)</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="import_darknet_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_darknet_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_darknet_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 darknet 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的命令</span>
|
||||
<span class="n">convert_darknet_cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> import darknet"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> darknet model ==========="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_darknet_cmd</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.cfg </span><span class="se">\</span>
|
||||
<span class="s2"> --weight </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.weights </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span>
|
||||
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="n">check_status</span><span class="p">(</span><span class="n">result</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="import_pytorch_network">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.import_pytorch_network">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_pytorch_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""导入 pytorch 模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> name (str): 模型名字</span>
|
||||
<span class="sd"> netrans_path (str): 模型路径</span>
|
||||
|
||||
<span class="sd"> Returns:</span>
|
||||
<span class="sd"> cmd (str): 生成的pnnacc 命令行, 被subprocesses执行</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="c1"># 定义转换工具的命令</span>
|
||||
<span class="n">convert_pytorch_cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans_path</span><span class="si">}</span><span class="s2"> import pytorch"</span>
|
||||
|
||||
<span class="c1"># 打印转换信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"=========== Converting </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> pytorch model ==========="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 读取 input_size.txt 文件中的参数</span>
|
||||
<span class="k">try</span><span class="p">:</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s1">'input_size.txt'</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">)</span> <span class="k">as</span> <span class="n">file</span><span class="p">:</span>
|
||||
<span class="n">input_size_params</span> <span class="o">=</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">file</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span>
|
||||
<span class="k">except</span> <span class="ne">FileNotFoundError</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Error: input_size.txt not found."</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建转换命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">convert_pytorch_cmd</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.pt </span><span class="se">\</span>
|
||||
<span class="s2"> --output-model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --output-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> </span><span class="si">{</span><span class="n">input_size_params</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="c1"># 执行转换命令</span>
|
||||
<span class="c1"># print(cmd)</span>
|
||||
<span class="k">return</span> <span class="n">cmd</span>
|
||||
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="n">check_status</span><span class="p">(</span><span class="n">result</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<span class="c1"># 使用示例</span>
|
||||
<span class="c1"># import_tensorflow_network('model_name', '/path/to/NETRANS_PATH')</span>
|
||||
<div class="viewcode-block" id="ImportModel">
|
||||
<a class="viewcode-back" href="../import_model.html#import_model.ImportModel">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">ImportModel</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导入模型</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="sd">"""从实例化的 Netrans 中解析模型参数</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息</span>
|
||||
<span class="sd"> </span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
<span class="c1"># print(source_obj.__dict__)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">import_network</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""基于 pnnacc 导入模型</span>
|
||||
|
||||
<span class="sd"> Raises:</span>
|
||||
<span class="sd"> FileExistsError: 如果不存在模型文件则会报错 FileExistsError</span>
|
||||
<span class="sd"> RuntimeError: 如果执行导入失败则会报 RuntimeError</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="ow">is</span> <span class="kc">True</span> <span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"begin load model"</span><span class="p">)</span>
|
||||
<span class="c1"># print(self.model_path)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">())</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="bp">self</span><span class="o">.</span><span class="n">model_name</span><span class="si">}</span><span class="s2">.weights"</span><span class="p">)</span>
|
||||
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.prototxt"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_caffe_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.pb"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_tensorflow_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.onnx"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_onnx_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.tflite"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_tflite_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.weights"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_darknet_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">elif</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.pt"</span><span class="p">):</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="n">import_pytorch_network</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="k">else</span> <span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">FileExistsError</span><span class="p">(</span><span class="s2">"Can not find suitable model files"</span><span class="p">)</span>
|
||||
<span class="k">try</span> <span class="p">:</span>
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
<span class="k">except</span> <span class="p">:</span>
|
||||
<span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">"load model failed"</span><span class="p">)</span>
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="n">check_status</span><span class="p">(</span><span class="n">result</span><span class="p">)</span></div>
|
||||
|
||||
<span class="c1"># os.chdir("..") </span>
|
||||
|
||||
|
||||
<span class="c1"># def main():</span>
|
||||
<span class="c1"># if len(sys.argv) != 2 :</span>
|
||||
<span class="c1"># print("Input a network")</span>
|
||||
<span class="c1"># sys.exit(-1)</span>
|
||||
|
||||
<span class="c1"># network_name = sys.argv[1]</span>
|
||||
<span class="c1"># # check_env(network_name)</span>
|
||||
|
||||
<span class="c1"># netrans_path = os.environ['NETRANS_PATH']</span>
|
||||
<span class="c1"># # netrans = os.path.join(netrans_path, 'pnnacc')</span>
|
||||
<span class="c1"># clas = create_cls(netrans_path, network_name,verbose=False)</span>
|
||||
<span class="c1"># func = ImportModel(clas)</span>
|
||||
<span class="c1"># func.import_network()</span>
|
||||
<span class="c1"># if __name__ == "__main__":</span>
|
||||
<span class="c1"># main() </span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,109 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>概览：模块代码 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>代码可用的所有模块</h1>
|
||||
<ul><li><a href="config.html">config</a></li>
|
||||
<li><a href="example.html">example</a></li>
|
||||
<li><a href="export.html">export</a></li>
|
||||
<li><a href="import_model.html">import_model</a></li>
|
||||
<li><a href="infer.html">infer</a></li>
|
||||
<li><a href="quantize.html">quantize</a></li>
|
||||
<li><a href="quantize_hb.html">quantize_hb</a></li>
|
||||
<li><a href="utils.html">utils</a></li>
|
||||
</ul>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,204 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>infer — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>infer 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">subprocess</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
|
||||
<div class="viewcode-block" id="Infer">
|
||||
<a class="viewcode-back" href="../infer.html#infer.Infer">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">Infer</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">inference_network</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">netrans</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="n">quantized</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantize_type</span>
|
||||
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="c1"># print(self.__dict__)</span>
|
||||
|
||||
<span class="n">netrans</span> <span class="o">+=</span> <span class="s2">" inference"</span>
|
||||
<span class="c1"># 进入模型目录</span>
|
||||
|
||||
<span class="c1"># 定义类型和量化类型</span>
|
||||
<span class="k">if</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'float'</span><span class="p">:</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'float32'</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'float32'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'uint8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'asymmetric_affine'</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'int8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'dynamic_fixed_point-8'</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="k">elif</span> <span class="n">quantized</span> <span class="o">==</span> <span class="s1">'int16'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s1">'dynamic_fixed_point-16'</span>
|
||||
<span class="n">type_</span> <span class="o">=</span> <span class="s1">'quantized'</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== wrong quantization_type ! ( float / uint8 / int8 / int16 )==========="</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建推理命令</span>
|
||||
<span class="n">inf_path</span> <span class="o">=</span> <span class="s1">'./inf'</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --dtype </span><span class="si">{</span><span class="n">type_</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --batch-size 1 </span><span class="se">\</span>
|
||||
<span class="s2"> --model-quantize </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --output-dir </span><span class="si">{</span><span class="n">inf_path</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --with-input-meta </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_inputmeta.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --device CPU"</span>
|
||||
|
||||
<span class="c1"># 执行推理命令</span>
|
||||
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="ow">is</span> <span class="kc">True</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span>
|
||||
<span class="n">result</span> <span class="o">=</span> <span class="n">subprocess</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">cmd</span><span class="p">,</span> <span class="n">shell</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">capture_output</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">text</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查执行结果</span>
|
||||
<span class="k">if</span> <span class="n">result</span><span class="o">.</span><span class="n">returncode</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[32m SUCCESS </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m ERROR: </span><span class="si">{</span><span class="n">result</span><span class="o">.</span><span class="n">stderr</span><span class="si">}</span><span class="s2"> </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<span class="c1"># 返回原始目录</span>
|
||||
|
||||
<div class="viewcode-block" id="main">
|
||||
<a class="viewcode-back" href="../infer.html#infer.main">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
|
||||
<span class="c1"># 检查命令行参数数量</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Input a network name and quantized type ( float / uint8 / int8 / int16 )"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查网络目录是否存在</span>
|
||||
<span class="n">network_name</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">network_name</span><span class="p">):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Directory </span><span class="si">{</span><span class="n">network_name</span><span class="si">}</span><span class="s2"> does not exist !"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">2</span><span class="p">)</span>
|
||||
<span class="c1"># print("here")</span>
|
||||
<span class="c1"># 定义 netrans 路径</span>
|
||||
<span class="c1"># netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')</span>
|
||||
<span class="n">network_name</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||||
<span class="c1"># check_env(network_name)</span>
|
||||
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'NETRANS_PATH'</span><span class="p">]</span>
|
||||
<span class="c1"># netrans = os.path.join(netrans_path, 'pnnacc')</span>
|
||||
<span class="n">quantize_type</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
|
||||
<span class="n">cla</span> <span class="o">=</span> <span class="n">create_cls</span><span class="p">(</span><span class="n">netrans_path</span><span class="p">,</span> <span class="n">network_name</span><span class="p">,</span><span class="n">quantize_type</span><span class="p">,</span><span class="kc">False</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 调用量化函数</span>
|
||||
<span class="n">func</span> <span class="o">=</span> <span class="n">Infer</span><span class="p">(</span><span class="n">cla</span><span class="p">)</span>
|
||||
<span class="n">func</span><span class="o">.</span><span class="n">inference_network</span><span class="p">()</span></div>
|
||||
|
||||
|
||||
<span class="c1"># 定义数据集文件路径</span>
|
||||
<span class="c1"># dataset_path = './dataset.txt'</span>
|
||||
<span class="c1"># 调用推理函数</span>
|
||||
<span class="c1"># inference_network(network_name, sys.argv[2])</span>
|
||||
|
||||
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">'__main__'</span><span class="p">:</span>
|
||||
<span class="c1"># print("main")</span>
|
||||
<span class="n">main</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,211 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>quantize — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>quantize 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
|
||||
<div class="viewcode-block" id="Quantize">
|
||||
<a class="viewcode-back" href="../quantize.html#quantize.Quantize">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">Quantize</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""</span>
|
||||
<span class="sd"> 解析 Netrans 参数，基于 pnnacc 量化模型</span>
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> cla (class): 实例化以后的 Netrans 类，需要解析里面包含的参数</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="sd">"""</span>
|
||||
<span class="sd"> 从 Netrans 类中获取模型信息</span>
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> source_obj (class): 实例化以后的 Netrans 类，需要解析里面包含的参数</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">quantize_network</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""基于 pnnacc 量化模型 </span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="n">netrans</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="n">quantized_type</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantize_type</span>
|
||||
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="c1"># check_env(name)</span>
|
||||
<span class="c1"># print(os.getcwd())</span>
|
||||
<span class="n">netrans</span> <span class="o">+=</span> <span class="s2">" quantize"</span>
|
||||
<span class="c1"># 根据量化类型设置量化参数</span>
|
||||
<span class="k">if</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'float'</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== do not need quantized==========="</span><span class="p">)</span>
|
||||
<span class="k">return</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'uint8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"asymmetric_affine"</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'int8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"dynamic_fixed_point-8"</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'int16'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"dynamic_fixed_point-16"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== wrong quantization_type ! ( uint8 / int8 / int16 )==========="</span><span class="p">)</span>
|
||||
<span class="k">return</span>
|
||||
|
||||
<span class="c1"># 输出量化信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">" ======================================================================="</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">" ==== Start Quantizing </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> model with type of </span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2"> ==="</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">" ======================================================================="</span><span class="p">)</span>
|
||||
<span class="n">current_directory</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">()</span>
|
||||
<span class="n">txt_path</span> <span class="o">=</span> <span class="n">current_directory</span><span class="o">+</span><span class="s2">"/dataset.txt"</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">txt_path</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf-8'</span><span class="p">)</span> <span class="k">as</span> <span class="n">file</span><span class="p">:</span>
|
||||
<span class="n">num_lines</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">file</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span>
|
||||
|
||||
<span class="c1"># 移除已存在的量化文件</span>
|
||||
<span class="n">quantize_file</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize"</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">quantize_file</span><span class="p">):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m rm </span><span class="si">{</span><span class="n">quantize_file</span><span class="si">}</span><span class="s2"> </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">quantize_file</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 构建并执行量化命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --batch-size 1 </span><span class="se">\</span>
|
||||
<span class="s2"> --qtype </span><span class="si">{</span><span class="n">quantized_type</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --rebuild </span><span class="se">\</span>
|
||||
<span class="s2"> --quantizer </span><span class="si">{</span><span class="n">quantization_type</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model-quantize </span><span class="si">{</span><span class="n">quantize_file</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --with-input-meta </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_inputmeta.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --device CPU </span><span class="se">\</span>
|
||||
<span class="s2"> --algorithm kl_divergence </span><span class="se">\</span>
|
||||
<span class="s2"> --iterations </span><span class="si">{</span><span class="n">num_lines</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查量化结果</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">quantize_file</span><span class="p">):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m QUANTIZED SUCCESS </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m ERROR ! </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
|
||||
<span class="c1"># def main():</span>
|
||||
<span class="c1"># # 检查命令行参数数量</span>
|
||||
<span class="c1"># if len(sys.argv) < 3:</span>
|
||||
<span class="c1"># print("Input a network name and quantized type ( uint8 / int8 / int16 )")</span>
|
||||
<span class="c1"># sys.exit(-1)</span>
|
||||
|
||||
<span class="c1"># # 检查网络目录是否存在</span>
|
||||
<span class="c1"># network_name = sys.argv[1]</span>
|
||||
|
||||
<span class="c1"># # 定义 netrans 路径</span>
|
||||
<span class="c1"># # netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')</span>
|
||||
<span class="c1"># # network_name = sys.argv[1]</span>
|
||||
<span class="c1"># # check_env(network_name)</span>
|
||||
|
||||
<span class="c1"># netrans_path = os.environ['NETRANS_PATH']</span>
|
||||
<span class="c1"># # netrans = os.path.join(netrans_path, 'pnnacc')</span>
|
||||
<span class="c1"># quantize_type = sys.argv[2] </span>
|
||||
<span class="c1"># cla = create_cls(netrans_path, network_name,quantize_type)</span>
|
||||
|
||||
<span class="c1"># # 调用量化函数</span>
|
||||
<span class="c1"># run = Quantize(cla)</span>
|
||||
<span class="c1"># run.quantize_network()</span>
|
||||
|
||||
<span class="c1"># if __name__ == "__main__":</span>
|
||||
<span class="c1"># main() </span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,200 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>quantize_hb — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>quantize_hb 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">from</span><span class="w"> </span><span class="nn">utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">check_path</span><span class="p">,</span> <span class="n">AttributeCopier</span><span class="p">,</span> <span class="n">create_cls</span>
|
||||
|
||||
<div class="viewcode-block" id="Quantize">
|
||||
<a class="viewcode-back" href="../quantize_hb.html#quantize_hb.Quantize">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">Quantize</span><span class="p">(</span><span class="n">AttributeCopier</span><span class="p">):</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<span class="nd">@check_path</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">quantize_network</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="n">netrans</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">netrans</span>
|
||||
<span class="n">quantized_type</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">quantize_type</span>
|
||||
<span class="n">name</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">model_name</span>
|
||||
<span class="c1"># check_env(name)</span>
|
||||
<span class="c1"># print(os.getcwd())</span>
|
||||
<span class="n">netrans</span> <span class="o">+=</span> <span class="s2">" quantize"</span>
|
||||
<span class="c1"># 根据量化类型设置量化参数</span>
|
||||
<span class="k">if</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'float'</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== do not need quantized==========="</span><span class="p">)</span>
|
||||
<span class="k">return</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'uint8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"asymmetric_affine"</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'int8'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"dynamic_fixed_point-8"</span>
|
||||
<span class="k">elif</span> <span class="n">quantized_type</span> <span class="o">==</span> <span class="s1">'int16'</span><span class="p">:</span>
|
||||
<span class="n">quantization_type</span> <span class="o">=</span> <span class="s2">"dynamic_fixed_point-16"</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"=========== wrong quantization_type ! ( uint8 / int8 / int16 )==========="</span><span class="p">)</span>
|
||||
<span class="k">return</span>
|
||||
|
||||
<span class="c1"># 输出量化信息</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">" ======================================================================="</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">" ==== Start Quantizing </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2"> model with type of </span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2"> ==="</span><span class="p">)</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">" ======================================================================="</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 移除已存在的量化文件</span>
|
||||
<span class="n">quantize_file</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_</span><span class="si">{</span><span class="n">quantization_type</span><span class="si">}</span><span class="s2">.quantize"</span>
|
||||
<span class="n">current_directory</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">()</span>
|
||||
<span class="n">txt_path</span> <span class="o">=</span> <span class="n">current_directory</span><span class="o">+</span><span class="s2">"/dataset.txt"</span>
|
||||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">txt_path</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf-8'</span><span class="p">)</span> <span class="k">as</span> <span class="n">file</span><span class="p">:</span>
|
||||
<span class="n">num_lines</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">file</span><span class="o">.</span><span class="n">readlines</span><span class="p">())</span>
|
||||
|
||||
|
||||
<span class="c1"># 构建并执行量化命令</span>
|
||||
<span class="n">cmd</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">netrans</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --qtype </span><span class="si">{</span><span class="n">quantized_type</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --hybrid </span><span class="se">\</span>
|
||||
<span class="s2"> --quantizer </span><span class="si">{</span><span class="n">quantization_type</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model-quantize </span><span class="si">{</span><span class="n">quantize_file</span><span class="si">}</span><span class="s2"> </span><span class="se">\</span>
|
||||
<span class="s2"> --model </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json </span><span class="se">\</span>
|
||||
<span class="s2"> --model-data </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data </span><span class="se">\</span>
|
||||
<span class="s2"> --with-input-meta </span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">_inputmeta.yml </span><span class="se">\</span>
|
||||
<span class="s2"> --device CPU </span><span class="se">\</span>
|
||||
<span class="s2"> --algorithm kl_divergence </span><span class="se">\</span>
|
||||
<span class="s2"> --divergence-nbins 2048 </span><span class="se">\</span>
|
||||
<span class="s2"> --iterations </span><span class="si">{</span><span class="n">num_lines</span><span class="si">}</span><span class="s2">"</span>
|
||||
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">system</span><span class="p">(</span><span class="n">cmd</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查量化结果</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">quantize_file</span><span class="p">):</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m QUANTIZED SUCCESS </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span>
|
||||
<span class="k">else</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="se">\033</span><span class="s2">[31m ERROR ! </span><span class="se">\033</span><span class="s2">[0m"</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
|
||||
<div class="viewcode-block" id="main">
|
||||
<a class="viewcode-back" href="../quantize_hb.html#quantize_hb.main">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
|
||||
<span class="c1"># 检查命令行参数数量</span>
|
||||
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">)</span> <span class="o"><</span> <span class="mi">3</span><span class="p">:</span>
|
||||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Input a network name and quantized type ( uint8 / int8 / int16 )"</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 检查网络目录是否存在</span>
|
||||
<span class="n">network_name</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||||
|
||||
<span class="c1"># 定义 netrans 路径</span>
|
||||
<span class="c1"># netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')</span>
|
||||
<span class="c1"># network_name = sys.argv[1]</span>
|
||||
<span class="c1"># check_env(network_name)</span>
|
||||
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s1">'NETRANS_PATH'</span><span class="p">]</span>
|
||||
<span class="c1"># netrans = os.path.join(netrans_path, 'pnnacc')</span>
|
||||
<span class="n">quantize_type</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">argv</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
|
||||
<span class="n">cla</span> <span class="o">=</span> <span class="n">create_cls</span><span class="p">(</span><span class="n">netrans_path</span><span class="p">,</span> <span class="n">network_name</span><span class="p">,</span><span class="n">quantize_type</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># 调用量化函数</span>
|
||||
<span class="n">run</span> <span class="o">=</span> <span class="n">Quantize</span><span class="p">(</span><span class="n">cla</span><span class="p">)</span>
|
||||
<span class="n">run</span><span class="o">.</span><span class="n">quantize_network</span><span class="p">()</span></div>
|
||||
|
||||
|
||||
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
|
||||
<span class="n">main</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,236 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="../">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>utils — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="../_static/alabaster.css?v=27fed22d" />
|
||||
<script src="../_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
|
||||
<link rel="stylesheet" href="../_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1>utils 源代码</h1><div class="highlight"><pre>
|
||||
<span></span><span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="c1"># from functools import wraps</span>
|
||||
|
||||
<span class="c1"># def check_path(netrans, model_path):</span>
|
||||
<span class="c1"># def decorator(func):</span>
|
||||
<span class="c1"># @wraps(func)</span>
|
||||
<span class="c1"># def wrapper(netrans, model_path, *args, **kargs):</span>
|
||||
<span class="c1"># check_dir(model_path)</span>
|
||||
<span class="c1"># check_netrans(netrans)</span>
|
||||
<span class="c1"># if os.getcwd() != model_path :</span>
|
||||
<span class="c1"># os.chdir(model_path)</span>
|
||||
<span class="c1"># return func(netrans, model_path, *args, **kargs)</span>
|
||||
<span class="c1"># return wrapper</span>
|
||||
<span class="c1"># return decorator</span>
|
||||
|
||||
<div class="viewcode-block" id="check_path">
|
||||
<a class="viewcode-back" href="../utils.html#utils.check_path">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">check_path</span><span class="p">(</span><span class="n">func</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">""" 装饰器, 确保在工程目录运行 nertans </span>
|
||||
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">wrapper</span><span class="p">(</span><span class="n">cla</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kargs</span><span class="p">):</span>
|
||||
<span class="n">check_netrans</span><span class="p">(</span><span class="n">cla</span><span class="o">.</span><span class="n">netrans</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">getcwd</span><span class="p">()</span> <span class="o">!=</span> <span class="n">cla</span><span class="o">.</span><span class="n">model_path</span> <span class="p">:</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">cla</span><span class="o">.</span><span class="n">model_path</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="n">func</span><span class="p">(</span><span class="n">cla</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kargs</span><span class="p">)</span>
|
||||
<span class="k">return</span> <span class="n">wrapper</span></div>
|
||||
|
||||
|
||||
|
||||
<div class="viewcode-block" id="check_dir">
|
||||
<a class="viewcode-back" href="../utils.html#utils.check_dir">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">check_dir</span><span class="p">(</span><span class="n">network_name</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""判断工程目录是否存在</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> network_name (str): 工程目录路径</span>
|
||||
|
||||
<span class="sd"> Raises:</span>
|
||||
<span class="sd"> NotADirectoryError: 没有那个工程目录</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">network_name</span><span class="p">):</span>
|
||||
<span class="k">raise</span> <span class="ne">NotADirectoryError</span><span class="p">(</span>
|
||||
<span class="sa">f</span><span class="s2">"Directory not found: </span><span class="si">{</span><span class="n">network_name</span><span class="si">}</span><span class="s2">"</span>
|
||||
<span class="p">)</span>
|
||||
<span class="c1"># print(f"Directory {network_name} does not exist !")</span>
|
||||
<span class="c1"># sys.exit(-1)</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">network_name</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="check_netrans">
|
||||
<a class="viewcode-back" href="../utils.html#utils.check_netrans">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">check_netrans</span><span class="p">(</span><span class="n">netrans</span><span class="p">):</span>
|
||||
<span class="w"> </span><span class="sd">"""判断 netrans 是否配置成功</span>
|
||||
|
||||
<span class="sd"> Args:</span>
|
||||
<span class="sd"> netrans (str, bool): _netrans 路径, 如果没有配置(默认为False)会去环境变量里找</span>
|
||||
|
||||
<span class="sd"> Raises:</span>
|
||||
<span class="sd"> NotADirectoryError: 找不到 Netrans 会返回 NotADirectoryError</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">if</span> <span class="n">netrans</span> <span class="o">!=</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">netrans</span><span class="p">)</span> <span class="ow">is</span> <span class="kc">True</span><span class="p">:</span>
|
||||
<span class="k">return</span>
|
||||
<span class="k">if</span> <span class="s1">'NETRANS_PATH'</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span> <span class="p">:</span>
|
||||
<span class="k">return</span>
|
||||
<span class="k">raise</span> <span class="ne">NotADirectoryError</span><span class="p">(</span>
|
||||
<span class="sa">f</span><span class="s2">"Netrans not found: </span><span class="si">{</span><span class="n">netrans</span><span class="si">}</span><span class="s2">"</span>
|
||||
<span class="p">)</span></div>
|
||||
|
||||
|
||||
|
||||
<div class="viewcode-block" id="remove_history_file">
|
||||
<a class="viewcode-back" href="../utils.html#utils.remove_history_file">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">remove_history_file</span><span class="p">(</span><span class="n">name</span><span class="p">):</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json"</span><span class="p">):</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.json"</span><span class="p">)</span>
|
||||
<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span><span class="p">):</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">.data"</span><span class="p">)</span>
|
||||
<span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="s1">'..'</span><span class="p">)</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="check_env">
|
||||
<a class="viewcode-back" href="../utils.html#utils.check_env">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">check_env</span><span class="p">(</span><span class="n">name</span><span class="p">):</span>
|
||||
<span class="n">check_dir</span><span class="p">(</span><span class="n">name</span><span class="p">)</span></div>
|
||||
|
||||
<span class="c1"># check_netrans()</span>
|
||||
<span class="c1"># remove_history_file(name)</span>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="AttributeCopier">
|
||||
<a class="viewcode-back" href="../utils.html#utils.AttributeCopier">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">AttributeCopier</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="sd">"""快速解析复制 Netrans 信息</span>
|
||||
<span class="sd"> """</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">copy_attribute_name</span><span class="p">(</span><span class="n">source_obj</span><span class="p">)</span>
|
||||
|
||||
<div class="viewcode-block" id="AttributeCopier.copy_attribute_name">
|
||||
<a class="viewcode-back" href="../utils.html#utils.AttributeCopier.copy_attribute_name">[文档]</a>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">copy_attribute_name</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source_obj</span><span class="p">):</span>
|
||||
<span class="k">for</span> <span class="n">attribute_name</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_attribute_names</span><span class="p">(</span><span class="n">source_obj</span><span class="p">):</span>
|
||||
<span class="nb">setattr</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">attribute_name</span><span class="p">,</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">source_obj</span><span class="p">,</span> <span class="n">attribute_name</span><span class="p">))</span></div>
|
||||
|
||||
|
||||
<span class="nd">@staticmethod</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="nf">_get_attribute_names</span><span class="p">(</span><span class="n">source_obj</span><span class="p">):</span>
|
||||
<span class="k">return</span> <span class="n">source_obj</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span></div>
|
||||
|
||||
|
||||
<div class="viewcode-block" id="create_cls">
|
||||
<a class="viewcode-back" href="../utils.html#utils.create_cls">[文档]</a>
|
||||
<span class="k">class</span><span class="w"> </span><span class="nc">create_cls</span><span class="p">():</span> <span class="c1">#dataclass @netrans_params</span>
|
||||
<span class="w"> </span><span class="sd">"""快速测试时候模拟实例化Netrans"""</span>
|
||||
<span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">netrans_path</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">quantized_type</span> <span class="o">=</span> <span class="s1">'uint8'</span><span class="p">,</span><span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">netrans_path</span> <span class="o">=</span> <span class="n">netrans_path</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">netrans</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">netrans_path</span><span class="p">,</span> <span class="s1">'pnnacc'</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">model_name</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">model_path</span> <span class="o">=</span> <span class="n">name</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">model_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">model_path</span><span class="p">)</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">verbose</span><span class="o">=</span><span class="n">verbose</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">quantize_type</span> <span class="o">=</span> <span class="n">quantized_type</span>
|
||||
<span class="bp">self</span><span class="o">.</span><span class="n">profile</span> <span class="o">=</span> <span class="kc">False</span></div>
|
||||
|
||||
|
||||
|
||||
<span class="c1"># if __name__ == "__main__":</span>
|
||||
<span class="c1"># dir_name = "yolo"</span>
|
||||
<span class="c1"># os.mkdir(dir_name)</span>
|
||||
<span class="c1"># check_dir(dir_name)</span>
|
||||
|
||||
|
||||
</pre></div>
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="../index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="../search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="../index.html">Documentation overview</a><ul>
|
||||
<li><a href="index.html">模块代码</a><ul>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,9 +0,0 @@
|
|||
附录
|
||||
=============
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
|
||||
gen_api
|
||||
modules
|
||||
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
config module
|
||||
=============
|
||||
|
||||
.. automodule:: config
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
dump module
|
||||
===========
|
||||
|
||||
.. automodule:: dump
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
example module
|
||||
==============
|
||||
|
||||
.. automodule:: example
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
export module
|
||||
=============
|
||||
|
||||
.. automodule:: export
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
file\_model module
|
||||
==================
|
||||
|
||||
.. automodule:: file_model
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,136 +0,0 @@
|
|||
# gen api html & pdf by sphinx
|
||||
|
||||
netrans 目录结构如下
|
||||
```tree
|
||||
netrans/
|
||||
│
|
||||
├── docs/ # Sphinx 项目的根目录
|
||||
│ ├── source/ # 源文件目录
|
||||
│ │ ├── _static/ # 静态文件（如图片、CSS、JS）
|
||||
│ │ ├── _templates/ # 自定义模板
|
||||
│ │ ├── conf.py # 配置文件
|
||||
│ │ ├── index.rst # 主页文件
|
||||
│ │ └── my_module.rst # 其他文档文件
|
||||
│ └── build/ # 构建输出目录（生成的 HTML 文件等）
|
||||
│
|
||||
└── bin/
|
||||
└── netrans_cli/
|
||||
└── netrans_py/
|
||||
```
|
||||
|
||||
1. `sphinx-quickstart docs/` 快速生成
|
||||
2. 修改 `docs/source/conf.py` ,
|
||||
|
||||
|
||||
### *.rst
|
||||
|
||||
rst, reStructuredText 文件，用于定义文档的结构。通常放在source目录下。
|
||||
|
||||
rst 是一种和 markdown 类似的语法
|
||||
|
||||
使用目录树指令 `.. toctree::`，列出其他文档文件。
|
||||
|
||||
|
||||
## 使用 autodoc + Sphinx 实现 python api 文档(html)
|
||||
|
||||
1. 修改 docs/source/conf.py
|
||||
```py3
|
||||
# Configuration file for the Sphinx documentation builder.
|
||||
#
|
||||
# For the full list of built-in configuration values, see the documentation:
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html
|
||||
|
||||
# -- Project information -----------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
|
||||
|
||||
project = 'netrans'
|
||||
copyright = '2025, ccyh'
|
||||
author = 'xj'
|
||||
release = '0.1'
|
||||
|
||||
# -- General configuration ---------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.append('../../netrans_py/')
|
||||
sys.path.append('../../')
|
||||
|
||||
# Sphinx 扩展
|
||||
extensions = [
|
||||
'sphinx.ext.autodoc', # 自动生成文档
|
||||
'sphinx.ext.viewcode', # 添加源代码链接
|
||||
'sphinx.ext.napoleon', # 支持 NumPy 和 Google 风格的 docstring
|
||||
]
|
||||
|
||||
# 主题
|
||||
html_theme = 'sphinx_rtd_theme'
|
||||
|
||||
templates_path = ['_templates']
|
||||
exclude_patterns = []
|
||||
|
||||
language = 'zh'
|
||||
|
||||
# -- Options for HTML output -------------------------------------------------
|
||||
# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
|
||||
|
||||
html_theme = 'alabaster'
|
||||
html_static_path = ['_static']
|
||||
|
||||
source_suffix = {
|
||||
'.rst': 'restructuredtext',
|
||||
'.md': 'markdown',
|
||||
}
|
||||
```
|
||||
|
||||
2. sphinx-apidoc -o docs/source/ .
|
||||
生成 netrans_py 下所有的 *.py 的rst, 并添加到index.rst里.
|
||||
```text
|
||||
# index.rst
|
||||
|
||||
```
|
||||
|
||||
3. sphinx-build -b html docs/source docs/build
|
||||
|
||||
|
||||
## 使用 autodoc + Sphinx 实现 python api 文档(pdf)
|
||||
1. 在可以生成 html的 基础上, 使用make latexodf 生成 *.tex文件.
|
||||
这一步会报错,原因是无法识别中文
|
||||
|
||||
2.修改 netrans.tex文件
|
||||
```
|
||||
cd build/latex
|
||||
vim netrans.tex
|
||||
```
|
||||
|
||||
在各种usapackage的地方新增:
|
||||
```
|
||||
\usepackage[UTF8, fontset=ubuntu]{ctex}
|
||||
```
|
||||
|
||||
3. 使用 xelatex 生成pdf
|
||||
sphinx使用的是 xelatex 而非 pdflatex
|
||||
```
|
||||
xelatex netrans.tex
|
||||
```
|
||||
|
||||
|
||||
|
||||
## 常见报错
|
||||
|
||||
报错
|
||||
```log
|
||||
sphinx-quickstart
|
||||
Traceback (most recent call last):
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/bin/sphinx-quickstart", line 8, in <module>
|
||||
sys.exit(main())
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/lib/python3.10/site-packages/sphinx/cmd/quickstart.py", line 721, in main
|
||||
locale.setlocale(locale.LC_ALL, '')
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/lib/python3.10/locale.py", line 620, in setlocale
|
||||
return _setlocale(category, locale)
|
||||
locale.Error: unsupported locale setting
|
||||
```
|
||||
|
||||
解决:
|
||||
export LC_ALL=en_US.UTF-8
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
import\_model module
|
||||
====================
|
||||
|
||||
.. automodule:: import_model
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
.. netrans documentation master file, created by
|
||||
sphinx-quickstart on Fri Jun 27 15:04:57 2025.
|
||||
You can adapt this file completely to your liking, but it should at least
|
||||
contain the root `toctree` directive.
|
||||
|
||||
netrans documentation
|
||||
=====================
|
||||
netrans 是一套针对pnna 芯片的模型处理工具，提供命令行工具 netrans_cli 和 python api netrans_py， 其核心功能是将模型权重转换成在pnna芯片上运行的 nbg（network binary graph）格式（.nb 为后缀）。
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:caption: Contents:
|
||||
|
||||
quick_start_guide
|
||||
netrans_cli
|
||||
netrans_py
|
||||
appendix
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
infer module
|
||||
============
|
||||
|
||||
.. automodule:: infer
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,17 +0,0 @@
|
|||
netrans_py
|
||||
==========
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 4
|
||||
|
||||
netrans
|
||||
config
|
||||
dump
|
||||
example
|
||||
export
|
||||
file_model
|
||||
import_model
|
||||
infer
|
||||
quantize
|
||||
quantize_hb
|
||||
utils
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
netrans module
|
||||
==============
|
||||
|
||||
.. automodule:: netrans
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,192 +0,0 @@
|
|||
# netrans_cli 使用
|
||||
|
||||
netrans_cli 是 netrans 进行模型转换的命令行工具，使用 ntrans_cli 完成模型转换的步骤如下：
|
||||
|
||||
1. 导入模型
|
||||
2. 生成并修改前处理配置文件 *_inputmeta.yml
|
||||
3. 量化模型
|
||||
4. 导出模型
|
||||
|
||||
## netrans_cli 脚本
|
||||
|
||||
|脚本|功能|使用|
|
||||
|:---|---|---|
|
||||
|load.sh| 模型导入功能，将模型转换成 Pnna 支持的格式| load.sh model_name|
|
||||
|config.sh| 预处理模版生成功能，生成预处理模版，根据模型进行对于的修改| config.sh model_name|
|
||||
|quantize.sh| 量化功能， 对模型进行量化生成量化参数文件| quantize.sh model_name quantize_data_type|
|
||||
|export.sh|导出功能，将量化好的模型导出成 Pnna 上可以运行的runtime| export.sh model_name quantize_data_type|
|
||||
|
||||
<font color="#dd0000">对于不同框架下训练的模型，需要准备不同的数据，所有的数据都需要与模型放在同一个文件夹下，模型文件名和文件夹名需要保持一致。</font>
|
||||
|
||||
## load.sh 模型导入
|
||||
|
||||
使用 load.sh 导入模型
|
||||
|
||||
- 用法： load.sh 以模型文件名命名的模型数据文件夹，例如：
|
||||
|
||||
```bash
|
||||
load.sh lenet
|
||||
```
|
||||
|
||||
"lenet"是文件夹名，也作为模型名和权重文件名。导入会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有"lenet.json"和"lenet.data"文件:
|
||||
|
||||
```bash
|
||||
$ ls -lrt lenet
|
||||
total 3396
|
||||
-rwxr-xr-x 1 hope hope 1727201 Nov 5 2018 lenet.pb
|
||||
-rw-r--r-- 1 hope hope 553 Nov 5 2018 0.jpg
|
||||
-rwxr--r-- 1 hope hope 6 Apr 21 17:04 dataset.txt
|
||||
-rw-rw-r-- 1 hope hope 69 Jun 7 09:19 inputs_outputs.txt
|
||||
-rw-r--r-- 1 hope hope 5553 Jun 7 09:21 lenet.json
|
||||
-rw-r--r-- 1 hope hope 1725178 Jun 7 09:21 lenet.data
|
||||
```
|
||||
|
||||
## config.sh 预处理配置文件生成
|
||||
|
||||
使用 config.sh 生成 inputmeta 文件
|
||||
|
||||
- config.sh 以模型文件名命名的模型数据文件夹，例如：
|
||||
|
||||
```bash
|
||||
config.sh lenet
|
||||
```
|
||||
|
||||
inputmeta 文件生成会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有 "lenet_inputmeta.yml" 文件:
|
||||
|
||||
```shell
|
||||
$ ls -lrt lenet
|
||||
total 3400
|
||||
-rwxr-xr-x 1 hope hope 1727201 Nov 5 2018 lenet.pb
|
||||
-rw-r--r-- 1 hope hope 553 Nov 5 2018 0.jpg
|
||||
-rwxr--r-- 1 hope hope 6 Apr 21 17:04 dataset.txt
|
||||
-rw-rw-r-- 1 hope hope 69 Jun 7 09:19 inputs_outputs.txt
|
||||
-rw-r--r-- 1 hope hope 5553 Jun 7 09:21 lenet.json
|
||||
-rw-r--r-- 1 hope hope 1725178 Jun 7 09:21 lenet.data
|
||||
-rw-r--r-- 1 hope hope 948 Jun 7 09:35 lenet_inputmeta.yml
|
||||
```
|
||||
|
||||
可以看到，最终生成的是*.yml文件，该文件用于为Netrans中间模型配置输入层数据集合。<b>Netrans中的量化、推理、导出和图片转dat的操作都需要用到这个文件。因此，此步骤不可跳过。</b>
|
||||
|
||||
Inputmeta.yml文件结构如下：
|
||||
|
||||
```yaml
|
||||
%YAML 1.2
|
||||
---
|
||||
# !!!This file disallow TABs!!!
|
||||
# "category" allowed values: "image, undefined"
|
||||
# "database" allowed types: "H5FS, SQLITE, TEXT, LMDB, NPY, GENERATOR"
|
||||
# "tensor_name" only support in H5FS database
|
||||
# "preproc_type" allowed types:"IMAGE_RGB, IMAGE_RGB888_PLANAR, IMAGE_RGB888_PLANAR_SEP,
|
||||
IMAGE_I420,
|
||||
# IMAGE_NV12, IMAGE_YUV444, IMAGE_GRAY, IMAGE_BGRA, TENSOR"
|
||||
input_meta:
|
||||
databases:
|
||||
- path: dataset.txt
|
||||
type: TEXT
|
||||
ports:
|
||||
- lid: data_0
|
||||
category: image
|
||||
dtype: float32
|
||||
sparse: false
|
||||
tensor_name:
|
||||
layout: nhwc
|
||||
shape:
|
||||
- 50
|
||||
- 224
|
||||
- 224
|
||||
- 3
|
||||
preprocess:
|
||||
reverse_channel: false
|
||||
mean:
|
||||
- 103.94
|
||||
- 116.78
|
||||
- 123.67
|
||||
scale: 0.017
|
||||
preproc_node_params:
|
||||
preproc_type: IMAGE_RGB
|
||||
add_preproc_node: false
|
||||
preproc_perm:
|
||||
- 0
|
||||
- 1
|
||||
- 2
|
||||
- 3
|
||||
- lid: label_0
|
||||
redirect_to_output: true
|
||||
category: undefined
|
||||
tensor_name:
|
||||
dtype: float32
|
||||
shape:
|
||||
- 1
|
||||
- 1
|
||||
```
|
||||
|
||||
上面示例文件的各个参数解释：
|
||||
|
||||
```{table}
|
||||
:widths: 20, 80
|
||||
:align: left
|
||||
| 参数 | 说明 |
|
||||
| :--- | --- |
|
||||
| input_meta | 预处理参数配置申明。 |
|
||||
| databases | 数据配置，包括设置 path、type 和 ports 。|
|
||||
| path | 数据集文件的相对（执行目录）或绝对路径。默认为 dataset.txt, 不建议修改。 |
|
||||
| type | 数据集文件格式，固定为TEXT。 |
|
||||
| ports | 指向网络中的输入或重定向的输入，目前只支持一个输入，如果网络存在多个输入，请与@ccyh联系。 |
|
||||
| lid | 输入层的lid |
|
||||
| category | 输入的类别。将此参数设置为以下值之一：image（图像输入）或 undefined（其他类型的输入）。 |
|
||||
| dtype | 输入张量的数据类型，用于将数据发送到 Pnna 网络的输入端口。支持的数据类型包括 float32 和 quantized。 |
|
||||
| sparse | 指定网络张量是否以稀疏格式存在。将此参数设置为以下值之一：true（稀疏格式）或 false（压缩格式）。 |
|
||||
| tensor_name | 留空此参数 |
|
||||
| layout | 输入张量的格式，使用 nchw 用于 Caffe、Darknet、ONNX 和 PyTorch 模型。使用 nhwc 用于 TensorFlow、TensorFlow Lite 和 Keras 模型。 |
|
||||
| shape | 此张量的形状。第一维，shape[0]，表示每批的输入数量，允许在一次推理操作之前将多个输入发送到网络。如果batch维度设置为0，则需要从命令行指定--batch-size。如果 batch维度设置为大于1的值，则直接使用inputmeta.yml中的batch size并忽略命令行中的--batch-size。 |
|
||||
| fitting | 保留字段 |
|
||||
| preprocess | 预处理步骤和顺序。预处理支持下面的四个键，键的顺序代表预处理的顺序。您可以相应地调整顺序。 |
|
||||
| reverse_channel | 指定是否保留通道顺序。将此参数设置为以下值之一：true（保留通道顺序）或 false（不保留通道顺序）。对于 TensorFlow 和 TensorFlow Lite 框架的模型使用 true。 |
|
||||
| mean | 用于每个通道的均值。 |
|
||||
| scale | 张量的缩放值。均值和缩放值用于根据公式 (inputTensor - mean) × scale 归一化输入张量。|
|
||||
| preproc_node_params | 预处理节点参数，在 OVxlib C 项目案例中启用预处理任务 |
|
||||
| add_preproc_node | 用于处理 OVxlib C 项目案例中预处理节点的插入。[true, false] 中的布尔值，表示通过配置以下参数将预处理层添加到导出的应用程序中。此参数仅在 add_preproc_node 参数设置为 true 时有效。|
|
||||
| preproc_type | 预处理节点输入类型。 [IMAGE_RGB, IMAGE_RGB888_PLANAR,IMAGE_YUV420, IMAGE_GRAY, IMAGE_BGRA, TENSOR] 中的字符串值 |
|
||||
| preproc_perm | 预处理节点输入的置换参数。 |
|
||||
| redirect_to_output | 将database张量重定向到图形输出的特殊属性。如果为该属性设置了一个port，网络构建器将自动为该port生成一个输出层，以便后处理文件可以直接处理来自database的张量。 如果使用网络进行分类，则上例中的lid“input_0”表示输入数据集的标签lid。 您可以设置其他名称来表示标签的lid。 请注意，redirect_to_output 必须设置为 true，以便后处理文件可以直接处理来自database的张量。 标签的lid必须与后处理文件中定义的 labels_tensor 的lid相同。 [true, false] 中的布尔值。 指定是否将由张量表示的输入端口的数据直接发送到网络输出。true（直接发送到网络输出）或 false（不直接发送到网络输出）|
|
||||
```
|
||||
|
||||
可以根据实际情况对生成的inputmeta文件进行修改。
|
||||
|
||||
## quantize.sh 模型量化
|
||||
|
||||
如果我们训练好的模型的数据类型是float32的，为了使模型以更高的效率在Pnna上运行，我们可以对模型进行量化操作，量化操作可能会带来一定程度的精度损失。
|
||||
|
||||
- 在netrans_cli目录下使用quantize.sh脚本进行量化操作。
|
||||
|
||||
用法：./quantize.sh 以模型文件名命名的模型数据文件夹 量化类型，例如：
|
||||
|
||||
```bash
|
||||
quantize.sh lenet uint8
|
||||
```
|
||||
|
||||
支持的量化类型有：uint8、int8、int16
|
||||
|
||||
## export.sh 模型导出
|
||||
|
||||
使用 export.sh 导出模型生成nbg文件。
|
||||
|
||||
用法：export.sh 以模型文件名命名的模型数据文件夹 数据类型，例如：
|
||||
|
||||
```bash
|
||||
export.sh lenet uint8
|
||||
```
|
||||
|
||||
导出支持的数据类型：float、uint8、int8、int16，其中使用uint8、int8、int16导出时需要先进行模型量化。导出的工程会在模型所在的目录下面的wksp目录里。
|
||||
network_binary.nb文件在"asymmetric_affine"文件夹中：
|
||||
|
||||
```shell
|
||||
ls -lrt lenet/wksp/asymmetric_affine/
|
||||
-rw-r--r-- 1 hope hope 694912 Jun 7 09:55 network_binary.nb
|
||||
```
|
||||
|
||||
目前支持将生成的network_binary.nb文件部署到Pnna硬件平台。具体部署方法请参阅模型部署相关文档。
|
||||
|
||||
## 使用示例
|
||||
|
||||
请参照examples，examples 提供 [caffe 模型转换示例](./examples/caffe_model.md),[darknet 模型转换示例](./examples/darknet_model.md),[tensorflow 模型转换示例](./examples/tensorflow_model.md),[onnx 模型转换示例](./examples/onnx_model.md)。
|
||||
|
|
@ -1,167 +0,0 @@
|
|||
# netrans_py 使用
|
||||
|
||||
netrans_py 为 Netrans 编译器的 python 调用接口。
|
||||
使用 ntrans_py 完成模型转换的步骤如下：
|
||||
|
||||
1. 导入模型
|
||||
2. 生成并修改前处理配置文件 *_inputmeta.yml
|
||||
3. 量化模型
|
||||
4. 导出模型
|
||||
|
||||
## Netrans 类
|
||||
|
||||
创建 Netrans
|
||||
|
||||
描述： 实例化 Netrans 类。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
from netrans import Netrans
|
||||
yolo_netrans = Netrans("../examples/darknet/yolov4_tiny")
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|model_path| str| 第一位置参数，模型文件的路径|
|
||||
|netans| str | 如果 NETRANS_PATH 没有设置，可通过该参数指定netrans的路径|
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
|
||||
<!-- <font color="#dd0000">注意：</font> 模型目录准备需要和netrans_cli一致，具体数据准备要求见[introduction](./introduction.md)。 -->
|
||||
|
||||
## Netrans.import 模型导入
|
||||
|
||||
描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
yolo_netrans.import()
|
||||
```
|
||||
|
||||
参数：
|
||||
无。
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
在工程目录下生成 Pnna 支持的模型格式，以.json结尾的模型文件和 .data结尾的权重文件。
|
||||
|
||||
## Netrans.config 预处理配置文件生成
|
||||
|
||||
描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
yolo_netrans.config()
|
||||
```
|
||||
|
||||
参数：
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
```
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
|
||||
## Netrans.quantize 模型量化
|
||||
|
||||
描述： 对模型生成量化配置文件。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
yolo_netrans.quantize("uint8")
|
||||
```
|
||||
|
||||
参数：
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str| 第一位置参数，模型量化类型，仅支持 "uint8", "int8", "int16"|
|
||||
```
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
|
||||
## Netrans.export 模型导出
|
||||
|
||||
描述： 对模型生成量化配置文件。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
yolo_netrans.export()
|
||||
```
|
||||
|
||||
参数：
|
||||
无。
|
||||
|
||||
输出返回：
|
||||
无。请在目录 “wksp/*/” 下检查是否生成nbg文件。
|
||||
|
||||
## Netrans.model2nbg 模型生成nbg文件
|
||||
|
||||
描述： 模型导入、量化、及nbg文件生产
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
# 无预处理
|
||||
yolo_netrans.model2nbg(quantize_type='uint8')
|
||||
# 需要对数据进行normlize, menas为128, scale 为 0.0039
|
||||
yolo_netrans.model2nbg(quantize_type='uint8',mean=128, scale = 0.0039)
|
||||
# 需要对数据分通道进行normlize, menas为128,127,125,scale 为 0.0039, 且reverse_channel 为 True
|
||||
yolo_netrans.model2nbg(quantize_type='uint8'mean=[128, 127, 125], scale = 0.0039, reverse_channel= True)
|
||||
# 已经进行初始化设置
|
||||
yolo_netrans.model2nbg(quantize_type='uint8', inputmeta=True)
|
||||
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str, ["uint8", "int8", "int16" ] | 量化类型，将模型量化成该参数指定的类型 |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
```
|
||||
|
||||
输出返回：
|
||||
请在目录 “wksp/*/” 下检查是否生成nbg文件。
|
||||
|
||||
## 使用示例
|
||||
|
||||
```py3
|
||||
from nertans import Netrans
|
||||
model_path = 'example/darknet/yolov4_tiny'
|
||||
netrans_path = "netrans/bin" # 如果进行了export定义申明，这一步可以不用
|
||||
|
||||
# 初始化netrans
|
||||
net = Netrans(model_path,netrans=netrans_path)
|
||||
# 模型载入
|
||||
net.import()
|
||||
# 配置预处理 normlize 的参数
|
||||
net.config(scale=1,mean=0)
|
||||
# 模型量化
|
||||
net.quantize("uint8")
|
||||
# 模型导出
|
||||
net.export()
|
||||
|
||||
# 模型直接量化成 int16 并导出, 直接复用刚配置好的 inputmeta
|
||||
net.model2nbg(quantize_type = "int16", inputmeta=True)
|
||||
```
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
quantize module
|
||||
===============
|
||||
|
||||
.. automodule:: quantize
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
quantize\_hb module
|
||||
===================
|
||||
|
||||
.. automodule:: quantize_hb
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,160 +0,0 @@
|
|||
# 快速入门
|
||||
|
||||
本文档以 onnx 格式的 yolov5s 为例，演示如何快速安装Nertans 并使用 Netrans 量化、编译模型并生成 nbg 文件。
|
||||
|
||||
## 系统环境
|
||||
|
||||
- Linux操作系统，推荐 Ubuntu 20.04 或 Debian12
|
||||
- Python 3.8
|
||||
- RAM 至少 8GB
|
||||
|
||||
## 安装Netrans
|
||||
|
||||
创建 python3.8 环境
|
||||
|
||||
```bash
|
||||
wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
|
||||
mkdir -p ~/app
|
||||
INSTALL_PATH="${HOME}/app/miniforge3"
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${INSTALL_PATH}
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/conda.sh"" >> ${HOME}/.bashrc
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
source ${HOME}/.bashrc
|
||||
mamba create -n netrans python=3.8 -y
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
配置 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
```
|
||||
|
||||
## 使用 Netrans 编译 yolov5s 模型
|
||||
|
||||
进入工作目录
|
||||
|
||||
```bash
|
||||
cd ～/app/netrans/examples/onnx
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
||||
```text
|
||||
onnx/
|
||||
├── README.md
|
||||
└── yolov5s
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
### 使用 netrans_cli 编译 yolov5s
|
||||
|
||||
#### 导入模型
|
||||
|
||||
```bash
|
||||
load.sh yolov5s
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
|
||||
此时 yolov5s 的目录结构如下
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── yolov5s.data
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
#### 生成配置文件模板
|
||||
|
||||
配置文件定义输入数据前处理相关参数。Netrans预定义了配置文件模板生成脚本，用户需根据模型前处理参数对配置文件进行修改。
|
||||
|
||||
```bash
|
||||
config.sh yolov5s
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
|
||||
```
|
||||
|
||||
根据 yolov5s 的前处理参数 ，修改 yml 中的 scale 为 0.003921568627。
|
||||
打开 ` yolov5s_inputmeta.yml ` 文件，修改第30-33行：
|
||||
|
||||
```text
|
||||
scale:
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
```
|
||||
|
||||
#### 量化模型
|
||||
|
||||
生成 unit8 量化的量化参数文件
|
||||
|
||||
```bash
|
||||
quantize.sh yolov5s uint8
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
#### 导出模型
|
||||
|
||||
导出 unit8 量化的模型项目工程
|
||||
|
||||
```bash
|
||||
export.sh yolov5s uint8
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ └── asymmetric_affine
|
||||
│ └── network_binary.nb
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
### 使用 netrans_py 编译 yolov5s 模型
|
||||
|
||||
```bash
|
||||
example.py yolov5s -q uint8 -m 0 -s 0.003921568627
|
||||
```
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
setup module
|
||||
============
|
||||
|
||||
.. automodule:: setup
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
utils module
|
||||
============
|
||||
|
||||
.. automodule:: utils
|
||||
:members:
|
||||
:show-inheritance:
|
||||
:undoc-members:
|
||||
|
|
@ -1,663 +0,0 @@
|
|||
/* -- page layout ----------------------------------------------------------- */
|
||||
|
||||
body {
|
||||
font-family: Georgia, serif;
|
||||
font-size: 17px;
|
||||
background-color: #fff;
|
||||
color: #000;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
|
||||
div.document {
|
||||
width: 940px;
|
||||
margin: 30px auto 0 auto;
|
||||
}
|
||||
|
||||
div.documentwrapper {
|
||||
float: left;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
div.bodywrapper {
|
||||
margin: 0 0 0 220px;
|
||||
}
|
||||
|
||||
div.sphinxsidebar {
|
||||
width: 220px;
|
||||
font-size: 14px;
|
||||
line-height: 1.5;
|
||||
}
|
||||
|
||||
hr {
|
||||
border: 1px solid #B1B4B6;
|
||||
}
|
||||
|
||||
div.body {
|
||||
background-color: #fff;
|
||||
color: #3E4349;
|
||||
padding: 0 30px 0 30px;
|
||||
}
|
||||
|
||||
div.body > .section {
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
div.footer {
|
||||
width: 940px;
|
||||
margin: 20px auto 30px auto;
|
||||
font-size: 14px;
|
||||
color: #888;
|
||||
text-align: right;
|
||||
}
|
||||
|
||||
div.footer a {
|
||||
color: #888;
|
||||
}
|
||||
|
||||
p.caption {
|
||||
font-family: inherit;
|
||||
font-size: inherit;
|
||||
}
|
||||
|
||||
|
||||
div.relations {
|
||||
display: none;
|
||||
}
|
||||
|
||||
|
||||
div.sphinxsidebar {
|
||||
max-height: 100%;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
div.sphinxsidebar a {
|
||||
color: #444;
|
||||
text-decoration: none;
|
||||
border-bottom: 1px dotted #999;
|
||||
}
|
||||
|
||||
div.sphinxsidebar a:hover {
|
||||
border-bottom: 1px solid #999;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper {
|
||||
padding: 18px 10px;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper p.logo {
|
||||
padding: 0;
|
||||
margin: -10px 0 0 0px;
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper h1.logo {
|
||||
margin-top: -10px;
|
||||
text-align: center;
|
||||
margin-bottom: 5px;
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper h1.logo-name {
|
||||
margin-top: 0px;
|
||||
}
|
||||
|
||||
div.sphinxsidebarwrapper p.blurb {
|
||||
margin-top: 0;
|
||||
font-style: normal;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h3,
|
||||
div.sphinxsidebar h4 {
|
||||
font-family: Georgia, serif;
|
||||
color: #444;
|
||||
font-size: 24px;
|
||||
font-weight: normal;
|
||||
margin: 0 0 5px 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h4 {
|
||||
font-size: 20px;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h3 a {
|
||||
color: #444;
|
||||
}
|
||||
|
||||
div.sphinxsidebar p.logo a,
|
||||
div.sphinxsidebar h3 a,
|
||||
div.sphinxsidebar p.logo a:hover,
|
||||
div.sphinxsidebar h3 a:hover {
|
||||
border: none;
|
||||
}
|
||||
|
||||
div.sphinxsidebar p {
|
||||
color: #555;
|
||||
margin: 10px 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul {
|
||||
margin: 10px 0;
|
||||
padding: 0;
|
||||
color: #000;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul li.toctree-l1 > a {
|
||||
font-size: 120%;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul li.toctree-l2 > a {
|
||||
font-size: 110%;
|
||||
}
|
||||
|
||||
div.sphinxsidebar input {
|
||||
border: 1px solid #CCC;
|
||||
font-family: Georgia, serif;
|
||||
font-size: 1em;
|
||||
}
|
||||
|
||||
div.sphinxsidebar #searchbox {
|
||||
margin: 1em 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar .search > div {
|
||||
display: table-cell;
|
||||
}
|
||||
|
||||
div.sphinxsidebar hr {
|
||||
border: none;
|
||||
height: 1px;
|
||||
color: #AAA;
|
||||
background: #AAA;
|
||||
|
||||
text-align: left;
|
||||
margin-left: 0;
|
||||
width: 50%;
|
||||
}
|
||||
|
||||
div.sphinxsidebar .badge {
|
||||
border-bottom: none;
|
||||
}
|
||||
|
||||
div.sphinxsidebar .badge:hover {
|
||||
border-bottom: none;
|
||||
}
|
||||
|
||||
/* To address an issue with donation coming after search */
|
||||
div.sphinxsidebar h3.donation {
|
||||
margin-top: 10px;
|
||||
}
|
||||
|
||||
/* -- body styles ----------------------------------------------------------- */
|
||||
|
||||
a {
|
||||
color: #004B6B;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
color: #6D4100;
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
div.body h1,
|
||||
div.body h2,
|
||||
div.body h3,
|
||||
div.body h4,
|
||||
div.body h5,
|
||||
div.body h6 {
|
||||
font-family: Georgia, serif;
|
||||
font-weight: normal;
|
||||
margin: 30px 0px 10px 0px;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
div.body h1 { margin-top: 0; padding-top: 0; font-size: 240%; }
|
||||
div.body h2 { font-size: 180%; }
|
||||
div.body h3 { font-size: 150%; }
|
||||
div.body h4 { font-size: 130%; }
|
||||
div.body h5 { font-size: 100%; }
|
||||
div.body h6 { font-size: 100%; }
|
||||
|
||||
a.headerlink {
|
||||
color: #DDD;
|
||||
padding: 0 4px;
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
a.headerlink:hover {
|
||||
color: #444;
|
||||
background: #EAEAEA;
|
||||
}
|
||||
|
||||
div.body p, div.body dd, div.body li {
|
||||
line-height: 1.4em;
|
||||
}
|
||||
|
||||
div.admonition {
|
||||
margin: 20px 0px;
|
||||
padding: 10px 30px;
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.admonition tt.xref, div.admonition code.xref, div.admonition a tt {
|
||||
background-color: #FBFBFB;
|
||||
border-bottom: 1px solid #fafafa;
|
||||
}
|
||||
|
||||
div.admonition p.admonition-title {
|
||||
font-family: Georgia, serif;
|
||||
font-weight: normal;
|
||||
font-size: 24px;
|
||||
margin: 0 0 10px 0;
|
||||
padding: 0;
|
||||
line-height: 1;
|
||||
}
|
||||
|
||||
div.admonition p.last {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
dt:target, .highlight {
|
||||
background: #FAF3E8;
|
||||
}
|
||||
|
||||
div.warning {
|
||||
background-color: #FCC;
|
||||
border: 1px solid #FAA;
|
||||
}
|
||||
|
||||
div.danger {
|
||||
background-color: #FCC;
|
||||
border: 1px solid #FAA;
|
||||
-moz-box-shadow: 2px 2px 4px #D52C2C;
|
||||
-webkit-box-shadow: 2px 2px 4px #D52C2C;
|
||||
box-shadow: 2px 2px 4px #D52C2C;
|
||||
}
|
||||
|
||||
div.error {
|
||||
background-color: #FCC;
|
||||
border: 1px solid #FAA;
|
||||
-moz-box-shadow: 2px 2px 4px #D52C2C;
|
||||
-webkit-box-shadow: 2px 2px 4px #D52C2C;
|
||||
box-shadow: 2px 2px 4px #D52C2C;
|
||||
}
|
||||
|
||||
div.caution {
|
||||
background-color: #FCC;
|
||||
border: 1px solid #FAA;
|
||||
}
|
||||
|
||||
div.attention {
|
||||
background-color: #FCC;
|
||||
border: 1px solid #FAA;
|
||||
}
|
||||
|
||||
div.important {
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.note {
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.tip {
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.hint {
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.seealso {
|
||||
background-color: #EEE;
|
||||
border: 1px solid #CCC;
|
||||
}
|
||||
|
||||
div.topic {
|
||||
background-color: #EEE;
|
||||
}
|
||||
|
||||
p.admonition-title {
|
||||
display: inline;
|
||||
}
|
||||
|
||||
p.admonition-title:after {
|
||||
content: ":";
|
||||
}
|
||||
|
||||
pre, tt, code {
|
||||
font-family: 'Consolas', 'Menlo', 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
|
||||
.hll {
|
||||
background-color: #FFC;
|
||||
margin: 0 -12px;
|
||||
padding: 0 12px;
|
||||
display: block;
|
||||
}
|
||||
|
||||
img.screenshot {
|
||||
}
|
||||
|
||||
tt.descname, tt.descclassname, code.descname, code.descclassname {
|
||||
font-size: 0.95em;
|
||||
}
|
||||
|
||||
tt.descname, code.descname {
|
||||
padding-right: 0.08em;
|
||||
}
|
||||
|
||||
img.screenshot {
|
||||
-moz-box-shadow: 2px 2px 4px #EEE;
|
||||
-webkit-box-shadow: 2px 2px 4px #EEE;
|
||||
box-shadow: 2px 2px 4px #EEE;
|
||||
}
|
||||
|
||||
table.docutils {
|
||||
border: 1px solid #888;
|
||||
-moz-box-shadow: 2px 2px 4px #EEE;
|
||||
-webkit-box-shadow: 2px 2px 4px #EEE;
|
||||
box-shadow: 2px 2px 4px #EEE;
|
||||
}
|
||||
|
||||
table.docutils td, table.docutils th {
|
||||
border: 1px solid #888;
|
||||
padding: 0.25em 0.7em;
|
||||
}
|
||||
|
||||
table.field-list, table.footnote {
|
||||
border: none;
|
||||
-moz-box-shadow: none;
|
||||
-webkit-box-shadow: none;
|
||||
box-shadow: none;
|
||||
}
|
||||
|
||||
table.footnote {
|
||||
margin: 15px 0;
|
||||
width: 100%;
|
||||
border: 1px solid #EEE;
|
||||
background: #FDFDFD;
|
||||
font-size: 0.9em;
|
||||
}
|
||||
|
||||
table.footnote + table.footnote {
|
||||
margin-top: -15px;
|
||||
border-top: none;
|
||||
}
|
||||
|
||||
table.field-list th {
|
||||
padding: 0 0.8em 0 0;
|
||||
}
|
||||
|
||||
table.field-list td {
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
table.field-list p {
|
||||
margin-bottom: 0.8em;
|
||||
}
|
||||
|
||||
/* Cloned from
|
||||
* https://github.com/sphinx-doc/sphinx/commit/ef60dbfce09286b20b7385333d63a60321784e68
|
||||
*/
|
||||
.field-name {
|
||||
-moz-hyphens: manual;
|
||||
-ms-hyphens: manual;
|
||||
-webkit-hyphens: manual;
|
||||
hyphens: manual;
|
||||
}
|
||||
|
||||
table.footnote td.label {
|
||||
width: .1px;
|
||||
padding: 0.3em 0 0.3em 0.5em;
|
||||
}
|
||||
|
||||
table.footnote td {
|
||||
padding: 0.3em 0.5em;
|
||||
}
|
||||
|
||||
dl {
|
||||
margin-left: 0;
|
||||
margin-right: 0;
|
||||
margin-top: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
dl dd {
|
||||
margin-left: 30px;
|
||||
}
|
||||
|
||||
blockquote {
|
||||
margin: 0 0 0 30px;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
ul, ol {
|
||||
/* Matches the 30px from the narrow-screen "li > ul" selector below */
|
||||
margin: 10px 0 10px 30px;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
pre {
|
||||
background: unset;
|
||||
padding: 7px 30px;
|
||||
margin: 15px 0px;
|
||||
line-height: 1.3em;
|
||||
}
|
||||
|
||||
div.viewcode-block:target {
|
||||
background: #ffd;
|
||||
}
|
||||
|
||||
dl pre, blockquote pre, li pre {
|
||||
margin-left: 0;
|
||||
padding-left: 30px;
|
||||
}
|
||||
|
||||
tt, code {
|
||||
background-color: #ecf0f3;
|
||||
color: #222;
|
||||
/* padding: 1px 2px; */
|
||||
}
|
||||
|
||||
tt.xref, code.xref, a tt {
|
||||
background-color: #FBFBFB;
|
||||
border-bottom: 1px solid #fff;
|
||||
}
|
||||
|
||||
a.reference {
|
||||
text-decoration: none;
|
||||
border-bottom: 1px dotted #004B6B;
|
||||
}
|
||||
|
||||
a.reference:hover {
|
||||
border-bottom: 1px solid #6D4100;
|
||||
}
|
||||
|
||||
/* Don't put an underline on images */
|
||||
a.image-reference, a.image-reference:hover {
|
||||
border-bottom: none;
|
||||
}
|
||||
|
||||
a.footnote-reference {
|
||||
text-decoration: none;
|
||||
font-size: 0.7em;
|
||||
vertical-align: top;
|
||||
border-bottom: 1px dotted #004B6B;
|
||||
}
|
||||
|
||||
a.footnote-reference:hover {
|
||||
border-bottom: 1px solid #6D4100;
|
||||
}
|
||||
|
||||
a:hover tt, a:hover code {
|
||||
background: #EEE;
|
||||
}
|
||||
|
||||
@media screen and (max-width: 940px) {
|
||||
|
||||
body {
|
||||
margin: 0;
|
||||
padding: 20px 30px;
|
||||
}
|
||||
|
||||
div.documentwrapper {
|
||||
float: none;
|
||||
background: #fff;
|
||||
margin-left: 0;
|
||||
margin-top: 0;
|
||||
margin-right: 0;
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar {
|
||||
display: block;
|
||||
float: none;
|
||||
width: unset;
|
||||
margin: 50px -30px -20px -30px;
|
||||
padding: 10px 20px;
|
||||
background: #333;
|
||||
color: #FFF;
|
||||
}
|
||||
|
||||
div.sphinxsidebar h3, div.sphinxsidebar h4, div.sphinxsidebar p,
|
||||
div.sphinxsidebar h3 a {
|
||||
color: #fff;
|
||||
}
|
||||
|
||||
div.sphinxsidebar a {
|
||||
color: #AAA;
|
||||
}
|
||||
|
||||
div.sphinxsidebar p.logo {
|
||||
display: none;
|
||||
}
|
||||
|
||||
div.document {
|
||||
width: 100%;
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
div.footer {
|
||||
display: none;
|
||||
}
|
||||
|
||||
div.bodywrapper {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
div.body {
|
||||
min-height: 0;
|
||||
min-width: auto; /* fixes width on small screens, breaks .hll */
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
.hll {
|
||||
/* "fixes" the breakage */
|
||||
width: max-content;
|
||||
}
|
||||
|
||||
.rtd_doc_footer {
|
||||
display: none;
|
||||
}
|
||||
|
||||
.document {
|
||||
width: auto;
|
||||
}
|
||||
|
||||
.footer {
|
||||
width: auto;
|
||||
}
|
||||
|
||||
.github {
|
||||
display: none;
|
||||
}
|
||||
|
||||
ul {
|
||||
margin-left: 0;
|
||||
}
|
||||
|
||||
li > ul {
|
||||
/* Matches the 30px from the "ul, ol" selector above */
|
||||
margin-left: 30px;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/* misc. */
|
||||
|
||||
.revsys-inline {
|
||||
display: none!important;
|
||||
}
|
||||
|
||||
/* Hide ugly table cell borders in ..bibliography:: directive output */
|
||||
table.docutils.citation, table.docutils.citation td, table.docutils.citation th {
|
||||
border: none;
|
||||
/* Below needed in some edge cases; if not applied, bottom shadows appear */
|
||||
-moz-box-shadow: none;
|
||||
-webkit-box-shadow: none;
|
||||
box-shadow: none;
|
||||
}
|
||||
|
||||
|
||||
/* relbar */
|
||||
|
||||
.related {
|
||||
line-height: 30px;
|
||||
width: 100%;
|
||||
font-size: 0.9rem;
|
||||
}
|
||||
|
||||
.related.top {
|
||||
border-bottom: 1px solid #EEE;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.related.bottom {
|
||||
border-top: 1px solid #EEE;
|
||||
}
|
||||
|
||||
.related ul {
|
||||
padding: 0;
|
||||
margin: 0;
|
||||
list-style: none;
|
||||
}
|
||||
|
||||
.related li {
|
||||
display: inline;
|
||||
}
|
||||
|
||||
nav#rellinks {
|
||||
float: right;
|
||||
}
|
||||
|
||||
nav#rellinks li+li:before {
|
||||
content: "|";
|
||||
}
|
||||
|
||||
nav#breadcrumbs li+li:before {
|
||||
content: "\00BB";
|
||||
}
|
||||
|
||||
/* Hide certain items when printing */
|
||||
@media print {
|
||||
div.related {
|
||||
display: none;
|
||||
}
|
||||
}
|
||||
|
||||
img.github {
|
||||
position: absolute;
|
||||
top: 0;
|
||||
border: 0;
|
||||
right: 0;
|
||||
}
|
||||
|
|
@ -1,906 +0,0 @@
|
|||
/*
|
||||
* Sphinx stylesheet -- basic theme.
|
||||
*/
|
||||
|
||||
/* -- main layout ----------------------------------------------------------- */
|
||||
|
||||
div.clearer {
|
||||
clear: both;
|
||||
}
|
||||
|
||||
div.section::after {
|
||||
display: block;
|
||||
content: '';
|
||||
clear: left;
|
||||
}
|
||||
|
||||
/* -- relbar ---------------------------------------------------------------- */
|
||||
|
||||
div.related {
|
||||
width: 100%;
|
||||
font-size: 90%;
|
||||
}
|
||||
|
||||
div.related h3 {
|
||||
display: none;
|
||||
}
|
||||
|
||||
div.related ul {
|
||||
margin: 0;
|
||||
padding: 0 0 0 10px;
|
||||
list-style: none;
|
||||
}
|
||||
|
||||
div.related li {
|
||||
display: inline;
|
||||
}
|
||||
|
||||
div.related li.right {
|
||||
float: right;
|
||||
margin-right: 5px;
|
||||
}
|
||||
|
||||
/* -- sidebar --------------------------------------------------------------- */
|
||||
|
||||
div.sphinxsidebarwrapper {
|
||||
padding: 10px 5px 0 10px;
|
||||
}
|
||||
|
||||
div.sphinxsidebar {
|
||||
float: left;
|
||||
width: 230px;
|
||||
margin-left: -100%;
|
||||
font-size: 90%;
|
||||
word-wrap: break-word;
|
||||
overflow-wrap : break-word;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul {
|
||||
list-style: none;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul ul,
|
||||
div.sphinxsidebar ul.want-points {
|
||||
margin-left: 20px;
|
||||
list-style: square;
|
||||
}
|
||||
|
||||
div.sphinxsidebar ul ul {
|
||||
margin-top: 0;
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
div.sphinxsidebar form {
|
||||
margin-top: 10px;
|
||||
}
|
||||
|
||||
div.sphinxsidebar input {
|
||||
border: 1px solid #98dbcc;
|
||||
font-family: sans-serif;
|
||||
font-size: 1em;
|
||||
}
|
||||
|
||||
div.sphinxsidebar #searchbox form.search {
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
div.sphinxsidebar #searchbox input[type="text"] {
|
||||
float: left;
|
||||
width: 80%;
|
||||
padding: 0.25em;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
div.sphinxsidebar #searchbox input[type="submit"] {
|
||||
float: left;
|
||||
width: 20%;
|
||||
border-left: none;
|
||||
padding: 0.25em;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
|
||||
img {
|
||||
border: 0;
|
||||
max-width: 100%;
|
||||
}
|
||||
|
||||
/* -- search page ----------------------------------------------------------- */
|
||||
|
||||
ul.search {
|
||||
margin-top: 10px;
|
||||
}
|
||||
|
||||
ul.search li {
|
||||
padding: 5px 0;
|
||||
}
|
||||
|
||||
ul.search li a {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
ul.search li p.context {
|
||||
color: #888;
|
||||
margin: 2px 0 0 30px;
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
ul.keywordmatches li.goodmatch a {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
/* -- index page ------------------------------------------------------------ */
|
||||
|
||||
table.contentstable {
|
||||
width: 90%;
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
table.contentstable p.biglink {
|
||||
line-height: 150%;
|
||||
}
|
||||
|
||||
a.biglink {
|
||||
font-size: 1.3em;
|
||||
}
|
||||
|
||||
span.linkdescr {
|
||||
font-style: italic;
|
||||
padding-top: 5px;
|
||||
font-size: 90%;
|
||||
}
|
||||
|
||||
/* -- general index --------------------------------------------------------- */
|
||||
|
||||
table.indextable {
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
table.indextable td {
|
||||
text-align: left;
|
||||
vertical-align: top;
|
||||
}
|
||||
|
||||
table.indextable ul {
|
||||
margin-top: 0;
|
||||
margin-bottom: 0;
|
||||
list-style-type: none;
|
||||
}
|
||||
|
||||
table.indextable > tbody > tr > td > ul {
|
||||
padding-left: 0em;
|
||||
}
|
||||
|
||||
table.indextable tr.pcap {
|
||||
height: 10px;
|
||||
}
|
||||
|
||||
table.indextable tr.cap {
|
||||
margin-top: 10px;
|
||||
background-color: #f2f2f2;
|
||||
}
|
||||
|
||||
img.toggler {
|
||||
margin-right: 3px;
|
||||
margin-top: 3px;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
div.modindex-jumpbox {
|
||||
border-top: 1px solid #ddd;
|
||||
border-bottom: 1px solid #ddd;
|
||||
margin: 1em 0 1em 0;
|
||||
padding: 0.4em;
|
||||
}
|
||||
|
||||
div.genindex-jumpbox {
|
||||
border-top: 1px solid #ddd;
|
||||
border-bottom: 1px solid #ddd;
|
||||
margin: 1em 0 1em 0;
|
||||
padding: 0.4em;
|
||||
}
|
||||
|
||||
/* -- domain module index --------------------------------------------------- */
|
||||
|
||||
table.modindextable td {
|
||||
padding: 2px;
|
||||
border-collapse: collapse;
|
||||
}
|
||||
|
||||
/* -- general body styles --------------------------------------------------- */
|
||||
|
||||
div.body {
|
||||
min-width: inherit;
|
||||
max-width: 800px;
|
||||
}
|
||||
|
||||
div.body p, div.body dd, div.body li, div.body blockquote {
|
||||
-moz-hyphens: auto;
|
||||
-ms-hyphens: auto;
|
||||
-webkit-hyphens: auto;
|
||||
hyphens: auto;
|
||||
}
|
||||
|
||||
a.headerlink {
|
||||
visibility: hidden;
|
||||
}
|
||||
|
||||
a:visited {
|
||||
color: #551A8B;
|
||||
}
|
||||
|
||||
h1:hover > a.headerlink,
|
||||
h2:hover > a.headerlink,
|
||||
h3:hover > a.headerlink,
|
||||
h4:hover > a.headerlink,
|
||||
h5:hover > a.headerlink,
|
||||
h6:hover > a.headerlink,
|
||||
dt:hover > a.headerlink,
|
||||
caption:hover > a.headerlink,
|
||||
p.caption:hover > a.headerlink,
|
||||
div.code-block-caption:hover > a.headerlink {
|
||||
visibility: visible;
|
||||
}
|
||||
|
||||
div.body p.caption {
|
||||
text-align: inherit;
|
||||
}
|
||||
|
||||
div.body td {
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
.first {
|
||||
margin-top: 0 !important;
|
||||
}
|
||||
|
||||
p.rubric {
|
||||
margin-top: 30px;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
img.align-left, figure.align-left, .figure.align-left, object.align-left {
|
||||
clear: left;
|
||||
float: left;
|
||||
margin-right: 1em;
|
||||
}
|
||||
|
||||
img.align-right, figure.align-right, .figure.align-right, object.align-right {
|
||||
clear: right;
|
||||
float: right;
|
||||
margin-left: 1em;
|
||||
}
|
||||
|
||||
img.align-center, figure.align-center, .figure.align-center, object.align-center {
|
||||
display: block;
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
img.align-default, figure.align-default, .figure.align-default {
|
||||
display: block;
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
.align-left {
|
||||
text-align: left;
|
||||
}
|
||||
|
||||
.align-center {
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.align-default {
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.align-right {
|
||||
text-align: right;
|
||||
}
|
||||
|
||||
/* -- sidebars -------------------------------------------------------------- */
|
||||
|
||||
div.sidebar,
|
||||
aside.sidebar {
|
||||
margin: 0 0 0.5em 1em;
|
||||
border: 1px solid #ddb;
|
||||
padding: 7px;
|
||||
background-color: #ffe;
|
||||
width: 40%;
|
||||
float: right;
|
||||
clear: right;
|
||||
overflow-x: auto;
|
||||
}
|
||||
|
||||
p.sidebar-title {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
nav.contents,
|
||||
aside.topic,
|
||||
div.admonition, div.topic, blockquote {
|
||||
clear: left;
|
||||
}
|
||||
|
||||
/* -- topics ---------------------------------------------------------------- */
|
||||
|
||||
nav.contents,
|
||||
aside.topic,
|
||||
div.topic {
|
||||
border: 1px solid #ccc;
|
||||
padding: 7px;
|
||||
margin: 10px 0 10px 0;
|
||||
}
|
||||
|
||||
p.topic-title {
|
||||
font-size: 1.1em;
|
||||
font-weight: bold;
|
||||
margin-top: 10px;
|
||||
}
|
||||
|
||||
/* -- admonitions ----------------------------------------------------------- */
|
||||
|
||||
div.admonition {
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
padding: 7px;
|
||||
}
|
||||
|
||||
div.admonition dt {
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
p.admonition-title {
|
||||
margin: 0px 10px 5px 0px;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
div.body p.centered {
|
||||
text-align: center;
|
||||
margin-top: 25px;
|
||||
}
|
||||
|
||||
/* -- content of sidebars/topics/admonitions -------------------------------- */
|
||||
|
||||
div.sidebar > :last-child,
|
||||
aside.sidebar > :last-child,
|
||||
nav.contents > :last-child,
|
||||
aside.topic > :last-child,
|
||||
div.topic > :last-child,
|
||||
div.admonition > :last-child {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
div.sidebar::after,
|
||||
aside.sidebar::after,
|
||||
nav.contents::after,
|
||||
aside.topic::after,
|
||||
div.topic::after,
|
||||
div.admonition::after,
|
||||
blockquote::after {
|
||||
display: block;
|
||||
content: '';
|
||||
clear: both;
|
||||
}
|
||||
|
||||
/* -- tables ---------------------------------------------------------------- */
|
||||
|
||||
table.docutils {
|
||||
margin-top: 10px;
|
||||
margin-bottom: 10px;
|
||||
border: 0;
|
||||
border-collapse: collapse;
|
||||
}
|
||||
|
||||
table.align-center {
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
table.align-default {
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
table caption span.caption-number {
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
table caption span.caption-text {
|
||||
}
|
||||
|
||||
table.docutils td, table.docutils th {
|
||||
padding: 1px 8px 1px 5px;
|
||||
border-top: 0;
|
||||
border-left: 0;
|
||||
border-right: 0;
|
||||
border-bottom: 1px solid #aaa;
|
||||
}
|
||||
|
||||
th {
|
||||
text-align: left;
|
||||
padding-right: 5px;
|
||||
}
|
||||
|
||||
table.citation {
|
||||
border-left: solid 1px gray;
|
||||
margin-left: 1px;
|
||||
}
|
||||
|
||||
table.citation td {
|
||||
border-bottom: none;
|
||||
}
|
||||
|
||||
th > :first-child,
|
||||
td > :first-child {
|
||||
margin-top: 0px;
|
||||
}
|
||||
|
||||
th > :last-child,
|
||||
td > :last-child {
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
/* -- figures --------------------------------------------------------------- */
|
||||
|
||||
div.figure, figure {
|
||||
margin: 0.5em;
|
||||
padding: 0.5em;
|
||||
}
|
||||
|
||||
div.figure p.caption, figcaption {
|
||||
padding: 0.3em;
|
||||
}
|
||||
|
||||
div.figure p.caption span.caption-number,
|
||||
figcaption span.caption-number {
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
div.figure p.caption span.caption-text,
|
||||
figcaption span.caption-text {
|
||||
}
|
||||
|
||||
/* -- field list styles ----------------------------------------------------- */
|
||||
|
||||
table.field-list td, table.field-list th {
|
||||
border: 0 !important;
|
||||
}
|
||||
|
||||
.field-list ul {
|
||||
margin: 0;
|
||||
padding-left: 1em;
|
||||
}
|
||||
|
||||
.field-list p {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
.field-name {
|
||||
-moz-hyphens: manual;
|
||||
-ms-hyphens: manual;
|
||||
-webkit-hyphens: manual;
|
||||
hyphens: manual;
|
||||
}
|
||||
|
||||
/* -- hlist styles ---------------------------------------------------------- */
|
||||
|
||||
table.hlist {
|
||||
margin: 1em 0;
|
||||
}
|
||||
|
||||
table.hlist td {
|
||||
vertical-align: top;
|
||||
}
|
||||
|
||||
/* -- object description styles --------------------------------------------- */
|
||||
|
||||
.sig {
|
||||
font-family: 'Consolas', 'Menlo', 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
|
||||
}
|
||||
|
||||
.sig-name, code.descname {
|
||||
background-color: transparent;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
.sig-name {
|
||||
font-size: 1.1em;
|
||||
}
|
||||
|
||||
code.descname {
|
||||
font-size: 1.2em;
|
||||
}
|
||||
|
||||
.sig-prename, code.descclassname {
|
||||
background-color: transparent;
|
||||
}
|
||||
|
||||
.optional {
|
||||
font-size: 1.3em;
|
||||
}
|
||||
|
||||
.sig-paren {
|
||||
font-size: larger;
|
||||
}
|
||||
|
||||
.sig-param.n {
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
/* C++ specific styling */
|
||||
|
||||
.sig-inline.c-texpr,
|
||||
.sig-inline.cpp-texpr {
|
||||
font-family: unset;
|
||||
}
|
||||
|
||||
.sig.c .k, .sig.c .kt,
|
||||
.sig.cpp .k, .sig.cpp .kt {
|
||||
color: #0033B3;
|
||||
}
|
||||
|
||||
.sig.c .m,
|
||||
.sig.cpp .m {
|
||||
color: #1750EB;
|
||||
}
|
||||
|
||||
.sig.c .s, .sig.c .sc,
|
||||
.sig.cpp .s, .sig.cpp .sc {
|
||||
color: #067D17;
|
||||
}
|
||||
|
||||
|
||||
/* -- other body styles ----------------------------------------------------- */
|
||||
|
||||
ol.arabic {
|
||||
list-style: decimal;
|
||||
}
|
||||
|
||||
ol.loweralpha {
|
||||
list-style: lower-alpha;
|
||||
}
|
||||
|
||||
ol.upperalpha {
|
||||
list-style: upper-alpha;
|
||||
}
|
||||
|
||||
ol.lowerroman {
|
||||
list-style: lower-roman;
|
||||
}
|
||||
|
||||
ol.upperroman {
|
||||
list-style: upper-roman;
|
||||
}
|
||||
|
||||
:not(li) > ol > li:first-child > :first-child,
|
||||
:not(li) > ul > li:first-child > :first-child {
|
||||
margin-top: 0px;
|
||||
}
|
||||
|
||||
:not(li) > ol > li:last-child > :last-child,
|
||||
:not(li) > ul > li:last-child > :last-child {
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
ol.simple ol p,
|
||||
ol.simple ul p,
|
||||
ul.simple ol p,
|
||||
ul.simple ul p {
|
||||
margin-top: 0;
|
||||
}
|
||||
|
||||
ol.simple > li:not(:first-child) > p,
|
||||
ul.simple > li:not(:first-child) > p {
|
||||
margin-top: 0;
|
||||
}
|
||||
|
||||
ol.simple p,
|
||||
ul.simple p {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
aside.footnote > span,
|
||||
div.citation > span {
|
||||
float: left;
|
||||
}
|
||||
aside.footnote > span:last-of-type,
|
||||
div.citation > span:last-of-type {
|
||||
padding-right: 0.5em;
|
||||
}
|
||||
aside.footnote > p {
|
||||
margin-left: 2em;
|
||||
}
|
||||
div.citation > p {
|
||||
margin-left: 4em;
|
||||
}
|
||||
aside.footnote > p:last-of-type,
|
||||
div.citation > p:last-of-type {
|
||||
margin-bottom: 0em;
|
||||
}
|
||||
aside.footnote > p:last-of-type:after,
|
||||
div.citation > p:last-of-type:after {
|
||||
content: "";
|
||||
clear: both;
|
||||
}
|
||||
|
||||
dl.field-list {
|
||||
display: grid;
|
||||
grid-template-columns: fit-content(30%) auto;
|
||||
}
|
||||
|
||||
dl.field-list > dt {
|
||||
font-weight: bold;
|
||||
word-break: break-word;
|
||||
padding-left: 0.5em;
|
||||
padding-right: 5px;
|
||||
}
|
||||
|
||||
dl.field-list > dd {
|
||||
padding-left: 0.5em;
|
||||
margin-top: 0em;
|
||||
margin-left: 0em;
|
||||
margin-bottom: 0em;
|
||||
}
|
||||
|
||||
dl {
|
||||
margin-bottom: 15px;
|
||||
}
|
||||
|
||||
dd > :first-child {
|
||||
margin-top: 0px;
|
||||
}
|
||||
|
||||
dd ul, dd table {
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
dd {
|
||||
margin-top: 3px;
|
||||
margin-bottom: 10px;
|
||||
margin-left: 30px;
|
||||
}
|
||||
|
||||
.sig dd {
|
||||
margin-top: 0px;
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
.sig dl {
|
||||
margin-top: 0px;
|
||||
margin-bottom: 0px;
|
||||
}
|
||||
|
||||
dl > dd:last-child,
|
||||
dl > dd:last-child > :last-child {
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
dt:target, span.highlighted {
|
||||
background-color: #fbe54e;
|
||||
}
|
||||
|
||||
rect.highlighted {
|
||||
fill: #fbe54e;
|
||||
}
|
||||
|
||||
dl.glossary dt {
|
||||
font-weight: bold;
|
||||
font-size: 1.1em;
|
||||
}
|
||||
|
||||
.versionmodified {
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
.system-message {
|
||||
background-color: #fda;
|
||||
padding: 5px;
|
||||
border: 3px solid red;
|
||||
}
|
||||
|
||||
.footnote:target {
|
||||
background-color: #ffa;
|
||||
}
|
||||
|
||||
.line-block {
|
||||
display: block;
|
||||
margin-top: 1em;
|
||||
margin-bottom: 1em;
|
||||
}
|
||||
|
||||
.line-block .line-block {
|
||||
margin-top: 0;
|
||||
margin-bottom: 0;
|
||||
margin-left: 1.5em;
|
||||
}
|
||||
|
||||
.guilabel, .menuselection {
|
||||
font-family: sans-serif;
|
||||
}
|
||||
|
||||
.accelerator {
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
.classifier {
|
||||
font-style: oblique;
|
||||
}
|
||||
|
||||
.classifier:before {
|
||||
font-style: normal;
|
||||
margin: 0 0.5em;
|
||||
content: ":";
|
||||
display: inline-block;
|
||||
}
|
||||
|
||||
abbr, acronym {
|
||||
border-bottom: dotted 1px;
|
||||
cursor: help;
|
||||
}
|
||||
|
||||
/* -- code displays --------------------------------------------------------- */
|
||||
|
||||
pre {
|
||||
overflow: auto;
|
||||
overflow-y: hidden; /* fixes display issues on Chrome browsers */
|
||||
}
|
||||
|
||||
pre, div[class*="highlight-"] {
|
||||
clear: both;
|
||||
}
|
||||
|
||||
span.pre {
|
||||
-moz-hyphens: none;
|
||||
-ms-hyphens: none;
|
||||
-webkit-hyphens: none;
|
||||
hyphens: none;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
div[class*="highlight-"] {
|
||||
margin: 1em 0;
|
||||
}
|
||||
|
||||
td.linenos pre {
|
||||
border: 0;
|
||||
background-color: transparent;
|
||||
color: #aaa;
|
||||
}
|
||||
|
||||
table.highlighttable {
|
||||
display: block;
|
||||
}
|
||||
|
||||
table.highlighttable tbody {
|
||||
display: block;
|
||||
}
|
||||
|
||||
table.highlighttable tr {
|
||||
display: flex;
|
||||
}
|
||||
|
||||
table.highlighttable td {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
table.highlighttable td.linenos {
|
||||
padding-right: 0.5em;
|
||||
}
|
||||
|
||||
table.highlighttable td.code {
|
||||
flex: 1;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.highlight .hll {
|
||||
display: block;
|
||||
}
|
||||
|
||||
div.highlight pre,
|
||||
table.highlighttable pre {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
div.code-block-caption + div {
|
||||
margin-top: 0;
|
||||
}
|
||||
|
||||
div.code-block-caption {
|
||||
margin-top: 1em;
|
||||
padding: 2px 5px;
|
||||
font-size: small;
|
||||
}
|
||||
|
||||
div.code-block-caption code {
|
||||
background-color: transparent;
|
||||
}
|
||||
|
||||
table.highlighttable td.linenos,
|
||||
span.linenos,
|
||||
div.highlight span.gp { /* gp: Generic.Prompt */
|
||||
user-select: none;
|
||||
-webkit-user-select: text; /* Safari fallback only */
|
||||
-webkit-user-select: none; /* Chrome/Safari */
|
||||
-moz-user-select: none; /* Firefox */
|
||||
-ms-user-select: none; /* IE10+ */
|
||||
}
|
||||
|
||||
div.code-block-caption span.caption-number {
|
||||
padding: 0.1em 0.3em;
|
||||
font-style: italic;
|
||||
}
|
||||
|
||||
div.code-block-caption span.caption-text {
|
||||
}
|
||||
|
||||
div.literal-block-wrapper {
|
||||
margin: 1em 0;
|
||||
}
|
||||
|
||||
code.xref, a code {
|
||||
background-color: transparent;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
h1 code, h2 code, h3 code, h4 code, h5 code, h6 code {
|
||||
background-color: transparent;
|
||||
}
|
||||
|
||||
.viewcode-link {
|
||||
float: right;
|
||||
}
|
||||
|
||||
.viewcode-back {
|
||||
float: right;
|
||||
font-family: sans-serif;
|
||||
}
|
||||
|
||||
div.viewcode-block:target {
|
||||
margin: -1px -10px;
|
||||
padding: 0 10px;
|
||||
}
|
||||
|
||||
/* -- math display ---------------------------------------------------------- */
|
||||
|
||||
img.math {
|
||||
vertical-align: middle;
|
||||
}
|
||||
|
||||
div.body div.math p {
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
span.eqno {
|
||||
float: right;
|
||||
}
|
||||
|
||||
span.eqno a.headerlink {
|
||||
position: absolute;
|
||||
z-index: 1;
|
||||
}
|
||||
|
||||
div.math:hover a.headerlink {
|
||||
visibility: visible;
|
||||
}
|
||||
|
||||
/* -- printout stylesheet --------------------------------------------------- */
|
||||
|
||||
@media print {
|
||||
div.document,
|
||||
div.documentwrapper,
|
||||
div.bodywrapper {
|
||||
margin: 0 !important;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
div.sphinxsidebar,
|
||||
div.related,
|
||||
div.footer,
|
||||
#top-link {
|
||||
display: none;
|
||||
}
|
||||
}
|
||||
|
|
@ -1 +0,0 @@
|
|||
/* This file intentionally left blank. */
|
||||
|
|
@ -1,149 +0,0 @@
|
|||
/*
|
||||
* Base JavaScript utilities for all Sphinx HTML documentation.
|
||||
*/
|
||||
"use strict";
|
||||
|
||||
const BLACKLISTED_KEY_CONTROL_ELEMENTS = new Set([
|
||||
"TEXTAREA",
|
||||
"INPUT",
|
||||
"SELECT",
|
||||
"BUTTON",
|
||||
]);
|
||||
|
||||
const _ready = (callback) => {
|
||||
if (document.readyState !== "loading") {
|
||||
callback();
|
||||
} else {
|
||||
document.addEventListener("DOMContentLoaded", callback);
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Small JavaScript module for the documentation.
|
||||
*/
|
||||
const Documentation = {
|
||||
init: () => {
|
||||
Documentation.initDomainIndexTable();
|
||||
Documentation.initOnKeyListeners();
|
||||
},
|
||||
|
||||
/**
|
||||
* i18n support
|
||||
*/
|
||||
TRANSLATIONS: {},
|
||||
PLURAL_EXPR: (n) => (n === 1 ? 0 : 1),
|
||||
LOCALE: "unknown",
|
||||
|
||||
// gettext and ngettext don't access this so that the functions
|
||||
// can safely bound to a different name (_ = Documentation.gettext)
|
||||
gettext: (string) => {
|
||||
const translated = Documentation.TRANSLATIONS[string];
|
||||
switch (typeof translated) {
|
||||
case "undefined":
|
||||
return string; // no translation
|
||||
case "string":
|
||||
return translated; // translation exists
|
||||
default:
|
||||
return translated[0]; // (singular, plural) translation tuple exists
|
||||
}
|
||||
},
|
||||
|
||||
ngettext: (singular, plural, n) => {
|
||||
const translated = Documentation.TRANSLATIONS[singular];
|
||||
if (typeof translated !== "undefined")
|
||||
return translated[Documentation.PLURAL_EXPR(n)];
|
||||
return n === 1 ? singular : plural;
|
||||
},
|
||||
|
||||
addTranslations: (catalog) => {
|
||||
Object.assign(Documentation.TRANSLATIONS, catalog.messages);
|
||||
Documentation.PLURAL_EXPR = new Function(
|
||||
"n",
|
||||
`return (${catalog.plural_expr})`
|
||||
);
|
||||
Documentation.LOCALE = catalog.locale;
|
||||
},
|
||||
|
||||
/**
|
||||
* helper function to focus on search bar
|
||||
*/
|
||||
focusSearchBar: () => {
|
||||
document.querySelectorAll("input[name=q]")[0]?.focus();
|
||||
},
|
||||
|
||||
/**
|
||||
* Initialise the domain index toggle buttons
|
||||
*/
|
||||
initDomainIndexTable: () => {
|
||||
const toggler = (el) => {
|
||||
const idNumber = el.id.substr(7);
|
||||
const toggledRows = document.querySelectorAll(`tr.cg-${idNumber}`);
|
||||
if (el.src.substr(-9) === "minus.png") {
|
||||
el.src = `${el.src.substr(0, el.src.length - 9)}plus.png`;
|
||||
toggledRows.forEach((el) => (el.style.display = "none"));
|
||||
} else {
|
||||
el.src = `${el.src.substr(0, el.src.length - 8)}minus.png`;
|
||||
toggledRows.forEach((el) => (el.style.display = ""));
|
||||
}
|
||||
};
|
||||
|
||||
const togglerElements = document.querySelectorAll("img.toggler");
|
||||
togglerElements.forEach((el) =>
|
||||
el.addEventListener("click", (event) => toggler(event.currentTarget))
|
||||
);
|
||||
togglerElements.forEach((el) => (el.style.display = ""));
|
||||
if (DOCUMENTATION_OPTIONS.COLLAPSE_INDEX) togglerElements.forEach(toggler);
|
||||
},
|
||||
|
||||
initOnKeyListeners: () => {
|
||||
// only install a listener if it is really needed
|
||||
if (
|
||||
!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS &&
|
||||
!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS
|
||||
)
|
||||
return;
|
||||
|
||||
document.addEventListener("keydown", (event) => {
|
||||
// bail for input elements
|
||||
if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return;
|
||||
// bail with special keys
|
||||
if (event.altKey || event.ctrlKey || event.metaKey) return;
|
||||
|
||||
if (!event.shiftKey) {
|
||||
switch (event.key) {
|
||||
case "ArrowLeft":
|
||||
if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
|
||||
|
||||
const prevLink = document.querySelector('link[rel="prev"]');
|
||||
if (prevLink && prevLink.href) {
|
||||
window.location.href = prevLink.href;
|
||||
event.preventDefault();
|
||||
}
|
||||
break;
|
||||
case "ArrowRight":
|
||||
if (!DOCUMENTATION_OPTIONS.NAVIGATION_WITH_KEYS) break;
|
||||
|
||||
const nextLink = document.querySelector('link[rel="next"]');
|
||||
if (nextLink && nextLink.href) {
|
||||
window.location.href = nextLink.href;
|
||||
event.preventDefault();
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// some keyboard layouts may need Shift to get /
|
||||
switch (event.key) {
|
||||
case "/":
|
||||
if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) break;
|
||||
Documentation.focusSearchBar();
|
||||
event.preventDefault();
|
||||
}
|
||||
});
|
||||
},
|
||||
};
|
||||
|
||||
// quick alias for translations
|
||||
const _ = Documentation.gettext;
|
||||
|
||||
_ready(Documentation.init);
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
const DOCUMENTATION_OPTIONS = {
|
||||
VERSION: '0.1',
|
||||
LANGUAGE: 'zh',
|
||||
COLLAPSE_INDEX: false,
|
||||
BUILDER: 'html',
|
||||
FILE_SUFFIX: '.html',
|
||||
LINK_SUFFIX: '.html',
|
||||
HAS_SOURCE: true,
|
||||
SOURCELINK_SUFFIX: '.txt',
|
||||
NAVIGATION_WITH_KEYS: false,
|
||||
SHOW_SEARCH_SUMMARY: true,
|
||||
ENABLE_SEARCH_SHORTCUTS: true,
|
||||
};
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 286 B |
|
|
@ -1,5 +0,0 @@
|
|||
<svg xmlns="http://www.w3.org/2000/svg" width="80" height="80" viewBox="0 0 250 250" fill="#fff">
|
||||
<path d="M0 0l115 115h15l12 27 108 108V0z" fill="#151513"/>
|
||||
<path d="M128 109c-15-9-9-19-9-19 3-7 2-11 2-11-1-7 3-2 3-2 4 5 2 11 2 11-3 10 5 15 9 16"/>
|
||||
<path d="M115 115s4 2 5 0l14-14c3-2 6-3 8-3-8-11-15-24 2-41 5-5 10-7 16-7 1-2 3-7 12-11 0 0 5 3 7 16 4 2 8 5 12 9s7 8 9 12c14 3 17 7 17 7-4 8-9 11-11 11 0 6-2 11-7 16-16 16-30 10-41 2 0 3-1 7-5 11l-12 11c-1 1 1 5 1 5z"/>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 490 B |
|
|
@ -1,192 +0,0 @@
|
|||
/*
|
||||
* This script contains the language-specific data used by searchtools.js,
|
||||
* namely the list of stopwords, stemmer, scorer and splitter.
|
||||
*/
|
||||
|
||||
var stopwords = ["a", "and", "are", "as", "at", "be", "but", "by", "for", "if", "in", "into", "is", "it", "near", "no", "not", "of", "on", "or", "such", "that", "the", "their", "then", "there", "these", "they", "this", "to", "was", "will", "with"];
|
||||
|
||||
|
||||
/* Non-minified version is copied as a separate JS file, if available */
|
||||
|
||||
/**
|
||||
* Porter Stemmer
|
||||
*/
|
||||
var Stemmer = function() {
|
||||
|
||||
var step2list = {
|
||||
ational: 'ate',
|
||||
tional: 'tion',
|
||||
enci: 'ence',
|
||||
anci: 'ance',
|
||||
izer: 'ize',
|
||||
bli: 'ble',
|
||||
alli: 'al',
|
||||
entli: 'ent',
|
||||
eli: 'e',
|
||||
ousli: 'ous',
|
||||
ization: 'ize',
|
||||
ation: 'ate',
|
||||
ator: 'ate',
|
||||
alism: 'al',
|
||||
iveness: 'ive',
|
||||
fulness: 'ful',
|
||||
ousness: 'ous',
|
||||
aliti: 'al',
|
||||
iviti: 'ive',
|
||||
biliti: 'ble',
|
||||
logi: 'log'
|
||||
};
|
||||
|
||||
var step3list = {
|
||||
icate: 'ic',
|
||||
ative: '',
|
||||
alize: 'al',
|
||||
iciti: 'ic',
|
||||
ical: 'ic',
|
||||
ful: '',
|
||||
ness: ''
|
||||
};
|
||||
|
||||
var c = "[^aeiou]"; // consonant
|
||||
var v = "[aeiouy]"; // vowel
|
||||
var C = c + "[^aeiouy]*"; // consonant sequence
|
||||
var V = v + "[aeiou]*"; // vowel sequence
|
||||
|
||||
var mgr0 = "^(" + C + ")?" + V + C; // [C]VC... is m>0
|
||||
var meq1 = "^(" + C + ")?" + V + C + "(" + V + ")?$"; // [C]VC[V] is m=1
|
||||
var mgr1 = "^(" + C + ")?" + V + C + V + C; // [C]VCVC... is m>1
|
||||
var s_v = "^(" + C + ")?" + v; // vowel in stem
|
||||
|
||||
this.stemWord = function (w) {
|
||||
var stem;
|
||||
var suffix;
|
||||
var firstch;
|
||||
var origword = w;
|
||||
|
||||
if (w.length < 3)
|
||||
return w;
|
||||
|
||||
var re;
|
||||
var re2;
|
||||
var re3;
|
||||
var re4;
|
||||
|
||||
firstch = w.substr(0,1);
|
||||
if (firstch == "y")
|
||||
w = firstch.toUpperCase() + w.substr(1);
|
||||
|
||||
// Step 1a
|
||||
re = /^(.+?)(ss|i)es$/;
|
||||
re2 = /^(.+?)([^s])s$/;
|
||||
|
||||
if (re.test(w))
|
||||
w = w.replace(re,"$1$2");
|
||||
else if (re2.test(w))
|
||||
w = w.replace(re2,"$1$2");
|
||||
|
||||
// Step 1b
|
||||
re = /^(.+?)eed$/;
|
||||
re2 = /^(.+?)(ed|ing)$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
re = new RegExp(mgr0);
|
||||
if (re.test(fp[1])) {
|
||||
re = /.$/;
|
||||
w = w.replace(re,"");
|
||||
}
|
||||
}
|
||||
else if (re2.test(w)) {
|
||||
var fp = re2.exec(w);
|
||||
stem = fp[1];
|
||||
re2 = new RegExp(s_v);
|
||||
if (re2.test(stem)) {
|
||||
w = stem;
|
||||
re2 = /(at|bl|iz)$/;
|
||||
re3 = new RegExp("([^aeiouylsz])\\1$");
|
||||
re4 = new RegExp("^" + C + v + "[^aeiouwxy]$");
|
||||
if (re2.test(w))
|
||||
w = w + "e";
|
||||
else if (re3.test(w)) {
|
||||
re = /.$/;
|
||||
w = w.replace(re,"");
|
||||
}
|
||||
else if (re4.test(w))
|
||||
w = w + "e";
|
||||
}
|
||||
}
|
||||
|
||||
// Step 1c
|
||||
re = /^(.+?)y$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
stem = fp[1];
|
||||
re = new RegExp(s_v);
|
||||
if (re.test(stem))
|
||||
w = stem + "i";
|
||||
}
|
||||
|
||||
// Step 2
|
||||
re = /^(.+?)(ational|tional|enci|anci|izer|bli|alli|entli|eli|ousli|ization|ation|ator|alism|iveness|fulness|ousness|aliti|iviti|biliti|logi)$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
stem = fp[1];
|
||||
suffix = fp[2];
|
||||
re = new RegExp(mgr0);
|
||||
if (re.test(stem))
|
||||
w = stem + step2list[suffix];
|
||||
}
|
||||
|
||||
// Step 3
|
||||
re = /^(.+?)(icate|ative|alize|iciti|ical|ful|ness)$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
stem = fp[1];
|
||||
suffix = fp[2];
|
||||
re = new RegExp(mgr0);
|
||||
if (re.test(stem))
|
||||
w = stem + step3list[suffix];
|
||||
}
|
||||
|
||||
// Step 4
|
||||
re = /^(.+?)(al|ance|ence|er|ic|able|ible|ant|ement|ment|ent|ou|ism|ate|iti|ous|ive|ize)$/;
|
||||
re2 = /^(.+?)(s|t)(ion)$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
stem = fp[1];
|
||||
re = new RegExp(mgr1);
|
||||
if (re.test(stem))
|
||||
w = stem;
|
||||
}
|
||||
else if (re2.test(w)) {
|
||||
var fp = re2.exec(w);
|
||||
stem = fp[1] + fp[2];
|
||||
re2 = new RegExp(mgr1);
|
||||
if (re2.test(stem))
|
||||
w = stem;
|
||||
}
|
||||
|
||||
// Step 5
|
||||
re = /^(.+?)e$/;
|
||||
if (re.test(w)) {
|
||||
var fp = re.exec(w);
|
||||
stem = fp[1];
|
||||
re = new RegExp(mgr1);
|
||||
re2 = new RegExp(meq1);
|
||||
re3 = new RegExp("^" + C + v + "[^aeiouwxy]$");
|
||||
if (re.test(stem) || (re2.test(stem) && !(re3.test(stem))))
|
||||
w = stem;
|
||||
}
|
||||
re = /ll$/;
|
||||
re2 = new RegExp(mgr1);
|
||||
if (re.test(w) && re2.test(w)) {
|
||||
re = /.$/;
|
||||
w = w.replace(re,"");
|
||||
}
|
||||
|
||||
// and turn initial Y back to y
|
||||
if (firstch == "y")
|
||||
w = firstch.toLowerCase() + w.substr(1);
|
||||
return w;
|
||||
}
|
||||
}
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 90 B |
Binary file not shown.
|
Before Width: | Height: | Size: 90 B |
|
|
@ -1,84 +0,0 @@
|
|||
pre { line-height: 125%; }
|
||||
td.linenos .normal { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
span.linenos { color: inherit; background-color: transparent; padding-left: 5px; padding-right: 5px; }
|
||||
td.linenos .special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
|
||||
span.linenos.special { color: #000000; background-color: #ffffc0; padding-left: 5px; padding-right: 5px; }
|
||||
.highlight .hll { background-color: #ffffcc }
|
||||
.highlight { background: #f8f8f8; }
|
||||
.highlight .c { color: #8F5902; font-style: italic } /* Comment */
|
||||
.highlight .err { color: #A40000; border: 1px solid #EF2929 } /* Error */
|
||||
.highlight .g { color: #000 } /* Generic */
|
||||
.highlight .k { color: #004461; font-weight: bold } /* Keyword */
|
||||
.highlight .l { color: #000 } /* Literal */
|
||||
.highlight .n { color: #000 } /* Name */
|
||||
.highlight .o { color: #582800 } /* Operator */
|
||||
.highlight .x { color: #000 } /* Other */
|
||||
.highlight .p { color: #000; font-weight: bold } /* Punctuation */
|
||||
.highlight .ch { color: #8F5902; font-style: italic } /* Comment.Hashbang */
|
||||
.highlight .cm { color: #8F5902; font-style: italic } /* Comment.Multiline */
|
||||
.highlight .cp { color: #8F5902 } /* Comment.Preproc */
|
||||
.highlight .cpf { color: #8F5902; font-style: italic } /* Comment.PreprocFile */
|
||||
.highlight .c1 { color: #8F5902; font-style: italic } /* Comment.Single */
|
||||
.highlight .cs { color: #8F5902; font-style: italic } /* Comment.Special */
|
||||
.highlight .gd { color: #A40000 } /* Generic.Deleted */
|
||||
.highlight .ge { color: #000; font-style: italic } /* Generic.Emph */
|
||||
.highlight .ges { color: #000 } /* Generic.EmphStrong */
|
||||
.highlight .gr { color: #EF2929 } /* Generic.Error */
|
||||
.highlight .gh { color: #000080; font-weight: bold } /* Generic.Heading */
|
||||
.highlight .gi { color: #00A000 } /* Generic.Inserted */
|
||||
.highlight .go { color: #888 } /* Generic.Output */
|
||||
.highlight .gp { color: #745334 } /* Generic.Prompt */
|
||||
.highlight .gs { color: #000; font-weight: bold } /* Generic.Strong */
|
||||
.highlight .gu { color: #800080; font-weight: bold } /* Generic.Subheading */
|
||||
.highlight .gt { color: #A40000; font-weight: bold } /* Generic.Traceback */
|
||||
.highlight .kc { color: #004461; font-weight: bold } /* Keyword.Constant */
|
||||
.highlight .kd { color: #004461; font-weight: bold } /* Keyword.Declaration */
|
||||
.highlight .kn { color: #004461; font-weight: bold } /* Keyword.Namespace */
|
||||
.highlight .kp { color: #004461; font-weight: bold } /* Keyword.Pseudo */
|
||||
.highlight .kr { color: #004461; font-weight: bold } /* Keyword.Reserved */
|
||||
.highlight .kt { color: #004461; font-weight: bold } /* Keyword.Type */
|
||||
.highlight .ld { color: #000 } /* Literal.Date */
|
||||
.highlight .m { color: #900 } /* Literal.Number */
|
||||
.highlight .s { color: #4E9A06 } /* Literal.String */
|
||||
.highlight .na { color: #C4A000 } /* Name.Attribute */
|
||||
.highlight .nb { color: #004461 } /* Name.Builtin */
|
||||
.highlight .nc { color: #000 } /* Name.Class */
|
||||
.highlight .no { color: #000 } /* Name.Constant */
|
||||
.highlight .nd { color: #888 } /* Name.Decorator */
|
||||
.highlight .ni { color: #CE5C00 } /* Name.Entity */
|
||||
.highlight .ne { color: #C00; font-weight: bold } /* Name.Exception */
|
||||
.highlight .nf { color: #000 } /* Name.Function */
|
||||
.highlight .nl { color: #F57900 } /* Name.Label */
|
||||
.highlight .nn { color: #000 } /* Name.Namespace */
|
||||
.highlight .nx { color: #000 } /* Name.Other */
|
||||
.highlight .py { color: #000 } /* Name.Property */
|
||||
.highlight .nt { color: #004461; font-weight: bold } /* Name.Tag */
|
||||
.highlight .nv { color: #000 } /* Name.Variable */
|
||||
.highlight .ow { color: #004461; font-weight: bold } /* Operator.Word */
|
||||
.highlight .pm { color: #000; font-weight: bold } /* Punctuation.Marker */
|
||||
.highlight .w { color: #F8F8F8 } /* Text.Whitespace */
|
||||
.highlight .mb { color: #900 } /* Literal.Number.Bin */
|
||||
.highlight .mf { color: #900 } /* Literal.Number.Float */
|
||||
.highlight .mh { color: #900 } /* Literal.Number.Hex */
|
||||
.highlight .mi { color: #900 } /* Literal.Number.Integer */
|
||||
.highlight .mo { color: #900 } /* Literal.Number.Oct */
|
||||
.highlight .sa { color: #4E9A06 } /* Literal.String.Affix */
|
||||
.highlight .sb { color: #4E9A06 } /* Literal.String.Backtick */
|
||||
.highlight .sc { color: #4E9A06 } /* Literal.String.Char */
|
||||
.highlight .dl { color: #4E9A06 } /* Literal.String.Delimiter */
|
||||
.highlight .sd { color: #8F5902; font-style: italic } /* Literal.String.Doc */
|
||||
.highlight .s2 { color: #4E9A06 } /* Literal.String.Double */
|
||||
.highlight .se { color: #4E9A06 } /* Literal.String.Escape */
|
||||
.highlight .sh { color: #4E9A06 } /* Literal.String.Heredoc */
|
||||
.highlight .si { color: #4E9A06 } /* Literal.String.Interpol */
|
||||
.highlight .sx { color: #4E9A06 } /* Literal.String.Other */
|
||||
.highlight .sr { color: #4E9A06 } /* Literal.String.Regex */
|
||||
.highlight .s1 { color: #4E9A06 } /* Literal.String.Single */
|
||||
.highlight .ss { color: #4E9A06 } /* Literal.String.Symbol */
|
||||
.highlight .bp { color: #3465A4 } /* Name.Builtin.Pseudo */
|
||||
.highlight .fm { color: #000 } /* Name.Function.Magic */
|
||||
.highlight .vc { color: #000 } /* Name.Variable.Class */
|
||||
.highlight .vg { color: #000 } /* Name.Variable.Global */
|
||||
.highlight .vi { color: #000 } /* Name.Variable.Instance */
|
||||
.highlight .vm { color: #000 } /* Name.Variable.Magic */
|
||||
.highlight .il { color: #900 } /* Literal.Number.Integer.Long */
|
||||
|
|
@ -1,635 +0,0 @@
|
|||
/*
|
||||
* Sphinx JavaScript utilities for the full-text search.
|
||||
*/
|
||||
"use strict";
|
||||
|
||||
/**
|
||||
* Simple result scoring code.
|
||||
*/
|
||||
if (typeof Scorer === "undefined") {
|
||||
var Scorer = {
|
||||
// Implement the following function to further tweak the score for each result
|
||||
// The function takes a result array [docname, title, anchor, descr, score, filename]
|
||||
// and returns the new score.
|
||||
/*
|
||||
score: result => {
|
||||
const [docname, title, anchor, descr, score, filename, kind] = result
|
||||
return score
|
||||
},
|
||||
*/
|
||||
|
||||
// query matches the full name of an object
|
||||
objNameMatch: 11,
|
||||
// or matches in the last dotted part of the object name
|
||||
objPartialMatch: 6,
|
||||
// Additive scores depending on the priority of the object
|
||||
objPrio: {
|
||||
0: 15, // used to be importantResults
|
||||
1: 5, // used to be objectResults
|
||||
2: -5, // used to be unimportantResults
|
||||
},
|
||||
// Used when the priority is not in the mapping.
|
||||
objPrioDefault: 0,
|
||||
|
||||
// query found in title
|
||||
title: 15,
|
||||
partialTitle: 7,
|
||||
// query found in terms
|
||||
term: 5,
|
||||
partialTerm: 2,
|
||||
};
|
||||
}
|
||||
|
||||
// Global search result kind enum, used by themes to style search results.
|
||||
class SearchResultKind {
|
||||
static get index() { return "index"; }
|
||||
static get object() { return "object"; }
|
||||
static get text() { return "text"; }
|
||||
static get title() { return "title"; }
|
||||
}
|
||||
|
||||
const _removeChildren = (element) => {
|
||||
while (element && element.lastChild) element.removeChild(element.lastChild);
|
||||
};
|
||||
|
||||
/**
|
||||
* See https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Regular_Expressions#escaping
|
||||
*/
|
||||
const _escapeRegExp = (string) =>
|
||||
string.replace(/[.*+\-?^${}()|[\]\\]/g, "\\$&"); // $& means the whole matched string
|
||||
|
||||
const _displayItem = (item, searchTerms, highlightTerms) => {
|
||||
const docBuilder = DOCUMENTATION_OPTIONS.BUILDER;
|
||||
const docFileSuffix = DOCUMENTATION_OPTIONS.FILE_SUFFIX;
|
||||
const docLinkSuffix = DOCUMENTATION_OPTIONS.LINK_SUFFIX;
|
||||
const showSearchSummary = DOCUMENTATION_OPTIONS.SHOW_SEARCH_SUMMARY;
|
||||
const contentRoot = document.documentElement.dataset.content_root;
|
||||
|
||||
const [docName, title, anchor, descr, score, _filename, kind] = item;
|
||||
|
||||
let listItem = document.createElement("li");
|
||||
// Add a class representing the item's type:
|
||||
// can be used by a theme's CSS selector for styling
|
||||
// See SearchResultKind for the class names.
|
||||
listItem.classList.add(`kind-${kind}`);
|
||||
let requestUrl;
|
||||
let linkUrl;
|
||||
if (docBuilder === "dirhtml") {
|
||||
// dirhtml builder
|
||||
let dirname = docName + "/";
|
||||
if (dirname.match(/\/index\/$/))
|
||||
dirname = dirname.substring(0, dirname.length - 6);
|
||||
else if (dirname === "index/") dirname = "";
|
||||
requestUrl = contentRoot + dirname;
|
||||
linkUrl = requestUrl;
|
||||
} else {
|
||||
// normal html builders
|
||||
requestUrl = contentRoot + docName + docFileSuffix;
|
||||
linkUrl = docName + docLinkSuffix;
|
||||
}
|
||||
let linkEl = listItem.appendChild(document.createElement("a"));
|
||||
linkEl.href = linkUrl + anchor;
|
||||
linkEl.dataset.score = score;
|
||||
linkEl.innerHTML = title;
|
||||
if (descr) {
|
||||
listItem.appendChild(document.createElement("span")).innerHTML =
|
||||
" (" + descr + ")";
|
||||
// highlight search terms in the description
|
||||
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
|
||||
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
|
||||
}
|
||||
else if (showSearchSummary)
|
||||
fetch(requestUrl)
|
||||
.then((responseData) => responseData.text())
|
||||
.then((data) => {
|
||||
if (data)
|
||||
listItem.appendChild(
|
||||
Search.makeSearchSummary(data, searchTerms, anchor)
|
||||
);
|
||||
// highlight search terms in the summary
|
||||
if (SPHINX_HIGHLIGHT_ENABLED) // set in sphinx_highlight.js
|
||||
highlightTerms.forEach((term) => _highlightText(listItem, term, "highlighted"));
|
||||
});
|
||||
Search.output.appendChild(listItem);
|
||||
};
|
||||
const _finishSearch = (resultCount) => {
|
||||
Search.stopPulse();
|
||||
Search.title.innerText = _("Search Results");
|
||||
if (!resultCount)
|
||||
Search.status.innerText = Documentation.gettext(
|
||||
"Your search did not match any documents. Please make sure that all words are spelled correctly and that you've selected enough categories."
|
||||
);
|
||||
else
|
||||
Search.status.innerText = Documentation.ngettext(
|
||||
"Search finished, found one page matching the search query.",
|
||||
"Search finished, found ${resultCount} pages matching the search query.",
|
||||
resultCount,
|
||||
).replace('${resultCount}', resultCount);
|
||||
};
|
||||
const _displayNextItem = (
|
||||
results,
|
||||
resultCount,
|
||||
searchTerms,
|
||||
highlightTerms,
|
||||
) => {
|
||||
// results left, load the summary and display it
|
||||
// this is intended to be dynamic (don't sub resultsCount)
|
||||
if (results.length) {
|
||||
_displayItem(results.pop(), searchTerms, highlightTerms);
|
||||
setTimeout(
|
||||
() => _displayNextItem(results, resultCount, searchTerms, highlightTerms),
|
||||
5
|
||||
);
|
||||
}
|
||||
// search finished, update title and status message
|
||||
else _finishSearch(resultCount);
|
||||
};
|
||||
// Helper function used by query() to order search results.
|
||||
// Each input is an array of [docname, title, anchor, descr, score, filename, kind].
|
||||
// Order the results by score (in opposite order of appearance, since the
|
||||
// `_displayNextItem` function uses pop() to retrieve items) and then alphabetically.
|
||||
const _orderResultsByScoreThenName = (a, b) => {
|
||||
const leftScore = a[4];
|
||||
const rightScore = b[4];
|
||||
if (leftScore === rightScore) {
|
||||
// same score: sort alphabetically
|
||||
const leftTitle = a[1].toLowerCase();
|
||||
const rightTitle = b[1].toLowerCase();
|
||||
if (leftTitle === rightTitle) return 0;
|
||||
return leftTitle > rightTitle ? -1 : 1; // inverted is intentional
|
||||
}
|
||||
return leftScore > rightScore ? 1 : -1;
|
||||
};
|
||||
|
||||
/**
|
||||
* Default splitQuery function. Can be overridden in ``sphinx.search`` with a
|
||||
* custom function per language.
|
||||
*
|
||||
* The regular expression works by splitting the string on consecutive characters
|
||||
* that are not Unicode letters, numbers, underscores, or emoji characters.
|
||||
* This is the same as ``\W+`` in Python, preserving the surrogate pair area.
|
||||
*/
|
||||
if (typeof splitQuery === "undefined") {
|
||||
var splitQuery = (query) => query
|
||||
.split(/[^\p{Letter}\p{Number}_\p{Emoji_Presentation}]+/gu)
|
||||
.filter(term => term) // remove remaining empty strings
|
||||
}
|
||||
|
||||
/**
|
||||
* Search Module
|
||||
*/
|
||||
const Search = {
|
||||
_index: null,
|
||||
_queued_query: null,
|
||||
_pulse_status: -1,
|
||||
|
||||
htmlToText: (htmlString, anchor) => {
|
||||
const htmlElement = new DOMParser().parseFromString(htmlString, 'text/html');
|
||||
for (const removalQuery of [".headerlink", "script", "style"]) {
|
||||
htmlElement.querySelectorAll(removalQuery).forEach((el) => { el.remove() });
|
||||
}
|
||||
if (anchor) {
|
||||
const anchorContent = htmlElement.querySelector(`[role="main"] ${anchor}`);
|
||||
if (anchorContent) return anchorContent.textContent;
|
||||
|
||||
console.warn(
|
||||
`Anchored content block not found. Sphinx search tries to obtain it via DOM query '[role=main] ${anchor}'. Check your theme or template.`
|
||||
);
|
||||
}
|
||||
|
||||
// if anchor not specified or not found, fall back to main content
|
||||
const docContent = htmlElement.querySelector('[role="main"]');
|
||||
if (docContent) return docContent.textContent;
|
||||
|
||||
console.warn(
|
||||
"Content block not found. Sphinx search tries to obtain it via DOM query '[role=main]'. Check your theme or template."
|
||||
);
|
||||
return "";
|
||||
},
|
||||
|
||||
init: () => {
|
||||
const query = new URLSearchParams(window.location.search).get("q");
|
||||
document
|
||||
.querySelectorAll('input[name="q"]')
|
||||
.forEach((el) => (el.value = query));
|
||||
if (query) Search.performSearch(query);
|
||||
},
|
||||
|
||||
loadIndex: (url) =>
|
||||
(document.body.appendChild(document.createElement("script")).src = url),
|
||||
|
||||
setIndex: (index) => {
|
||||
Search._index = index;
|
||||
if (Search._queued_query !== null) {
|
||||
const query = Search._queued_query;
|
||||
Search._queued_query = null;
|
||||
Search.query(query);
|
||||
}
|
||||
},
|
||||
|
||||
hasIndex: () => Search._index !== null,
|
||||
|
||||
deferQuery: (query) => (Search._queued_query = query),
|
||||
|
||||
stopPulse: () => (Search._pulse_status = -1),
|
||||
|
||||
startPulse: () => {
|
||||
if (Search._pulse_status >= 0) return;
|
||||
|
||||
const pulse = () => {
|
||||
Search._pulse_status = (Search._pulse_status + 1) % 4;
|
||||
Search.dots.innerText = ".".repeat(Search._pulse_status);
|
||||
if (Search._pulse_status >= 0) window.setTimeout(pulse, 500);
|
||||
};
|
||||
pulse();
|
||||
},
|
||||
|
||||
/**
|
||||
* perform a search for something (or wait until index is loaded)
|
||||
*/
|
||||
performSearch: (query) => {
|
||||
// create the required interface elements
|
||||
const searchText = document.createElement("h2");
|
||||
searchText.textContent = _("Searching");
|
||||
const searchSummary = document.createElement("p");
|
||||
searchSummary.classList.add("search-summary");
|
||||
searchSummary.innerText = "";
|
||||
const searchList = document.createElement("ul");
|
||||
searchList.setAttribute("role", "list");
|
||||
searchList.classList.add("search");
|
||||
|
||||
const out = document.getElementById("search-results");
|
||||
Search.title = out.appendChild(searchText);
|
||||
Search.dots = Search.title.appendChild(document.createElement("span"));
|
||||
Search.status = out.appendChild(searchSummary);
|
||||
Search.output = out.appendChild(searchList);
|
||||
|
||||
const searchProgress = document.getElementById("search-progress");
|
||||
// Some themes don't use the search progress node
|
||||
if (searchProgress) {
|
||||
searchProgress.innerText = _("Preparing search...");
|
||||
}
|
||||
Search.startPulse();
|
||||
|
||||
// index already loaded, the browser was quick!
|
||||
if (Search.hasIndex()) Search.query(query);
|
||||
else Search.deferQuery(query);
|
||||
},
|
||||
|
||||
_parseQuery: (query) => {
|
||||
// stem the search terms and add them to the correct list
|
||||
const stemmer = new Stemmer();
|
||||
const searchTerms = new Set();
|
||||
const excludedTerms = new Set();
|
||||
const highlightTerms = new Set();
|
||||
const objectTerms = new Set(splitQuery(query.toLowerCase().trim()));
|
||||
splitQuery(query.trim()).forEach((queryTerm) => {
|
||||
const queryTermLower = queryTerm.toLowerCase();
|
||||
|
||||
// maybe skip this "word"
|
||||
// stopwords array is from language_data.js
|
||||
if (
|
||||
stopwords.indexOf(queryTermLower) !== -1 ||
|
||||
queryTerm.match(/^\d+$/)
|
||||
)
|
||||
return;
|
||||
|
||||
// stem the word
|
||||
let word = stemmer.stemWord(queryTermLower);
|
||||
// select the correct list
|
||||
if (word[0] === "-") excludedTerms.add(word.substr(1));
|
||||
else {
|
||||
searchTerms.add(word);
|
||||
highlightTerms.add(queryTermLower);
|
||||
}
|
||||
});
|
||||
|
||||
if (SPHINX_HIGHLIGHT_ENABLED) { // set in sphinx_highlight.js
|
||||
localStorage.setItem("sphinx_highlight_terms", [...highlightTerms].join(" "))
|
||||
}
|
||||
|
||||
// console.debug("SEARCH: searching for:");
|
||||
// console.info("required: ", [...searchTerms]);
|
||||
// console.info("excluded: ", [...excludedTerms]);
|
||||
|
||||
return [query, searchTerms, excludedTerms, highlightTerms, objectTerms];
|
||||
},
|
||||
|
||||
/**
|
||||
* execute search (requires search index to be loaded)
|
||||
*/
|
||||
_performSearch: (query, searchTerms, excludedTerms, highlightTerms, objectTerms) => {
|
||||
const filenames = Search._index.filenames;
|
||||
const docNames = Search._index.docnames;
|
||||
const titles = Search._index.titles;
|
||||
const allTitles = Search._index.alltitles;
|
||||
const indexEntries = Search._index.indexentries;
|
||||
|
||||
// Collect multiple result groups to be sorted separately and then ordered.
|
||||
// Each is an array of [docname, title, anchor, descr, score, filename, kind].
|
||||
const normalResults = [];
|
||||
const nonMainIndexResults = [];
|
||||
|
||||
_removeChildren(document.getElementById("search-progress"));
|
||||
|
||||
const queryLower = query.toLowerCase().trim();
|
||||
for (const [title, foundTitles] of Object.entries(allTitles)) {
|
||||
if (title.toLowerCase().trim().includes(queryLower) && (queryLower.length >= title.length/2)) {
|
||||
for (const [file, id] of foundTitles) {
|
||||
const score = Math.round(Scorer.title * queryLower.length / title.length);
|
||||
const boost = titles[file] === title ? 1 : 0; // add a boost for document titles
|
||||
normalResults.push([
|
||||
docNames[file],
|
||||
titles[file] !== title ? `${titles[file]} > ${title}` : title,
|
||||
id !== null ? "#" + id : "",
|
||||
null,
|
||||
score + boost,
|
||||
filenames[file],
|
||||
SearchResultKind.title,
|
||||
]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// search for explicit entries in index directives
|
||||
for (const [entry, foundEntries] of Object.entries(indexEntries)) {
|
||||
if (entry.includes(queryLower) && (queryLower.length >= entry.length/2)) {
|
||||
for (const [file, id, isMain] of foundEntries) {
|
||||
const score = Math.round(100 * queryLower.length / entry.length);
|
||||
const result = [
|
||||
docNames[file],
|
||||
titles[file],
|
||||
id ? "#" + id : "",
|
||||
null,
|
||||
score,
|
||||
filenames[file],
|
||||
SearchResultKind.index,
|
||||
];
|
||||
if (isMain) {
|
||||
normalResults.push(result);
|
||||
} else {
|
||||
nonMainIndexResults.push(result);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// lookup as object
|
||||
objectTerms.forEach((term) =>
|
||||
normalResults.push(...Search.performObjectSearch(term, objectTerms))
|
||||
);
|
||||
|
||||
// lookup as search terms in fulltext
|
||||
normalResults.push(...Search.performTermsSearch(searchTerms, excludedTerms));
|
||||
|
||||
// let the scorer override scores with a custom scoring function
|
||||
if (Scorer.score) {
|
||||
normalResults.forEach((item) => (item[4] = Scorer.score(item)));
|
||||
nonMainIndexResults.forEach((item) => (item[4] = Scorer.score(item)));
|
||||
}
|
||||
|
||||
// Sort each group of results by score and then alphabetically by name.
|
||||
normalResults.sort(_orderResultsByScoreThenName);
|
||||
nonMainIndexResults.sort(_orderResultsByScoreThenName);
|
||||
|
||||
// Combine the result groups in (reverse) order.
|
||||
// Non-main index entries are typically arbitrary cross-references,
|
||||
// so display them after other results.
|
||||
let results = [...nonMainIndexResults, ...normalResults];
|
||||
|
||||
// remove duplicate search results
|
||||
// note the reversing of results, so that in the case of duplicates, the highest-scoring entry is kept
|
||||
let seen = new Set();
|
||||
results = results.reverse().reduce((acc, result) => {
|
||||
let resultStr = result.slice(0, 4).concat([result[5]]).map(v => String(v)).join(',');
|
||||
if (!seen.has(resultStr)) {
|
||||
acc.push(result);
|
||||
seen.add(resultStr);
|
||||
}
|
||||
return acc;
|
||||
}, []);
|
||||
|
||||
return results.reverse();
|
||||
},
|
||||
|
||||
query: (query) => {
|
||||
const [searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms] = Search._parseQuery(query);
|
||||
const results = Search._performSearch(searchQuery, searchTerms, excludedTerms, highlightTerms, objectTerms);
|
||||
|
||||
// for debugging
|
||||
//Search.lastresults = results.slice(); // a copy
|
||||
// console.info("search results:", Search.lastresults);
|
||||
|
||||
// print the results
|
||||
_displayNextItem(results, results.length, searchTerms, highlightTerms);
|
||||
},
|
||||
|
||||
/**
|
||||
* search for object names
|
||||
*/
|
||||
performObjectSearch: (object, objectTerms) => {
|
||||
const filenames = Search._index.filenames;
|
||||
const docNames = Search._index.docnames;
|
||||
const objects = Search._index.objects;
|
||||
const objNames = Search._index.objnames;
|
||||
const titles = Search._index.titles;
|
||||
|
||||
const results = [];
|
||||
|
||||
const objectSearchCallback = (prefix, match) => {
|
||||
const name = match[4]
|
||||
const fullname = (prefix ? prefix + "." : "") + name;
|
||||
const fullnameLower = fullname.toLowerCase();
|
||||
if (fullnameLower.indexOf(object) < 0) return;
|
||||
|
||||
let score = 0;
|
||||
const parts = fullnameLower.split(".");
|
||||
|
||||
// check for different match types: exact matches of full name or
|
||||
// "last name" (i.e. last dotted part)
|
||||
if (fullnameLower === object || parts.slice(-1)[0] === object)
|
||||
score += Scorer.objNameMatch;
|
||||
else if (parts.slice(-1)[0].indexOf(object) > -1)
|
||||
score += Scorer.objPartialMatch; // matches in last name
|
||||
|
||||
const objName = objNames[match[1]][2];
|
||||
const title = titles[match[0]];
|
||||
|
||||
// If more than one term searched for, we require other words to be
|
||||
// found in the name/title/description
|
||||
const otherTerms = new Set(objectTerms);
|
||||
otherTerms.delete(object);
|
||||
if (otherTerms.size > 0) {
|
||||
const haystack = `${prefix} ${name} ${objName} ${title}`.toLowerCase();
|
||||
if (
|
||||
[...otherTerms].some((otherTerm) => haystack.indexOf(otherTerm) < 0)
|
||||
)
|
||||
return;
|
||||
}
|
||||
|
||||
let anchor = match[3];
|
||||
if (anchor === "") anchor = fullname;
|
||||
else if (anchor === "-") anchor = objNames[match[1]][1] + "-" + fullname;
|
||||
|
||||
const descr = objName + _(", in ") + title;
|
||||
|
||||
// add custom score for some objects according to scorer
|
||||
if (Scorer.objPrio.hasOwnProperty(match[2]))
|
||||
score += Scorer.objPrio[match[2]];
|
||||
else score += Scorer.objPrioDefault;
|
||||
|
||||
results.push([
|
||||
docNames[match[0]],
|
||||
fullname,
|
||||
"#" + anchor,
|
||||
descr,
|
||||
score,
|
||||
filenames[match[0]],
|
||||
SearchResultKind.object,
|
||||
]);
|
||||
};
|
||||
Object.keys(objects).forEach((prefix) =>
|
||||
objects[prefix].forEach((array) =>
|
||||
objectSearchCallback(prefix, array)
|
||||
)
|
||||
);
|
||||
return results;
|
||||
},
|
||||
|
||||
/**
|
||||
* search for full-text terms in the index
|
||||
*/
|
||||
performTermsSearch: (searchTerms, excludedTerms) => {
|
||||
// prepare search
|
||||
const terms = Search._index.terms;
|
||||
const titleTerms = Search._index.titleterms;
|
||||
const filenames = Search._index.filenames;
|
||||
const docNames = Search._index.docnames;
|
||||
const titles = Search._index.titles;
|
||||
|
||||
const scoreMap = new Map();
|
||||
const fileMap = new Map();
|
||||
|
||||
// perform the search on the required terms
|
||||
searchTerms.forEach((word) => {
|
||||
const files = [];
|
||||
// find documents, if any, containing the query word in their text/title term indices
|
||||
// use Object.hasOwnProperty to avoid mismatching against prototype properties
|
||||
const arr = [
|
||||
{ files: terms.hasOwnProperty(word) ? terms[word] : undefined, score: Scorer.term },
|
||||
{ files: titleTerms.hasOwnProperty(word) ? titleTerms[word] : undefined, score: Scorer.title },
|
||||
];
|
||||
// add support for partial matches
|
||||
if (word.length > 2) {
|
||||
const escapedWord = _escapeRegExp(word);
|
||||
if (!terms.hasOwnProperty(word)) {
|
||||
Object.keys(terms).forEach((term) => {
|
||||
if (term.match(escapedWord))
|
||||
arr.push({ files: terms[term], score: Scorer.partialTerm });
|
||||
});
|
||||
}
|
||||
if (!titleTerms.hasOwnProperty(word)) {
|
||||
Object.keys(titleTerms).forEach((term) => {
|
||||
if (term.match(escapedWord))
|
||||
arr.push({ files: titleTerms[term], score: Scorer.partialTitle });
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// no match but word was a required one
|
||||
if (arr.every((record) => record.files === undefined)) return;
|
||||
|
||||
// found search word in contents
|
||||
arr.forEach((record) => {
|
||||
if (record.files === undefined) return;
|
||||
|
||||
let recordFiles = record.files;
|
||||
if (recordFiles.length === undefined) recordFiles = [recordFiles];
|
||||
files.push(...recordFiles);
|
||||
|
||||
// set score for the word in each file
|
||||
recordFiles.forEach((file) => {
|
||||
if (!scoreMap.has(file)) scoreMap.set(file, new Map());
|
||||
const fileScores = scoreMap.get(file);
|
||||
fileScores.set(word, record.score);
|
||||
});
|
||||
});
|
||||
|
||||
// create the mapping
|
||||
files.forEach((file) => {
|
||||
if (!fileMap.has(file)) fileMap.set(file, [word]);
|
||||
else if (fileMap.get(file).indexOf(word) === -1) fileMap.get(file).push(word);
|
||||
});
|
||||
});
|
||||
|
||||
// now check if the files don't contain excluded terms
|
||||
const results = [];
|
||||
for (const [file, wordList] of fileMap) {
|
||||
// check if all requirements are matched
|
||||
|
||||
// as search terms with length < 3 are discarded
|
||||
const filteredTermCount = [...searchTerms].filter(
|
||||
(term) => term.length > 2
|
||||
).length;
|
||||
if (
|
||||
wordList.length !== searchTerms.size &&
|
||||
wordList.length !== filteredTermCount
|
||||
)
|
||||
continue;
|
||||
|
||||
// ensure that none of the excluded terms is in the search result
|
||||
if (
|
||||
[...excludedTerms].some(
|
||||
(term) =>
|
||||
terms[term] === file ||
|
||||
titleTerms[term] === file ||
|
||||
(terms[term] || []).includes(file) ||
|
||||
(titleTerms[term] || []).includes(file)
|
||||
)
|
||||
)
|
||||
break;
|
||||
|
||||
// select one (max) score for the file.
|
||||
const score = Math.max(...wordList.map((w) => scoreMap.get(file).get(w)));
|
||||
// add result to the result list
|
||||
results.push([
|
||||
docNames[file],
|
||||
titles[file],
|
||||
"",
|
||||
null,
|
||||
score,
|
||||
filenames[file],
|
||||
SearchResultKind.text,
|
||||
]);
|
||||
}
|
||||
return results;
|
||||
},
|
||||
|
||||
/**
|
||||
* helper function to return a node containing the
|
||||
* search summary for a given text. keywords is a list
|
||||
* of stemmed words.
|
||||
*/
|
||||
makeSearchSummary: (htmlText, keywords, anchor) => {
|
||||
const text = Search.htmlToText(htmlText, anchor);
|
||||
if (text === "") return null;
|
||||
|
||||
const textLower = text.toLowerCase();
|
||||
const actualStartPosition = [...keywords]
|
||||
.map((k) => textLower.indexOf(k.toLowerCase()))
|
||||
.filter((i) => i > -1)
|
||||
.slice(-1)[0];
|
||||
const startWithContext = Math.max(actualStartPosition - 120, 0);
|
||||
|
||||
const top = startWithContext === 0 ? "" : "...";
|
||||
const tail = startWithContext + 240 < text.length ? "..." : "";
|
||||
|
||||
let summary = document.createElement("p");
|
||||
summary.classList.add("context");
|
||||
summary.textContent = top + text.substr(startWithContext, 240).trim() + tail;
|
||||
|
||||
return summary;
|
||||
},
|
||||
};
|
||||
|
||||
_ready(Search.init);
|
||||
|
|
@ -1,154 +0,0 @@
|
|||
/* Highlighting utilities for Sphinx HTML documentation. */
|
||||
"use strict";
|
||||
|
||||
const SPHINX_HIGHLIGHT_ENABLED = true
|
||||
|
||||
/**
|
||||
* highlight a given string on a node by wrapping it in
|
||||
* span elements with the given class name.
|
||||
*/
|
||||
const _highlight = (node, addItems, text, className) => {
|
||||
if (node.nodeType === Node.TEXT_NODE) {
|
||||
const val = node.nodeValue;
|
||||
const parent = node.parentNode;
|
||||
const pos = val.toLowerCase().indexOf(text);
|
||||
if (
|
||||
pos >= 0 &&
|
||||
!parent.classList.contains(className) &&
|
||||
!parent.classList.contains("nohighlight")
|
||||
) {
|
||||
let span;
|
||||
|
||||
const closestNode = parent.closest("body, svg, foreignObject");
|
||||
const isInSVG = closestNode && closestNode.matches("svg");
|
||||
if (isInSVG) {
|
||||
span = document.createElementNS("http://www.w3.org/2000/svg", "tspan");
|
||||
} else {
|
||||
span = document.createElement("span");
|
||||
span.classList.add(className);
|
||||
}
|
||||
|
||||
span.appendChild(document.createTextNode(val.substr(pos, text.length)));
|
||||
const rest = document.createTextNode(val.substr(pos + text.length));
|
||||
parent.insertBefore(
|
||||
span,
|
||||
parent.insertBefore(
|
||||
rest,
|
||||
node.nextSibling
|
||||
)
|
||||
);
|
||||
node.nodeValue = val.substr(0, pos);
|
||||
/* There may be more occurrences of search term in this node. So call this
|
||||
* function recursively on the remaining fragment.
|
||||
*/
|
||||
_highlight(rest, addItems, text, className);
|
||||
|
||||
if (isInSVG) {
|
||||
const rect = document.createElementNS(
|
||||
"http://www.w3.org/2000/svg",
|
||||
"rect"
|
||||
);
|
||||
const bbox = parent.getBBox();
|
||||
rect.x.baseVal.value = bbox.x;
|
||||
rect.y.baseVal.value = bbox.y;
|
||||
rect.width.baseVal.value = bbox.width;
|
||||
rect.height.baseVal.value = bbox.height;
|
||||
rect.setAttribute("class", className);
|
||||
addItems.push({ parent: parent, target: rect });
|
||||
}
|
||||
}
|
||||
} else if (node.matches && !node.matches("button, select, textarea")) {
|
||||
node.childNodes.forEach((el) => _highlight(el, addItems, text, className));
|
||||
}
|
||||
};
|
||||
const _highlightText = (thisNode, text, className) => {
|
||||
let addItems = [];
|
||||
_highlight(thisNode, addItems, text, className);
|
||||
addItems.forEach((obj) =>
|
||||
obj.parent.insertAdjacentElement("beforebegin", obj.target)
|
||||
);
|
||||
};
|
||||
|
||||
/**
|
||||
* Small JavaScript module for the documentation.
|
||||
*/
|
||||
const SphinxHighlight = {
|
||||
|
||||
/**
|
||||
* highlight the search words provided in localstorage in the text
|
||||
*/
|
||||
highlightSearchWords: () => {
|
||||
if (!SPHINX_HIGHLIGHT_ENABLED) return; // bail if no highlight
|
||||
|
||||
// get and clear terms from localstorage
|
||||
const url = new URL(window.location);
|
||||
const highlight =
|
||||
localStorage.getItem("sphinx_highlight_terms")
|
||||
|| url.searchParams.get("highlight")
|
||||
|| "";
|
||||
localStorage.removeItem("sphinx_highlight_terms")
|
||||
url.searchParams.delete("highlight");
|
||||
window.history.replaceState({}, "", url);
|
||||
|
||||
// get individual terms from highlight string
|
||||
const terms = highlight.toLowerCase().split(/\s+/).filter(x => x);
|
||||
if (terms.length === 0) return; // nothing to do
|
||||
|
||||
// There should never be more than one element matching "div.body"
|
||||
const divBody = document.querySelectorAll("div.body");
|
||||
const body = divBody.length ? divBody[0] : document.querySelector("body");
|
||||
window.setTimeout(() => {
|
||||
terms.forEach((term) => _highlightText(body, term, "highlighted"));
|
||||
}, 10);
|
||||
|
||||
const searchBox = document.getElementById("searchbox");
|
||||
if (searchBox === null) return;
|
||||
searchBox.appendChild(
|
||||
document
|
||||
.createRange()
|
||||
.createContextualFragment(
|
||||
'<p class="highlight-link">' +
|
||||
'<a href="javascript:SphinxHighlight.hideSearchWords()">' +
|
||||
_("Hide Search Matches") +
|
||||
"</a></p>"
|
||||
)
|
||||
);
|
||||
},
|
||||
|
||||
/**
|
||||
* helper function to hide the search marks again
|
||||
*/
|
||||
hideSearchWords: () => {
|
||||
document
|
||||
.querySelectorAll("#searchbox .highlight-link")
|
||||
.forEach((el) => el.remove());
|
||||
document
|
||||
.querySelectorAll("span.highlighted")
|
||||
.forEach((el) => el.classList.remove("highlighted"));
|
||||
localStorage.removeItem("sphinx_highlight_terms")
|
||||
},
|
||||
|
||||
initEscapeListener: () => {
|
||||
// only install a listener if it is really needed
|
||||
if (!DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS) return;
|
||||
|
||||
document.addEventListener("keydown", (event) => {
|
||||
// bail for input elements
|
||||
if (BLACKLISTED_KEY_CONTROL_ELEMENTS.has(document.activeElement.tagName)) return;
|
||||
// bail with special keys
|
||||
if (event.shiftKey || event.altKey || event.ctrlKey || event.metaKey) return;
|
||||
if (DOCUMENTATION_OPTIONS.ENABLE_SEARCH_SHORTCUTS && (event.key === "Escape")) {
|
||||
SphinxHighlight.hideSearchWords();
|
||||
event.preventDefault();
|
||||
}
|
||||
});
|
||||
},
|
||||
};
|
||||
|
||||
_ready(() => {
|
||||
/* Do not call highlightSearchWords() when we are on the search page.
|
||||
* It will highlight words from the *previous* search query.
|
||||
*/
|
||||
if (typeof Search === "undefined") SphinxHighlight.highlightSearchWords();
|
||||
SphinxHighlight.initEscapeListener();
|
||||
});
|
||||
|
|
@ -1,140 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>附录 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="gen api html & pdf by sphinx" href="gen_api.html" />
|
||||
<link rel="prev" title="netrans_py 使用" href="netrans_py.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="id1">
|
||||
<h1>附录<a class="headerlink" href="#id1" title="Link to this heading">¶</a></h1>
|
||||
<div class="toctree-wrapper compound">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html#rst">*.rst</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html#autodoc-sphinx-python-api-html">使用 autodoc + Sphinx 实现 python api 文档(html)</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html#autodoc-sphinx-python-api-pdf">使用 autodoc + Sphinx 实现 python api 文档(pdf)</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html#id1">常见报错</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="modules.html">netrans_py</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans.html">netrans module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="config.html">config module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="dump.html">dump module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="example.html">example module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="export.html">export module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="file_model.html">file_model module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html">import_model module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="infer.html">infer module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quantize.html">quantize module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quantize_hb.html">quantize_hb module</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html">utils module</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">附录</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li>Previous: <a href="netrans_py.html" title="上一章">netrans_py 使用</a></li>
|
||||
<li>Next: <a href="gen_api.html" title="下一章">gen api html & pdf by sphinx</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/appendix.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,136 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>config module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="dump module" href="dump.html" />
|
||||
<link rel="prev" title="netrans module" href="netrans.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-config">
|
||||
<span id="config-module"></span><h1>config module<a class="headerlink" href="#module-config" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="config.Config">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">config.</span></span><span class="sig-name descname"><span class="pre">Config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/config.html#Config"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#config.Config" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<p>从实例化的 Netrans 中解析模型参数,并基于pnnacc 生成配置文件模板</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>Netrans</strong> (<em>class</em>) -- 实例化的Netrans类,包含 模型信息 和 Netrans 信息</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="config.Config.inputmeta_gen">
|
||||
<span class="sig-name descname"><span class="pre">inputmeta_gen</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#config.Config.inputmeta_gen" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="netrans.html" title="上一章">netrans module</a></li>
|
||||
<li>Next: <a href="dump.html" title="下一章">dump module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/config.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,119 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>dump module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="example module" href="example.html" />
|
||||
<link rel="prev" title="config module" href="config.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="dump-module">
|
||||
<h1>dump module<a class="headerlink" href="#dump-module" title="Link to this heading">¶</a></h1>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="config.html" title="上一章">config module</a></li>
|
||||
<li>Next: <a href="example.html" title="下一章">example module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/dump.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,124 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>example module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="export module" href="export.html" />
|
||||
<link rel="prev" title="dump module" href="dump.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-example">
|
||||
<span id="example-module"></span><h1>example module<a class="headerlink" href="#module-example" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="example.main">
|
||||
<span class="sig-prename descclassname"><span class="pre">example.</span></span><span class="sig-name descname"><span class="pre">main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/example.html#main"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#example.main" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="dump.html" title="上一章">dump module</a></li>
|
||||
<li>Next: <a href="export.html" title="下一章">export module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/example.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,141 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>export module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="file_model module" href="file_model.html" />
|
||||
<link rel="prev" title="example module" href="example.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-export">
|
||||
<span id="export-module"></span><h1>export module<a class="headerlink" href="#module-export" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="export.Export">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">export.</span></span><span class="sig-name descname"><span class="pre">Export</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/export.html#Export"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#export.Export" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<p>从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导出模型ngb文件</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>Netrans</strong> (<em>class</em>) -- 实例化的Netrans类,包含 模型信息 和 Netrans 信息</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="export.Export.export_network">
|
||||
<span class="sig-name descname"><span class="pre">export_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#export.Export.export_network" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="export.main">
|
||||
<span class="sig-prename descclassname"><span class="pre">export.</span></span><span class="sig-name descname"><span class="pre">main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/export.html#main"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#export.main" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="example.html" title="上一章">example module</a></li>
|
||||
<li>Next: <a href="file_model.html" title="下一章">file_model module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/export.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,119 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>file_model module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="import_model module" href="import_model.html" />
|
||||
<link rel="prev" title="export module" href="export.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-file_model">
|
||||
<span id="file-model-module"></span><h1>file_model module<a class="headerlink" href="#module-file_model" title="Link to this heading">¶</a></h1>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="export.html" title="上一章">export module</a></li>
|
||||
<li>Next: <a href="import_model.html" title="下一章">import_model module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/file_model.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,249 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>gen api html & pdf by sphinx — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="netrans_py" href="modules.html" />
|
||||
<link rel="prev" title="附录" href="appendix.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="gen-api-html-pdf-by-sphinx">
|
||||
<h1>gen api html & pdf by sphinx<a class="headerlink" href="#gen-api-html-pdf-by-sphinx" title="Link to this heading">¶</a></h1>
|
||||
<p>netrans 目录结构如下</p>
|
||||
<div class="highlight-tree notranslate"><div class="highlight"><pre><span></span>netrans/
|
||||
│
|
||||
├── docs/ # Sphinx 项目的根目录
|
||||
│ ├── source/ # 源文件目录
|
||||
│ │ ├── _static/ # 静态文件（如图片、CSS、JS）
|
||||
│ │ ├── _templates/ # 自定义模板
|
||||
│ │ ├── conf.py # 配置文件
|
||||
│ │ ├── index.rst # 主页文件
|
||||
│ │ └── my_module.rst # 其他文档文件
|
||||
│ └── build/ # 构建输出目录（生成的 HTML 文件等）
|
||||
│
|
||||
└── bin/
|
||||
└── netrans_cli/
|
||||
└── netrans_py/
|
||||
</pre></div>
|
||||
</div>
|
||||
<ol class="simple">
|
||||
<li><p><code class="docutils literal notranslate"><span class="pre">sphinx-quickstart</span> <span class="pre">docs/</span></code> 快速生成</p></li>
|
||||
<li><p>修改 <code class="docutils literal notranslate"><span class="pre">docs/source/conf.py</span></code> ,</p></li>
|
||||
</ol>
|
||||
<section id="rst">
|
||||
<h2>*.rst<a class="headerlink" href="#rst" title="Link to this heading">¶</a></h2>
|
||||
<p>rst, reStructuredText 文件，用于定义文档的结构。通常放在source目录下。</p>
|
||||
<p>rst 是一种和 markdown 类似的语法</p>
|
||||
<p>使用目录树指令 <code class="docutils literal notranslate"><span class="pre">..</span> <span class="pre">toctree::</span></code>，列出其他文档文件。</p>
|
||||
</section>
|
||||
<section id="autodoc-sphinx-python-api-html">
|
||||
<h2>使用 autodoc + Sphinx 实现 python api 文档(html)<a class="headerlink" href="#autodoc-sphinx-python-api-html" title="Link to this heading">¶</a></h2>
|
||||
<ol class="simple">
|
||||
<li><p>修改 docs/source/conf.py</p></li>
|
||||
</ol>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="c1"># Configuration file for the Sphinx documentation builder.</span>
|
||||
<span class="c1">#</span>
|
||||
<span class="c1"># For the full list of built-in configuration values, see the documentation:</span>
|
||||
<span class="c1"># https://www.sphinx-doc.org/en/master/usage/configuration.html</span>
|
||||
|
||||
<span class="c1"># -- Project information -----------------------------------------------------</span>
|
||||
<span class="c1"># https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information</span>
|
||||
|
||||
<span class="n">project</span> <span class="o">=</span> <span class="s1">'netrans'</span>
|
||||
<span class="n">copyright</span> <span class="o">=</span> <span class="s1">'2025, ccyh'</span>
|
||||
<span class="n">author</span> <span class="o">=</span> <span class="s1">'xj'</span>
|
||||
<span class="n">release</span> <span class="o">=</span> <span class="s1">'0.1'</span>
|
||||
|
||||
<span class="c1"># -- General configuration ---------------------------------------------------</span>
|
||||
<span class="c1"># https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration</span>
|
||||
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">os</span>
|
||||
<span class="kn">import</span><span class="w"> </span><span class="nn">sys</span>
|
||||
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">'../../netrans_py/'</span><span class="p">)</span>
|
||||
<span class="n">sys</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">'../../'</span><span class="p">)</span>
|
||||
|
||||
<span class="c1"># Sphinx 扩展</span>
|
||||
<span class="n">extensions</span> <span class="o">=</span> <span class="p">[</span>
|
||||
<span class="s1">'sphinx.ext.autodoc'</span><span class="p">,</span> <span class="c1"># 自动生成文档</span>
|
||||
<span class="s1">'sphinx.ext.viewcode'</span><span class="p">,</span> <span class="c1"># 添加源代码链接</span>
|
||||
<span class="s1">'sphinx.ext.napoleon'</span><span class="p">,</span> <span class="c1"># 支持 NumPy 和 Google 风格的 docstring</span>
|
||||
<span class="p">]</span>
|
||||
|
||||
<span class="c1"># 主题</span>
|
||||
<span class="n">html_theme</span> <span class="o">=</span> <span class="s1">'sphinx_rtd_theme'</span>
|
||||
|
||||
<span class="n">templates_path</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'_templates'</span><span class="p">]</span>
|
||||
<span class="n">exclude_patterns</span> <span class="o">=</span> <span class="p">[]</span>
|
||||
|
||||
<span class="n">language</span> <span class="o">=</span> <span class="s1">'zh'</span>
|
||||
|
||||
<span class="c1"># -- Options for HTML output -------------------------------------------------</span>
|
||||
<span class="c1"># https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output</span>
|
||||
|
||||
<span class="n">html_theme</span> <span class="o">=</span> <span class="s1">'alabaster'</span>
|
||||
<span class="n">html_static_path</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'_static'</span><span class="p">]</span>
|
||||
|
||||
<span class="n">source_suffix</span> <span class="o">=</span> <span class="p">{</span>
|
||||
<span class="s1">'.rst'</span><span class="p">:</span> <span class="s1">'restructuredtext'</span><span class="p">,</span>
|
||||
<span class="s1">'.md'</span><span class="p">:</span> <span class="s1">'markdown'</span><span class="p">,</span>
|
||||
<span class="p">}</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<ol class="simple">
|
||||
<li><p>sphinx-apidoc -o docs/source/ .
|
||||
生成 netrans_py 下所有的 *.py 的rst, 并添加到index.rst里.</p></li>
|
||||
</ol>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span># index.rst
|
||||
</pre></div>
|
||||
</div>
|
||||
<ol class="simple">
|
||||
<li><p>sphinx-build -b html docs/source docs/build</p></li>
|
||||
</ol>
|
||||
</section>
|
||||
<section id="autodoc-sphinx-python-api-pdf">
|
||||
<h2>使用 autodoc + Sphinx 实现 python api 文档(pdf)<a class="headerlink" href="#autodoc-sphinx-python-api-pdf" title="Link to this heading">¶</a></h2>
|
||||
<ol class="simple">
|
||||
<li><p>在可以生成 html的 基础上, 使用make latexodf 生成 *.tex文件.
|
||||
这一步会报错,原因是无法识别中文</p></li>
|
||||
</ol>
|
||||
<p>2.修改 netrans.tex文件</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">cd</span> <span class="n">build</span><span class="o">/</span><span class="n">latex</span>
|
||||
<span class="n">vim</span> <span class="n">netrans</span><span class="o">.</span><span class="n">tex</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>在各种usapackage的地方新增:</p>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span>\<span class="n">usepackage</span><span class="p">[</span><span class="n">UTF8</span><span class="p">,</span> <span class="n">fontset</span><span class="o">=</span><span class="n">ubuntu</span><span class="p">]{</span><span class="n">ctex</span><span class="p">}</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<ol class="simple">
|
||||
<li><p>使用 xelatex 生成pdf
|
||||
sphinx使用的是 xelatex 而非 pdflatex</p></li>
|
||||
</ol>
|
||||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">xelatex</span> <span class="n">netrans</span><span class="o">.</span><span class="n">tex</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="id1">
|
||||
<h2>常见报错<a class="headerlink" href="#id1" title="Link to this heading">¶</a></h2>
|
||||
<p>报错</p>
|
||||
<div class="highlight-log notranslate"><div class="highlight"><pre><span></span>sphinx-quickstart
|
||||
Traceback (most recent call last):
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/bin/sphinx-quickstart", line 8, in <module>
|
||||
sys.exit(main())
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/lib/python3.10/site-packages/sphinx/cmd/quickstart.py", line 721, in main
|
||||
locale.setlocale(locale.LC_ALL, '')
|
||||
File "/home/xj/app/miniforge3/envs/sphinx/lib/python3.10/locale.py", line 620, in setlocale
|
||||
return _setlocale(category, locale)
|
||||
locale.Error: unsupported locale setting
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>解决:
|
||||
export LC_ALL=en_US.UTF-8</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li>Previous: <a href="appendix.html" title="上一章">附录</a></li>
|
||||
<li>Next: <a href="modules.html" title="下一章">netrans_py</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/gen_api.md.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,341 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>索引 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="#" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
|
||||
<h1 id="index">索引</h1>
|
||||
|
||||
<div class="genindex-jumpbox">
|
||||
<a href="#A"><strong>A</strong></a>
|
||||
| <a href="#C"><strong>C</strong></a>
|
||||
| <a href="#E"><strong>E</strong></a>
|
||||
| <a href="#F"><strong>F</strong></a>
|
||||
| <a href="#I"><strong>I</strong></a>
|
||||
| <a href="#M"><strong>M</strong></a>
|
||||
| <a href="#N"><strong>N</strong></a>
|
||||
| <a href="#Q"><strong>Q</strong></a>
|
||||
| <a href="#R"><strong>R</strong></a>
|
||||
| <a href="#U"><strong>U</strong></a>
|
||||
|
||||
</div>
|
||||
<h2 id="A">A</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="utils.html#utils.AttributeCopier">AttributeCopier（utils 中的类）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="C">C</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="utils.html#utils.check_dir">check_dir()（在 utils 模块中）</a>
|
||||
</li>
|
||||
<li><a href="utils.html#utils.check_env">check_env()（在 utils 模块中）</a>
|
||||
</li>
|
||||
<li><a href="utils.html#utils.check_netrans">check_netrans()（在 utils 模块中）</a>
|
||||
</li>
|
||||
<li><a href="utils.html#utils.check_path">check_path()（在 utils 模块中）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.check_status">check_status()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
config
|
||||
|
||||
<ul>
|
||||
<li><a href="config.html#module-config">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="config.html#config.Config">Config（config 中的类）</a>
|
||||
</li>
|
||||
<li><a href="utils.html#utils.AttributeCopier.copy_attribute_name">copy_attribute_name() （utils.AttributeCopier 方法）</a>
|
||||
</li>
|
||||
<li><a href="utils.html#utils.create_cls">create_cls（utils 中的类）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="E">E</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
example
|
||||
|
||||
<ul>
|
||||
<li><a href="example.html#module-example">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
export
|
||||
|
||||
<ul>
|
||||
<li><a href="export.html#module-export">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="export.html#export.Export.export_network">export_network() （export.Export 方法）</a>
|
||||
</li>
|
||||
<li><a href="export.html#export.Export">Export（export 中的类）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="F">F</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
file_model
|
||||
|
||||
<ul>
|
||||
<li><a href="file_model.html#module-file_model">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="I">I</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="import_model.html#import_model.import_caffe_network">import_caffe_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.import_darknet_network">import_darknet_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
<li>
|
||||
import_model
|
||||
|
||||
<ul>
|
||||
<li><a href="import_model.html#module-import_model">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="import_model.html#import_model.ImportModel.import_network">import_network() （import_model.ImportModel 方法）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.import_onnx_network">import_onnx_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.import_pytorch_network">import_pytorch_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="import_model.html#import_model.import_tensorflow_network">import_tensorflow_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.import_tflite_network">import_tflite_network()（在 import_model 模块中）</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#import_model.ImportModel">ImportModel（import_model 中的类）</a>
|
||||
</li>
|
||||
<li>
|
||||
infer
|
||||
|
||||
<ul>
|
||||
<li><a href="infer.html#module-infer">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li><a href="infer.html#infer.Infer.inference_network">inference_network() （infer.Infer 方法）</a>
|
||||
</li>
|
||||
<li><a href="infer.html#infer.Infer">Infer（infer 中的类）</a>
|
||||
</li>
|
||||
<li><a href="config.html#config.Config.inputmeta_gen">inputmeta_gen() （config.Config 方法）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="M">M</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="example.html#example.main">main()（在 example 模块中）</a>
|
||||
</li>
|
||||
<li><a href="export.html#export.main">main()（在 export 模块中）</a>
|
||||
</li>
|
||||
<li><a href="infer.html#infer.main">main()（在 infer 模块中）</a>
|
||||
</li>
|
||||
<li><a href="quantize_hb.html#quantize_hb.main">main()（在 quantize_hb 模块中）</a>
|
||||
</li>
|
||||
<li>
|
||||
module
|
||||
|
||||
<ul>
|
||||
<li><a href="config.html#module-config">config</a>
|
||||
</li>
|
||||
<li><a href="example.html#module-example">example</a>
|
||||
</li>
|
||||
<li><a href="export.html#module-export">export</a>
|
||||
</li>
|
||||
<li><a href="file_model.html#module-file_model">file_model</a>
|
||||
</li>
|
||||
<li><a href="import_model.html#module-import_model">import_model</a>
|
||||
</li>
|
||||
<li><a href="infer.html#module-infer">infer</a>
|
||||
</li>
|
||||
<li><a href="netrans.html#module-netrans">netrans</a>
|
||||
</li>
|
||||
<li><a href="quantize.html#module-quantize">quantize</a>
|
||||
</li>
|
||||
<li><a href="quantize_hb.html#module-quantize_hb">quantize_hb</a>
|
||||
</li>
|
||||
<li><a href="utils.html#module-utils">utils</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="N">N</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
netrans
|
||||
|
||||
<ul>
|
||||
<li><a href="netrans.html#module-netrans">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="Q">Q</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
quantize
|
||||
|
||||
<ul>
|
||||
<li><a href="quantize.html#module-quantize">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
<li>
|
||||
quantize_hb
|
||||
|
||||
<ul>
|
||||
<li><a href="quantize_hb.html#module-quantize_hb">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="quantize.html#quantize.Quantize.quantize_network">quantize_network() （quantize.Quantize 方法）</a>
|
||||
</li>
|
||||
<li><a href="quantize_hb.html#quantize_hb.Quantize.quantize_network">quantize_network() （quantize_hb.Quantize 方法）</a>
|
||||
</li>
|
||||
<li><a href="quantize.html#quantize.Quantize">Quantize（quantize 中的类）</a>
|
||||
</li>
|
||||
<li><a href="quantize_hb.html#quantize_hb.Quantize">Quantize（quantize_hb 中的类）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="R">R</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li><a href="utils.html#utils.remove_history_file">remove_history_file()（在 utils 模块中）</a>
|
||||
</li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
<h2 id="U">U</h2>
|
||||
<table style="width: 100%" class="indextable genindextable"><tr>
|
||||
<td style="width: 33%; vertical-align: top;"><ul>
|
||||
<li>
|
||||
utils
|
||||
|
||||
<ul>
|
||||
<li><a href="utils.html#module-utils">module</a>
|
||||
</li>
|
||||
</ul></li>
|
||||
</ul></td>
|
||||
</tr></table>
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,267 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>import_model module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="infer module" href="infer.html" />
|
||||
<link rel="prev" title="file_model module" href="file_model.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-import_model">
|
||||
<span id="import-model-module"></span><h1>import_model module<a class="headerlink" href="#module-import_model" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="import_model.ImportModel">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">ImportModel</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#ImportModel"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.ImportModel" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<p>从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导入模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>Netrans</strong> (<em>class</em>) -- 实例化的Netrans类,包含 模型信息 和 Netrans 信息</p>
|
||||
</dd>
|
||||
</dl>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="import_model.ImportModel.import_network">
|
||||
<span class="sig-name descname"><span class="pre">import_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#import_model.ImportModel.import_network" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.check_status">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">check_status</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">result</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#check_status"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.check_status" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>解析命令执行情况</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>result</strong> (<em>return</em><em> of </em><em>subprocrss.run</em>) -- subprocess.run的返回值</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_caffe_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_caffe_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_caffe_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_caffe_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 caffe 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_darknet_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_darknet_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_darknet_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_darknet_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 darknet 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_onnx_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_onnx_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_onnx_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_onnx_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 onnx 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_pytorch_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_pytorch_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_pytorch_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_pytorch_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 pytorch 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_tensorflow_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_tensorflow_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_tensorflow_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_tensorflow_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 tensorflow 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="import_model.import_tflite_network">
|
||||
<span class="sig-prename descclassname"><span class="pre">import_model.</span></span><span class="sig-name descname"><span class="pre">import_tflite_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/import_model.html#import_tflite_network"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#import_model.import_tflite_network" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>导入 tflite 模型</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><ul class="simple">
|
||||
<li><p><strong>name</strong> (<em>str</em>) -- 模型名字</p></li>
|
||||
<li><p><strong>netrans_path</strong> (<em>str</em>) -- 模型路径</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt class="field-even">返回<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p>生成的pnnacc 命令行, 被subprocesses执行</p>
|
||||
</dd>
|
||||
<dt class="field-odd">返回类型<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p>cmd (str)</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="file_model.html" title="上一章">file_model module</a></li>
|
||||
<li>Next: <a href="infer.html" title="下一章">infer module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/import_model.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,145 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>netrans documentation — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="快速入门" href="quick_start_guide.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="netrans-documentation">
|
||||
<h1>netrans documentation<a class="headerlink" href="#netrans-documentation" title="Link to this heading">¶</a></h1>
|
||||
<p>netrans 是一套针对pnna 芯片的模型处理工具，提供命令行工具 netrans_cli 和 python api netrans_py， 其核心功能是将模型权重转换成在pnna芯片上运行的 nbg（network binary graph）格式（.nb 为后缀）。</p>
|
||||
<div class="toctree-wrapper compound">
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quick_start_guide.html#id2">系统环境</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quick_start_guide.html#netrans">安装Netrans</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quick_start_guide.html#netrans-yolov5s">使用 Netrans 编译 yolov5s 模型</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#id1">netrans_cli 脚本</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#load-sh">load.sh 模型导入</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#config-sh">config.sh 预处理配置文件生成</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#quantize-sh">quantize.sh 模型量化</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#export-sh">export.sh 模型导出</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_cli.html#id2">使用示例</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans">Netrans 类</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans-import">Netrans.import 模型导入</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans-config">Netrans.config 预处理配置文件生成</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans-quantize">Netrans.quantize 模型量化</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans-export">Netrans.export 模型导出</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#netrans-model2nbg-nbg">Netrans.model2nbg 模型生成nbg文件</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="netrans_py.html#id1">使用示例</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="#">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="#">Documentation overview</a><ul>
|
||||
<li>Next: <a href="quick_start_guide.html" title="下一章">快速入门</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/index.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,135 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>infer module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="quantize module" href="quantize.html" />
|
||||
<link rel="prev" title="import_model module" href="import_model.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-infer">
|
||||
<span id="infer-module"></span><h1>infer module<a class="headerlink" href="#module-infer" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="infer.Infer">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">infer.</span></span><span class="sig-name descname"><span class="pre">Infer</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/infer.html#Infer"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#infer.Infer" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="infer.Infer.inference_network">
|
||||
<span class="sig-name descname"><span class="pre">inference_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#infer.Infer.inference_network" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="infer.main">
|
||||
<span class="sig-prename descclassname"><span class="pre">infer.</span></span><span class="sig-name descname"><span class="pre">main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/infer.html#main"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#infer.main" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="import_model.html" title="上一章">import_model module</a></li>
|
||||
<li>Next: <a href="quantize.html" title="下一章">quantize module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/infer.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,193 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>netrans_py — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="netrans module" href="netrans.html" />
|
||||
<link rel="prev" title="gen api html & pdf by sphinx" href="gen_api.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="netrans-py">
|
||||
<h1>netrans_py<a class="headerlink" href="#netrans-py" title="Link to this heading">¶</a></h1>
|
||||
<div class="toctree-wrapper compound">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans.html">netrans module</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="config.html">config module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="config.html#config.Config"><code class="docutils literal notranslate"><span class="pre">Config</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="config.html#config.Config.inputmeta_gen"><code class="docutils literal notranslate"><span class="pre">Config.inputmeta_gen()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="dump.html">dump module</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="example.html">example module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="example.html#example.main"><code class="docutils literal notranslate"><span class="pre">main()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="export.html">export module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="export.html#export.Export"><code class="docutils literal notranslate"><span class="pre">Export</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="export.html#export.Export.export_network"><code class="docutils literal notranslate"><span class="pre">Export.export_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="export.html#export.main"><code class="docutils literal notranslate"><span class="pre">main()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="file_model.html">file_model module</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="import_model.html">import_model module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.ImportModel"><code class="docutils literal notranslate"><span class="pre">ImportModel</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="import_model.html#import_model.ImportModel.import_network"><code class="docutils literal notranslate"><span class="pre">ImportModel.import_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.check_status"><code class="docutils literal notranslate"><span class="pre">check_status()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_caffe_network"><code class="docutils literal notranslate"><span class="pre">import_caffe_network()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_darknet_network"><code class="docutils literal notranslate"><span class="pre">import_darknet_network()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_onnx_network"><code class="docutils literal notranslate"><span class="pre">import_onnx_network()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_pytorch_network"><code class="docutils literal notranslate"><span class="pre">import_pytorch_network()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_tensorflow_network"><code class="docutils literal notranslate"><span class="pre">import_tensorflow_network()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="import_model.html#import_model.import_tflite_network"><code class="docutils literal notranslate"><span class="pre">import_tflite_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="infer.html">infer module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="infer.html#infer.Infer"><code class="docutils literal notranslate"><span class="pre">Infer</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="infer.html#infer.Infer.inference_network"><code class="docutils literal notranslate"><span class="pre">Infer.inference_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="infer.html#infer.main"><code class="docutils literal notranslate"><span class="pre">main()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quantize.html">quantize module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quantize.html#quantize.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quantize.html#quantize.Quantize.quantize_network"><code class="docutils literal notranslate"><span class="pre">Quantize.quantize_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quantize_hb.html">quantize_hb module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quantize_hb.html#quantize_hb.Quantize"><code class="docutils literal notranslate"><span class="pre">Quantize</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="quantize_hb.html#quantize_hb.Quantize.quantize_network"><code class="docutils literal notranslate"><span class="pre">Quantize.quantize_network()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="quantize_hb.html#quantize_hb.main"><code class="docutils literal notranslate"><span class="pre">main()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="utils.html">utils module</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.AttributeCopier"><code class="docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a><ul>
|
||||
<li class="toctree-l3"><a class="reference internal" href="utils.html#utils.AttributeCopier.copy_attribute_name"><code class="docutils literal notranslate"><span class="pre">AttributeCopier.copy_attribute_name()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.check_dir"><code class="docutils literal notranslate"><span class="pre">check_dir()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.check_env"><code class="docutils literal notranslate"><span class="pre">check_env()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.check_netrans"><code class="docutils literal notranslate"><span class="pre">check_netrans()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.check_path"><code class="docutils literal notranslate"><span class="pre">check_path()</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.create_cls"><code class="docutils literal notranslate"><span class="pre">create_cls</span></code></a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="utils.html#utils.remove_history_file"><code class="docutils literal notranslate"><span class="pre">remove_history_file()</span></code></a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li>Previous: <a href="gen_api.html" title="上一章">gen api html & pdf by sphinx</a></li>
|
||||
<li>Next: <a href="netrans.html" title="下一章">netrans module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/modules.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,119 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>netrans module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="config module" href="config.html" />
|
||||
<link rel="prev" title="netrans_py" href="modules.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-netrans">
|
||||
<span id="netrans-module"></span><h1>netrans module<a class="headerlink" href="#module-netrans" title="Link to this heading">¶</a></h1>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="modules.html" title="上一章">netrans_py</a></li>
|
||||
<li>Next: <a href="config.html" title="下一章">config module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/netrans.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,318 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>netrans_cli 使用 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="netrans_py 使用" href="netrans_py.html" />
|
||||
<link rel="prev" title="快速入门" href="quick_start_guide.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="netrans-cli">
|
||||
<h1>netrans_cli 使用<a class="headerlink" href="#netrans-cli" title="Link to this heading">¶</a></h1>
|
||||
<p>netrans_cli 是 netrans 进行模型转换的命令行工具，使用 ntrans_cli 完成模型转换的步骤如下：</p>
|
||||
<ol class="simple">
|
||||
<li><p>导入模型</p></li>
|
||||
<li><p>生成并修改前处理配置文件 *_inputmeta.yml</p></li>
|
||||
<li><p>量化模型</p></li>
|
||||
<li><p>导出模型</p></li>
|
||||
</ol>
|
||||
<section id="id1">
|
||||
<h2>netrans_cli 脚本<a class="headerlink" href="#id1" title="Link to this heading">¶</a></h2>
|
||||
<table border="1" class="docutils">
|
||||
<thead>
|
||||
<tr>
|
||||
<th style="text-align: left;">脚本</th>
|
||||
<th>功能</th>
|
||||
<th>使用</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style="text-align: left;">load.sh</td>
|
||||
<td>模型导入功能，将模型转换成 Pnna 支持的格式</td>
|
||||
<td>load.sh model_name</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style="text-align: left;">config.sh</td>
|
||||
<td>预处理模版生成功能，生成预处理模版，根据模型进行对于的修改</td>
|
||||
<td>config.sh model_name</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style="text-align: left;">quantize.sh</td>
|
||||
<td>量化功能， 对模型进行量化生成量化参数文件</td>
|
||||
<td>quantize.sh model_name quantize_data_type</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style="text-align: left;">export.sh</td>
|
||||
<td>导出功能，将量化好的模型导出成 Pnna 上可以运行的runtime</td>
|
||||
<td>export.sh model_name quantize_data_type</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table><p><font color="#dd0000">对于不同框架下训练的模型，需要准备不同的数据，所有的数据都需要与模型放在同一个文件夹下，模型文件名和文件夹名需要保持一致。</font></p>
|
||||
</section>
|
||||
<section id="load-sh">
|
||||
<h2>load.sh 模型导入<a class="headerlink" href="#load-sh" title="Link to this heading">¶</a></h2>
|
||||
<p>使用 load.sh 导入模型</p>
|
||||
<ul>
|
||||
<li><p>用法： load.sh 以模型文件名命名的模型数据文件夹，例如：</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>load.sh<span class="w"> </span>lenet
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>"lenet"是文件夹名，也作为模型名和权重文件名。导入会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有"lenet.json"和"lenet.data"文件:</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>$<span class="w"> </span>ls<span class="w"> </span>-lrt<span class="w"> </span>lenet
|
||||
total<span class="w"> </span><span class="m">3396</span>
|
||||
-rwxr-xr-x<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">1727201</span><span class="w"> </span>Nov<span class="w"> </span><span class="m">5</span><span class="w"> </span><span class="m">2018</span><span class="w"> </span>lenet.pb
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">553</span><span class="w"> </span>Nov<span class="w"> </span><span class="m">5</span><span class="w"> </span><span class="m">2018</span><span class="w"> </span><span class="m">0</span>.jpg
|
||||
-rwxr--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">6</span><span class="w"> </span>Apr<span class="w"> </span><span class="m">21</span><span class="w"> </span><span class="m">17</span>:04<span class="w"> </span>dataset.txt
|
||||
-rw-rw-r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">69</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:19<span class="w"> </span>inputs_outputs.txt
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">5553</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:21<span class="w"> </span>lenet.json
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">1725178</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:21<span class="w"> </span>lenet.data
|
||||
</pre></div>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="config-sh">
|
||||
<h2>config.sh 预处理配置文件生成<a class="headerlink" href="#config-sh" title="Link to this heading">¶</a></h2>
|
||||
<p>使用 config.sh 生成 inputmeta 文件</p>
|
||||
<ul>
|
||||
<li><p>config.sh 以模型文件名命名的模型数据文件夹，例如：</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>config.sh<span class="w"> </span>lenet
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>inputmeta 文件生成会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有 "lenet_inputmeta.yml" 文件:</p>
|
||||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span><span class="w"> </span>$<span class="w"> </span>ls<span class="w"> </span>-lrt<span class="w"> </span>lenet
|
||||
total<span class="w"> </span><span class="m">3400</span>
|
||||
-rwxr-xr-x<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">1727201</span><span class="w"> </span>Nov<span class="w"> </span><span class="m">5</span><span class="w"> </span><span class="m">2018</span><span class="w"> </span>lenet.pb
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">553</span><span class="w"> </span>Nov<span class="w"> </span><span class="m">5</span><span class="w"> </span><span class="m">2018</span><span class="w"> </span><span class="m">0</span>.jpg
|
||||
-rwxr--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">6</span><span class="w"> </span>Apr<span class="w"> </span><span class="m">21</span><span class="w"> </span><span class="m">17</span>:04<span class="w"> </span>dataset.txt
|
||||
-rw-rw-r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">69</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:19<span class="w"> </span>inputs_outputs.txt
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">5553</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:21<span class="w"> </span>lenet.json
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">1725178</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:21<span class="w"> </span>lenet.data
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">948</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:35<span class="w"> </span>lenet_inputmeta.yml
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>可以看到，最终生成的是*.yml文件，该文件用于为Netrans中间模型配置输入层数据集合。<b>Netrans中的量化、推理、导出和图片转dat的操作都需要用到这个文件。因此，此步骤不可跳过。</b></p>
|
||||
</li>
|
||||
</ul>
|
||||
<p>Inputmeta.yml文件结构如下：</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="nt">%YAML</span><span class="w"> </span><span class="m">1.2</span>
|
||||
<span class="nn">---</span>
|
||||
<span class="c1"># !!!This file disallow TABs!!!</span>
|
||||
<span class="c1"># "category" allowed values: "image, undefined"</span>
|
||||
<span class="c1"># "database" allowed types: "H5FS, SQLITE, TEXT, LMDB, NPY, GENERATOR"</span>
|
||||
<span class="c1"># "tensor_name" only support in H5FS database</span>
|
||||
<span class="c1"># "preproc_type" allowed types:"IMAGE_RGB, IMAGE_RGB888_PLANAR, IMAGE_RGB888_PLANAR_SEP, </span>
|
||||
<span class="l l-Scalar l-Scalar-Plain">IMAGE_I420,</span><span class="w"> </span>
|
||||
<span class="l l-Scalar l-Scalar-Plain"># IMAGE_NV12, IMAGE_YUV444, IMAGE_GRAY, IMAGE_BGRA, TENSOR"</span>
|
||||
<span class="l l-Scalar l-Scalar-Plain">input_meta</span><span class="p p-Indicator">:</span>
|
||||
<span class="w"> </span><span class="nt">databases</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">dataset.txt</span>
|
||||
<span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">TEXT</span>
|
||||
<span class="w"> </span><span class="nt">ports</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">lid</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">data_0</span>
|
||||
<span class="w"> </span><span class="nt">category</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">image</span>
|
||||
<span class="w"> </span><span class="nt">dtype</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">float32</span>
|
||||
<span class="w"> </span><span class="nt">sparse</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<span class="w"> </span><span class="nt">tensor_name</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="nt">layout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">nhwc</span>
|
||||
<span class="w"> </span><span class="nt">shape</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">50</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">224</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">224</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span>
|
||||
<span class="w"> </span><span class="nt">preprocess</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="nt">reverse_channel</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<span class="w"> </span><span class="nt">mean</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">103.94</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">116.78</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">123.67</span>
|
||||
<span class="w"> </span><span class="nt">scale</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.017</span>
|
||||
<span class="w"> </span><span class="nt">preproc_node_params</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="nt">preproc_type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">IMAGE_RGB</span>
|
||||
<span class="w"> </span><span class="nt">add_preproc_node</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
<span class="w"> </span><span class="nt">preproc_perm</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">1</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">2</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">3</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">lid</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">label_0</span>
|
||||
<span class="w"> </span><span class="nt">redirect_to_output</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
<span class="w"> </span><span class="nt">category</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">undefined</span>
|
||||
<span class="w"> </span><span class="nt">tensor_name</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="nt">dtype</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">float32</span>
|
||||
<span class="w"> </span><span class="nt">shape</span><span class="p">:</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">1</span>
|
||||
<span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">1</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>上面示例文件的各个参数解释：</p>
|
||||
<div class="highlight-{table} notranslate"><div class="highlight"><pre><span></span>:widths: 20, 80
|
||||
:align: left
|
||||
| 参数 | 说明 |
|
||||
| :--- | --- |
|
||||
| input_meta | 预处理参数配置申明。 |
|
||||
| databases | 数据配置，包括设置 path、type 和 ports 。|
|
||||
| path | 数据集文件的相对（执行目录）或绝对路径。默认为 dataset.txt, 不建议修改。 |
|
||||
| type | 数据集文件格式，固定为TEXT。 |
|
||||
| ports | 指向网络中的输入或重定向的输入，目前只支持一个输入，如果网络存在多个输入，请与@ccyh联系。 |
|
||||
| lid | 输入层的lid |
|
||||
| category | 输入的类别。将此参数设置为以下值之一：image（图像输入）或 undefined（其他类型的输入）。 |
|
||||
| dtype | 输入张量的数据类型，用于将数据发送到 Pnna 网络的输入端口。支持的数据类型包括 float32 和 quantized。 |
|
||||
| sparse | 指定网络张量是否以稀疏格式存在。将此参数设置为以下值之一：true（稀疏格式）或 false（压缩格式）。 |
|
||||
| tensor_name | 留空此参数 |
|
||||
| layout | 输入张量的格式，使用 nchw 用于 Caffe、Darknet、ONNX 和 PyTorch 模型。使用 nhwc 用于 TensorFlow、TensorFlow Lite 和 Keras 模型。 |
|
||||
| shape | 此张量的形状。第一维，shape[0]，表示每批的输入数量，允许在一次推理操作之前将多个输入发送到网络。如果batch维度设置为0，则需要从命令行指定--batch-size。如果 batch维度设置为大于1的值，则直接使用inputmeta.yml中的batch size并忽略命令行中的--batch-size。 |
|
||||
| fitting | 保留字段 |
|
||||
| preprocess | 预处理步骤和顺序。预处理支持下面的四个键，键的顺序代表预处理的顺序。您可以相应地调整顺序。 |
|
||||
| reverse_channel | 指定是否保留通道顺序。将此参数设置为以下值之一：true（保留通道顺序）或 false（不保留通道顺序）。对于 TensorFlow 和 TensorFlow Lite 框架的模型使用 true。 |
|
||||
| mean | 用于每个通道的均值。 |
|
||||
| scale | 张量的缩放值。均值和缩放值用于根据公式 (inputTensor - mean) × scale 归一化输入张量。|
|
||||
| preproc_node_params | 预处理节点参数，在 OVxlib C 项目案例中启用预处理任务 |
|
||||
| add_preproc_node | 用于处理 OVxlib C 项目案例中预处理节点的插入。[true, false] 中的布尔值，表示通过配置以下参数将预处理层添加到导出的应用程序中。此参数仅在 add_preproc_node 参数设置为 true 时有效。|
|
||||
| preproc_type | 预处理节点输入类型。 [IMAGE_RGB, IMAGE_RGB888_PLANAR,IMAGE_YUV420, IMAGE_GRAY, IMAGE_BGRA, TENSOR] 中的字符串值 |
|
||||
| preproc_perm | 预处理节点输入的置换参数。 |
|
||||
| redirect_to_output | 将database张量重定向到图形输出的特殊属性。如果为该属性设置了一个port，网络构建器将自动为该port生成一个输出层，以便后处理文件可以直接处理来自database的张量。 如果使用网络进行分类，则上例中的lid“input_0”表示输入数据集的标签lid。 您可以设置其他名称来表示标签的lid。 请注意，redirect_to_output 必须设置为 true，以便后处理文件可以直接处理来自database的张量。 标签的lid必须与后处理文件中定义的 labels_tensor 的lid相同。 [true, false] 中的布尔值。 指定是否将由张量表示的输入端口的数据直接发送到网络输出。true（直接发送到网络输出）或 false（不直接发送到网络输出）|
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>可以根据实际情况对生成的inputmeta文件进行修改。</p>
|
||||
</section>
|
||||
<section id="quantize-sh">
|
||||
<h2>quantize.sh 模型量化<a class="headerlink" href="#quantize-sh" title="Link to this heading">¶</a></h2>
|
||||
<p>如果我们训练好的模型的数据类型是float32的，为了使模型以更高的效率在Pnna上运行，我们可以对模型进行量化操作，量化操作可能会带来一定程度的精度损失。</p>
|
||||
<ul class="simple">
|
||||
<li><p>在netrans_cli目录下使用quantize.sh脚本进行量化操作。</p></li>
|
||||
</ul>
|
||||
<p>用法：./quantize.sh 以模型文件名命名的模型数据文件夹 量化类型，例如：</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>quantize.sh<span class="w"> </span>lenet<span class="w"> </span>uint8
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>支持的量化类型有：uint8、int8、int16</p>
|
||||
</section>
|
||||
<section id="export-sh">
|
||||
<h2>export.sh 模型导出<a class="headerlink" href="#export-sh" title="Link to this heading">¶</a></h2>
|
||||
<p>使用 export.sh 导出模型生成nbg文件。</p>
|
||||
<p>用法：export.sh 以模型文件名命名的模型数据文件夹 数据类型，例如：</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>export.sh<span class="w"> </span>lenet<span class="w"> </span>uint8
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>导出支持的数据类型：float、uint8、int8、int16，其中使用uint8、int8、int16导出时需要先进行模型量化。导出的工程会在模型所在的目录下面的wksp目录里。
|
||||
network_binary.nb文件在"asymmetric_affine"文件夹中：</p>
|
||||
<div class="highlight-shell notranslate"><div class="highlight"><pre><span></span>ls<span class="w"> </span>-lrt<span class="w"> </span>lenet/wksp/asymmetric_affine/
|
||||
-rw-r--r--<span class="w"> </span><span class="m">1</span><span class="w"> </span>hope<span class="w"> </span>hope<span class="w"> </span><span class="m">694912</span><span class="w"> </span>Jun<span class="w"> </span><span class="m">7</span><span class="w"> </span><span class="m">09</span>:55<span class="w"> </span>network_binary.nb
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>目前支持将生成的network_binary.nb文件部署到Pnna硬件平台。具体部署方法请参阅模型部署相关文档。</p>
|
||||
</section>
|
||||
<section id="id2">
|
||||
<h2>使用示例<a class="headerlink" href="#id2" title="Link to this heading">¶</a></h2>
|
||||
<p>请参照examples，examples 提供 <a class="reference external" href="./examples/caffe_model">caffe 模型转换示例</a>,<a class="reference external" href="./examples/darknet_model">darknet 模型转换示例</a>,<a class="reference external" href="./examples/tensorflow_model">tensorflow 模型转换示例</a>,<a class="reference external" href="./examples/onnx_model">onnx 模型转换示例</a>。</p>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">netrans_cli 使用</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#id1">netrans_cli 脚本</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#load-sh">load.sh 模型导入</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#config-sh">config.sh 预处理配置文件生成</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#quantize-sh">quantize.sh 模型量化</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#export-sh">export.sh 模型导出</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#id2">使用示例</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li>Previous: <a href="quick_start_guide.html" title="上一章">快速入门</a></li>
|
||||
<li>Next: <a href="netrans_py.html" title="下一章">netrans_py 使用</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/netrans_cli.md.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,276 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>netrans_py 使用 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="附录" href="appendix.html" />
|
||||
<link rel="prev" title="netrans_cli 使用" href="netrans_cli.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="netrans-py">
|
||||
<h1>netrans_py 使用<a class="headerlink" href="#netrans-py" title="Link to this heading">¶</a></h1>
|
||||
<p>netrans_py 为 Netrans 编译器的 python 调用接口。
|
||||
使用 ntrans_py 完成模型转换的步骤如下：</p>
|
||||
<ol class="simple">
|
||||
<li><p>导入模型</p></li>
|
||||
<li><p>生成并修改前处理配置文件 *_inputmeta.yml</p></li>
|
||||
<li><p>量化模型</p></li>
|
||||
<li><p>导出模型</p></li>
|
||||
</ol>
|
||||
<section id="netrans">
|
||||
<h2>Netrans 类<a class="headerlink" href="#netrans" title="Link to this heading">¶</a></h2>
|
||||
<p>创建 Netrans</p>
|
||||
<p>描述： 实例化 Netrans 类。
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">netrans</span><span class="w"> </span><span class="kn">import</span> <span class="n">Netrans</span>
|
||||
<span class="n">yolo_netrans</span> <span class="o">=</span> <span class="n">Netrans</span><span class="p">(</span><span class="s2">"../examples/darknet/yolov4_tiny"</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数</p>
|
||||
<table border="1" class="docutils">
|
||||
<thead>
|
||||
<tr>
|
||||
<th style="text-align: left;">参数名</th>
|
||||
<th>类型</th>
|
||||
<th>说明</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td style="text-align: left;">model_path</td>
|
||||
<td>str</td>
|
||||
<td>第一位置参数，模型文件的路径</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td style="text-align: left;">netans</td>
|
||||
<td>str</td>
|
||||
<td>如果 NETRANS_PATH 没有设置，可通过该参数指定netrans的路径</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table><p>输出返回：
|
||||
无。</p>
|
||||
<!-- <font color="#dd0000">注意：</font> 模型目录准备需要和netrans_cli一致，具体数据准备要求见[introduction](./introduction.md)。 --></section>
|
||||
<section id="netrans-import">
|
||||
<h2>Netrans.import 模型导入<a class="headerlink" href="#netrans-import" title="Link to this heading">¶</a></h2>
|
||||
<p>描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="n">yolo_netrans</span><span class="o">.</span><span class="n">import</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数：
|
||||
无。</p>
|
||||
<p>输出返回：
|
||||
无。
|
||||
在工程目录下生成 Pnna 支持的模型格式，以.json结尾的模型文件和 .data结尾的权重文件。</p>
|
||||
</section>
|
||||
<section id="netrans-config">
|
||||
<h2>Netrans.config 预处理配置文件生成<a class="headerlink" href="#netrans-config" title="Link to this heading">¶</a></h2>
|
||||
<p>描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="n">yolo_netrans</span><span class="o">.</span><span class="n">config</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数：</p>
|
||||
<div class="highlight-{table} notranslate"><div class="highlight"><pre><span></span>:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>输出返回：
|
||||
无。</p>
|
||||
</section>
|
||||
<section id="netrans-quantize">
|
||||
<h2>Netrans.quantize 模型量化<a class="headerlink" href="#netrans-quantize" title="Link to this heading">¶</a></h2>
|
||||
<p>描述： 对模型生成量化配置文件。
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="n">yolo_netrans</span><span class="o">.</span><span class="n">quantize</span><span class="p">(</span><span class="s2">"uint8"</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数：</p>
|
||||
<div class="highlight-{table} notranslate"><div class="highlight"><pre><span></span>:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str| 第一位置参数，模型量化类型，仅支持 "uint8", "int8", "int16"|
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>输出返回：
|
||||
无。</p>
|
||||
</section>
|
||||
<section id="netrans-export">
|
||||
<h2>Netrans.export 模型导出<a class="headerlink" href="#netrans-export" title="Link to this heading">¶</a></h2>
|
||||
<p>描述： 对模型生成量化配置文件。
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="n">yolo_netrans</span><span class="o">.</span><span class="n">export</span><span class="p">()</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数：
|
||||
无。</p>
|
||||
<p>输出返回：
|
||||
无。请在目录 “wksp/*/” 下检查是否生成nbg文件。</p>
|
||||
</section>
|
||||
<section id="netrans-model2nbg-nbg">
|
||||
<h2>Netrans.model2nbg 模型生成nbg文件<a class="headerlink" href="#netrans-model2nbg-nbg" title="Link to this heading">¶</a></h2>
|
||||
<p>描述： 模型导入、量化、及nbg文件生产
|
||||
代码示例：</p>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span> <span class="c1"># 无预处理</span>
|
||||
<span class="n">yolo_netrans</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span><span class="n">quantize_type</span><span class="o">=</span><span class="s1">'uint8'</span><span class="p">)</span>
|
||||
<span class="c1"># 需要对数据进行normlize, menas为128, scale 为 0.0039</span>
|
||||
<span class="n">yolo_netrans</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span><span class="n">quantize_type</span><span class="o">=</span><span class="s1">'uint8'</span><span class="p">,</span><span class="n">mean</span><span class="o">=</span><span class="mi">128</span><span class="p">,</span> <span class="n">scale</span> <span class="o">=</span> <span class="mf">0.0039</span><span class="p">)</span>
|
||||
<span class="c1"># 需要对数据分通道进行normlize, menas为128,127,125,scale 为 0.0039, 且reverse_channel 为 True </span>
|
||||
<span class="n">yolo_netrans</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span><span class="n">quantize_type</span><span class="o">=</span><span class="s1">'uint8'</span><span class="n">mean</span><span class="o">=</span><span class="p">[</span><span class="mi">128</span><span class="p">,</span> <span class="mi">127</span><span class="p">,</span> <span class="mi">125</span><span class="p">],</span> <span class="n">scale</span> <span class="o">=</span> <span class="mf">0.0039</span><span class="p">,</span> <span class="n">reverse_channel</span><span class="o">=</span> <span class="kc">True</span><span class="p">)</span>
|
||||
<span class="c1"># 已经进行初始化设置</span>
|
||||
<span class="n">yolo_netrans</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span><span class="n">quantize_type</span><span class="o">=</span><span class="s1">'uint8'</span><span class="p">,</span> <span class="n">inputmeta</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>参数</p>
|
||||
<div class="highlight-{table} notranslate"><div class="highlight"><pre><span></span>:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str, ["uint8", "int8", "int16" ] | 量化类型，将模型量化成该参数指定的类型 |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>输出返回：
|
||||
请在目录 “wksp/*/” 下检查是否生成nbg文件。</p>
|
||||
</section>
|
||||
<section id="id1">
|
||||
<h2>使用示例<a class="headerlink" href="#id1" title="Link to this heading">¶</a></h2>
|
||||
<div class="highlight-py3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">nertans</span><span class="w"> </span><span class="kn">import</span> <span class="n">Netrans</span>
|
||||
<span class="n">model_path</span> <span class="o">=</span> <span class="s1">'example/darknet/yolov4_tiny'</span>
|
||||
<span class="n">netrans_path</span> <span class="o">=</span> <span class="s2">"netrans/bin"</span> <span class="c1"># 如果进行了export定义申明，这一步可以不用</span>
|
||||
|
||||
<span class="c1"># 初始化netrans</span>
|
||||
<span class="n">net</span> <span class="o">=</span> <span class="n">Netrans</span><span class="p">(</span><span class="n">model_path</span><span class="p">,</span><span class="n">netrans</span><span class="o">=</span><span class="n">netrans_path</span><span class="p">)</span>
|
||||
<span class="c1"># 模型载入</span>
|
||||
<span class="n">net</span><span class="o">.</span><span class="n">import</span><span class="p">()</span>
|
||||
<span class="c1"># 配置预处理 normlize 的参数</span>
|
||||
<span class="n">net</span><span class="o">.</span><span class="n">config</span><span class="p">(</span><span class="n">scale</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span><span class="n">mean</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="c1"># 模型量化</span>
|
||||
<span class="n">net</span><span class="o">.</span><span class="n">quantize</span><span class="p">(</span><span class="s2">"uint8"</span><span class="p">)</span>
|
||||
<span class="c1"># 模型导出</span>
|
||||
<span class="n">net</span><span class="o">.</span><span class="n">export</span><span class="p">()</span>
|
||||
|
||||
<span class="c1"># 模型直接量化成 int16 并导出, 直接复用刚配置好的 inputmeta</span>
|
||||
<span class="n">net</span><span class="o">.</span><span class="n">model2nbg</span><span class="p">(</span><span class="n">quantize_type</span> <span class="o">=</span> <span class="s2">"int16"</span><span class="p">,</span> <span class="n">inputmeta</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">netrans_py 使用</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans">Netrans 类</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-import">Netrans.import 模型导入</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-config">Netrans.config 预处理配置文件生成</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-quantize">Netrans.quantize 模型量化</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-export">Netrans.export 模型导出</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-model2nbg-nbg">Netrans.model2nbg 模型生成nbg文件</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#id1">使用示例</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li>Previous: <a href="netrans_cli.html" title="上一章">netrans_cli 使用</a></li>
|
||||
<li>Next: <a href="appendix.html" title="下一章">附录</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/netrans_py.md.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Binary file not shown.
|
|
@ -1,193 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Python 模块索引 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<script>
|
||||
DOCUMENTATION_OPTIONS.COLLAPSE_INDEX = true;
|
||||
</script>
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
|
||||
<h1>Python 模块索引</h1>
|
||||
|
||||
<div class="modindex-jumpbox">
|
||||
<a href="#cap-c"><strong>c</strong></a> |
|
||||
<a href="#cap-e"><strong>e</strong></a> |
|
||||
<a href="#cap-f"><strong>f</strong></a> |
|
||||
<a href="#cap-i"><strong>i</strong></a> |
|
||||
<a href="#cap-n"><strong>n</strong></a> |
|
||||
<a href="#cap-q"><strong>q</strong></a> |
|
||||
<a href="#cap-u"><strong>u</strong></a>
|
||||
</div>
|
||||
|
||||
<table class="indextable modindextable">
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-c"><td></td><td>
|
||||
<strong>c</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="config.html#module-config"><code class="xref">config</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-e"><td></td><td>
|
||||
<strong>e</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="example.html#module-example"><code class="xref">example</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="export.html#module-export"><code class="xref">export</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-f"><td></td><td>
|
||||
<strong>f</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="file_model.html#module-file_model"><code class="xref">file_model</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-i"><td></td><td>
|
||||
<strong>i</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="import_model.html#module-import_model"><code class="xref">import_model</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="infer.html#module-infer"><code class="xref">infer</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-n"><td></td><td>
|
||||
<strong>n</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="netrans.html#module-netrans"><code class="xref">netrans</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-q"><td></td><td>
|
||||
<strong>q</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="quantize.html#module-quantize"><code class="xref">quantize</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="quantize_hb.html#module-quantize_hb"><code class="xref">quantize_hb</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
<tr class="pcap"><td></td><td> </td><td></td></tr>
|
||||
<tr class="cap" id="cap-u"><td></td><td>
|
||||
<strong>u</strong></td><td></td></tr>
|
||||
<tr>
|
||||
<td></td>
|
||||
<td>
|
||||
<a href="utils.html#module-utils"><code class="xref">utils</code></a></td><td>
|
||||
<em></em></td></tr>
|
||||
</table>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,133 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>quantize module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="quantize_hb module" href="quantize_hb.html" />
|
||||
<link rel="prev" title="infer module" href="infer.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-quantize">
|
||||
<span id="quantize-module"></span><h1>quantize module<a class="headerlink" href="#module-quantize" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quantize.Quantize">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quantize.</span></span><span class="sig-name descname"><span class="pre">Quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quantize.html#Quantize"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#quantize.Quantize" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<p>解析 Netrans 参数，基于 pnnacc 量化模型
|
||||
:param cla: 实例化以后的 Netrans 类，需要解析里面包含的参数
|
||||
:type cla: class</p>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quantize.Quantize.quantize_network">
|
||||
<span class="sig-name descname"><span class="pre">quantize_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quantize.Quantize.quantize_network" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="infer.html" title="上一章">infer module</a></li>
|
||||
<li>Next: <a href="quantize_hb.html" title="下一章">quantize_hb module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/quantize.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,135 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>quantize_hb module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="utils module" href="utils.html" />
|
||||
<link rel="prev" title="quantize module" href="quantize.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-quantize_hb">
|
||||
<span id="quantize-hb-module"></span><h1>quantize_hb module<a class="headerlink" href="#module-quantize_hb" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="quantize_hb.Quantize">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">quantize_hb.</span></span><span class="sig-name descname"><span class="pre">Quantize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/quantize_hb.html#Quantize"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#quantize_hb.Quantize" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<a class="reference internal" href="utils.html#utils.AttributeCopier" title="utils.AttributeCopier"><code class="xref py py-class docutils literal notranslate"><span class="pre">AttributeCopier</span></code></a></p>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="quantize_hb.Quantize.quantize_network">
|
||||
<span class="sig-name descname"><span class="pre">quantize_network</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span><span class="n"><span class="pre">args</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kargs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#quantize_hb.Quantize.quantize_network" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="quantize_hb.main">
|
||||
<span class="sig-prename descclassname"><span class="pre">quantize_hb.</span></span><span class="sig-name descname"><span class="pre">main</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/quantize_hb.html#main"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#quantize_hb.main" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="quantize.html" title="上一章">quantize module</a></li>
|
||||
<li>Next: <a href="utils.html" title="下一章">utils module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/quantize_hb.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,254 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>快速入门 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="next" title="netrans_cli 使用" href="netrans_cli.html" />
|
||||
<link rel="prev" title="netrans documentation" href="index.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="id1">
|
||||
<h1>快速入门<a class="headerlink" href="#id1" title="Link to this heading">¶</a></h1>
|
||||
<p>本文档以 onnx 格式的 yolov5s 为例，演示如何快速安装Nertans 并使用 Netrans 量化、编译模型并生成 nbg 文件。</p>
|
||||
<section id="id2">
|
||||
<h2>系统环境<a class="headerlink" href="#id2" title="Link to this heading">¶</a></h2>
|
||||
<ul class="simple">
|
||||
<li><p>Linux操作系统，推荐 Ubuntu 20.04 或 Debian12</p></li>
|
||||
<li><p>Python 3.8</p></li>
|
||||
<li><p>RAM 至少 8GB</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="netrans">
|
||||
<h2>安装Netrans<a class="headerlink" href="#netrans" title="Link to this heading">¶</a></h2>
|
||||
<p>创建 python3.8 环境</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>wget<span class="w"> </span><span class="s2">"https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-</span><span class="k">$(</span>uname<span class="k">)</span><span class="s2">-</span><span class="k">$(</span>uname<span class="w"> </span>-m<span class="k">)</span><span class="s2">.sh"</span>
|
||||
mkdir<span class="w"> </span>-p<span class="w"> </span>~/app
|
||||
<span class="nv">INSTALL_PATH</span><span class="o">=</span><span class="s2">"</span><span class="si">${</span><span class="nv">HOME</span><span class="si">}</span><span class="s2">/app/miniforge3"</span>
|
||||
bash<span class="w"> </span>Miniforge3-Linux-x86_64.sh<span class="w"> </span>-b<span class="w"> </span>-p<span class="w"> </span><span class="si">${</span><span class="nv">INSTALL_PATH</span><span class="si">}</span>
|
||||
<span class="nb">echo</span><span class="w"> </span><span class="s2">"source "</span><span class="si">${</span><span class="nv">INSTALL_PATH</span><span class="si">}</span>/etc/profile.d/conda.sh<span class="s2">""</span><span class="w"> </span>>><span class="w"> </span><span class="si">${</span><span class="nv">HOME</span><span class="si">}</span>/.bashrc
|
||||
<span class="nb">echo</span><span class="w"> </span><span class="s2">"source "</span><span class="si">${</span><span class="nv">INSTALL_PATH</span><span class="si">}</span>/etc/profile.d/mamba.sh<span class="s2">""</span><span class="w"> </span>>><span class="w"> </span><span class="si">${</span><span class="nv">HOME</span><span class="si">}</span>/.bashrc
|
||||
<span class="nb">source</span><span class="w"> </span><span class="si">${</span><span class="nv">HOME</span><span class="si">}</span>/.bashrc
|
||||
mamba<span class="w"> </span>create<span class="w"> </span>-n<span class="w"> </span>netrans<span class="w"> </span><span class="nv">python</span><span class="o">=</span><span class="m">3</span>.8<span class="w"> </span>-y
|
||||
mamba<span class="w"> </span>activate<span class="w"> </span>netrans
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>下载 Netrans</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span>~/app
|
||||
git<span class="w"> </span>clone<span class="w"> </span>https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>配置 Netrans</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span>~/app/netrans
|
||||
./setup.sh
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="netrans-yolov5s">
|
||||
<h2>使用 Netrans 编译 yolov5s 模型<a class="headerlink" href="#netrans-yolov5s" title="Link to this heading">¶</a></h2>
|
||||
<p>进入工作目录</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><span class="nb">cd</span><span class="w"> </span>～/app/netrans/examples/onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>此时目录如下：</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>onnx/
|
||||
├── README.md
|
||||
└── yolov5s
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
└── yolov5s.onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
<section id="netrans-cli-yolov5s">
|
||||
<h3>使用 netrans_cli 编译 yolov5s<a class="headerlink" href="#netrans-cli-yolov5s" title="Link to this heading">¶</a></h3>
|
||||
<section id="id3">
|
||||
<h4>导入模型<a class="headerlink" href="#id3" title="Link to this heading">¶</a></h4>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>load.sh<span class="w"> </span>yolov5s
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。</p>
|
||||
<p>此时 yolov5s 的目录结构如下</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>yolov5s/
|
||||
├── 0.jpg
|
||||
├── yolov5s.data
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="id4">
|
||||
<h4>生成配置文件模板<a class="headerlink" href="#id4" title="Link to this heading">¶</a></h4>
|
||||
<p>配置文件定义输入数据前处理相关参数。Netrans预定义了配置文件模板生成脚本，用户需根据模型前处理参数对配置文件进行修改。</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>config.sh<span class="w"> </span>yolov5s
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>此时 yolov5s 的目录结构如下：</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>根据 yolov5s 的前处理参数 ，修改 yml 中的 scale 为 0.003921568627。
|
||||
打开 <code class="docutils literal notranslate"><span class="pre">yolov5s_inputmeta.yml</span></code> 文件，修改第30-33行：</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span> scale:
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="id5">
|
||||
<h4>量化模型<a class="headerlink" href="#id5" title="Link to this heading">¶</a></h4>
|
||||
<p>生成 unit8 量化的量化参数文件</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>quantize.sh<span class="w"> </span>yolov5s<span class="w"> </span>uint8
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>此时 yolov5s 的目录结构如下：</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
<section id="id6">
|
||||
<h4>导出模型<a class="headerlink" href="#id6" title="Link to this heading">¶</a></h4>
|
||||
<p>导出 unit8 量化的模型项目工程</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>export.sh<span class="w"> </span>yolov5s<span class="w"> </span>uint8
|
||||
</pre></div>
|
||||
</div>
|
||||
<p>此时 yolov5s 的目录结构如下：</p>
|
||||
<div class="highlight-text notranslate"><div class="highlight"><pre><span></span>yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ └── asymmetric_affine
|
||||
│ └── network_binary.nb
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
<section id="netrans-py-yolov5s">
|
||||
<h3>使用 netrans_py 编译 yolov5s 模型<a class="headerlink" href="#netrans-py-yolov5s" title="Link to this heading">¶</a></h3>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>example.py<span class="w"> </span>yolov5s<span class="w"> </span>-q<span class="w"> </span>uint8<span class="w"> </span>-m<span class="w"> </span><span class="m">0</span><span class="w"> </span>-s<span class="w"> </span><span class="m">0</span>.003921568627
|
||||
</pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</section>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">快速入门</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#id2">系统环境</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans">安装Netrans</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="#netrans-yolov5s">使用 Netrans 编译 yolov5s 模型</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li>Previous: <a href="index.html" title="上一章">netrans documentation</a></li>
|
||||
<li>Next: <a href="netrans_cli.html" title="下一章">netrans_cli 使用</a></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/quick_start_guide.md.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,122 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>搜索 — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script src="_static/searchtools.js"></script>
|
||||
<script src="_static/language_data.js"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="#" />
|
||||
<script src="searchindex.js" defer="defer"></script>
|
||||
<meta name="robots" content="noindex" />
|
||||
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<h1 id="search-documentation">搜索</h1>
|
||||
|
||||
<noscript>
|
||||
<div class="admonition warning">
|
||||
<p>
|
||||
请激活 JavaScript 以开启搜索功能。
|
||||
</p>
|
||||
</div>
|
||||
</noscript>
|
||||
|
||||
|
||||
<p>
|
||||
当搜索多个关键词时，只会显示同时包含所有关键词的内容。
|
||||
</p>
|
||||
|
||||
|
||||
<form action="" method="get">
|
||||
<input type="text" name="q" aria-labelledby="search-documentation" value="" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||||
<input type="submit" value="搜索" />
|
||||
<span id="search-progress" style="padding-left: 10px"></span>
|
||||
</form>
|
||||
|
||||
|
||||
<div id="search-results"></div>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1,107 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>setup module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="setup-module">
|
||||
<h1>setup module<a class="headerlink" href="#setup-module" title="Link to this heading">¶</a></h1>
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="appendix.html">附录</a></li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/setup.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,180 +0,0 @@
|
|||
<!DOCTYPE html>
|
||||
|
||||
<html lang="zh" data-content_root="./">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
|
||||
<title>utils module — netrans 0.1 文档</title>
|
||||
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=5ecbeea2" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/basic.css?v=b08954a9" />
|
||||
<link rel="stylesheet" type="text/css" href="_static/alabaster.css?v=27fed22d" />
|
||||
<script src="_static/documentation_options.js?v=52efc512"></script>
|
||||
<script src="_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<link rel="index" title="索引" href="genindex.html" />
|
||||
<link rel="search" title="搜索" href="search.html" />
|
||||
<link rel="prev" title="quantize_hb module" href="quantize_hb.html" />
|
||||
|
||||
<link rel="stylesheet" href="_static/custom.css" type="text/css" />
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</head><body>
|
||||
|
||||
|
||||
<div class="document">
|
||||
<div class="documentwrapper">
|
||||
<div class="bodywrapper">
|
||||
|
||||
|
||||
<div class="body" role="main">
|
||||
|
||||
<section id="module-utils">
|
||||
<span id="utils-module"></span><h1>utils module<a class="headerlink" href="#module-utils" title="Link to this heading">¶</a></h1>
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="utils.AttributeCopier">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">AttributeCopier</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#AttributeCopier"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.AttributeCopier" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>快速解析复制 Netrans 信息</p>
|
||||
<dl class="py method">
|
||||
<dt class="sig sig-object py" id="utils.AttributeCopier.copy_attribute_name">
|
||||
<span class="sig-name descname"><span class="pre">copy_attribute_name</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source_obj</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#AttributeCopier.copy_attribute_name"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.AttributeCopier.copy_attribute_name" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="utils.check_dir">
|
||||
<span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">check_dir</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">network_name</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#check_dir"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.check_dir" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>判断工程目录是否存在</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>network_name</strong> (<em>str</em>) -- 工程目录路径</p>
|
||||
</dd>
|
||||
<dt class="field-even">抛出<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p><strong>NotADirectoryError</strong> -- 没有那个工程目录</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="utils.check_env">
|
||||
<span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">check_env</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#check_env"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.check_env" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="utils.check_netrans">
|
||||
<span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">check_netrans</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">netrans</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#check_netrans"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.check_netrans" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>判断 netrans 是否配置成功</p>
|
||||
<dl class="field-list simple">
|
||||
<dt class="field-odd">参数<span class="colon">:</span></dt>
|
||||
<dd class="field-odd"><p><strong>netrans</strong> (<em>str</em><em>, </em><em>bool</em>) -- _netrans 路径, 如果没有配置(默认为False)会去环境变量里找</p>
|
||||
</dd>
|
||||
<dt class="field-even">抛出<span class="colon">:</span></dt>
|
||||
<dd class="field-even"><p><strong>NotADirectoryError</strong> -- 找不到 Netrans 会返回 NotADirectoryError</p>
|
||||
</dd>
|
||||
</dl>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="utils.check_path">
|
||||
<span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">check_path</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">func</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#check_path"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.check_path" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>装饰器, 确保在工程目录运行 nertans</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py class">
|
||||
<dt class="sig sig-object py" id="utils.create_cls">
|
||||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">create_cls</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">netrans_path</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quantized_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">'uint8'</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">verbose</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#create_cls"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.create_cls" title="Link to this definition">¶</a></dt>
|
||||
<dd><p>基类：<code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
|
||||
<p>快速测试时候模拟实例化Netrans</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="py function">
|
||||
<dt class="sig sig-object py" id="utils.remove_history_file">
|
||||
<span class="sig-prename descclassname"><span class="pre">utils.</span></span><span class="sig-name descname"><span class="pre">remove_history_file</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/utils.html#remove_history_file"><span class="viewcode-link"><span class="pre">[源代码]</span></span></a><a class="headerlink" href="#utils.remove_history_file" title="Link to this definition">¶</a></dt>
|
||||
<dd></dd></dl>
|
||||
|
||||
</section>
|
||||
|
||||
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h1 class="logo"><a href="index.html">netrans</a></h1>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
<search id="searchbox" style="display: none" role="search">
|
||||
<div class="searchformwrapper">
|
||||
<form class="search" action="search.html" method="get">
|
||||
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false" placeholder="Search"/>
|
||||
<input type="submit" value="提交" />
|
||||
</form>
|
||||
</div>
|
||||
</search>
|
||||
<script>document.getElementById('searchbox').style.display = "block"</script><h3>导航</h3>
|
||||
<p class="caption" role="heading"><span class="caption-text">Contents:</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1"><a class="reference internal" href="quick_start_guide.html">快速入门</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_cli.html">netrans_cli 使用</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="netrans_py.html">netrans_py 使用</a></li>
|
||||
<li class="toctree-l1 current"><a class="reference internal" href="appendix.html">附录</a><ul class="current">
|
||||
<li class="toctree-l2"><a class="reference internal" href="gen_api.html">gen api html & pdf by sphinx</a></li>
|
||||
<li class="toctree-l2 current"><a class="reference internal" href="modules.html">netrans_py</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<div class="relations">
|
||||
<h3>Related Topics</h3>
|
||||
<ul>
|
||||
<li><a href="index.html">Documentation overview</a><ul>
|
||||
<li><a href="appendix.html">附录</a><ul>
|
||||
<li><a href="modules.html">netrans_py</a><ul>
|
||||
<li>Previous: <a href="quantize_hb.html" title="上一章">quantize_hb module</a></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul></li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="footer">
|
||||
©2025, ccyh.
|
||||
|
||||
|
|
||||
Powered by <a href="https://www.sphinx-doc.org/">Sphinx 8.2.3</a>
|
||||
& <a href="https://alabaster.readthedocs.io">Alabaster 1.0.0</a>
|
||||
|
||||
|
|
||||
<a href="_sources/utils.rst.txt"
|
||||
rel="nofollow">Page source</a>
|
||||
</div>
|
||||
|
||||
|
||||
|
||||
|
||||
</body>
|
||||
</html>
|
||||
BIN
docs/netrans.pdf
BIN
docs/netrans.pdf
Binary file not shown.
|
|
@ -1,192 +1,229 @@
|
|||
# netrans_cli 使用
|
||||
# netrans_cli
|
||||
|
||||
netrans_cli 是 netrans 进行模型转换的命令行工具，使用 ntrans_cli 完成模型转换的步骤如下：
|
||||
netrans_cli 是 netrans 进行模型转换的命令行工具，使用 netrans_cli 完成模型转换的步骤如下：
|
||||
|
||||
1. 导入模型
|
||||
2. 生成并修改前处理配置文件 *_inputmeta.yml
|
||||
3. 量化模型
|
||||
4. 导出模型
|
||||
1. 使用 `load` 导入模型 & 生成前后处理配置文件
|
||||
2. 使用 `quantize` 量化模型 & 生成量化参数文件
|
||||
3. 使用 `add_pre_post` 把前后处理加入推理计算图
|
||||
4. 使用 `export` 导出模型
|
||||
|
||||
## netrans_cli 脚本
|
||||
## 目录
|
||||
|
||||
|脚本|功能|使用|
|
||||
|:---|---|---|
|
||||
|load.sh| 模型导入功能，将模型转换成 Pnna 支持的格式| load.sh model_name|
|
||||
|config.sh| 预处理模版生成功能，生成预处理模版，根据模型进行对于的修改| config.sh model_name|
|
||||
|quantize.sh| 量化功能， 对模型进行量化生成量化参数文件| quantize.sh model_name quantize_data_type|
|
||||
|export.sh|导出功能，将量化好的模型导出成 Pnna 上可以运行的runtime| export.sh model_name quantize_data_type|
|
||||
[系统依赖](#系统依赖)
|
||||
[安装指南](#安装-netrans_cli)
|
||||
[模型准备](#模型准备)
|
||||
[命令介绍](#命令介绍)
|
||||
[使用示例](#使用示例)
|
||||
|
||||
<font color="#dd0000">对于不同框架下训练的模型，需要准备不同的数据，所有的数据都需要与模型放在同一个文件夹下，模型文件名和文件夹名需要保持一致。</font>
|
||||
## 系统依赖
|
||||
|
||||
## load.sh 模型导入
|
||||
- CPU：Intel® Core™ i5-6500 CPU @ 3.2 GHz x4 支持 the Intel® Advanced Vector Extensions
|
||||
- RAM：至少8GB
|
||||
- 硬盘：160GB
|
||||
- 操作系统：Ubuntu 20.04 LTS 64-bit with Python 3.10，不推荐使用其他版本
|
||||
|
||||
使用 load.sh 导入模型
|
||||
## 安装 Netrans_cli
|
||||
|
||||
- 用法： load.sh 以模型文件名命名的模型数据文件夹，例如：
|
||||
|
||||
```bash
|
||||
load.sh lenet
|
||||
```
|
||||
|
||||
"lenet"是文件夹名，也作为模型名和权重文件名。导入会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有"lenet.json"和"lenet.data"文件:
|
||||
|
||||
```bash
|
||||
$ ls -lrt lenet
|
||||
total 3396
|
||||
-rwxr-xr-x 1 hope hope 1727201 Nov 5 2018 lenet.pb
|
||||
-rw-r--r-- 1 hope hope 553 Nov 5 2018 0.jpg
|
||||
-rwxr--r-- 1 hope hope 6 Apr 21 17:04 dataset.txt
|
||||
-rw-rw-r-- 1 hope hope 69 Jun 7 09:19 inputs_outputs.txt
|
||||
-rw-r--r-- 1 hope hope 5553 Jun 7 09:21 lenet.json
|
||||
-rw-r--r-- 1 hope hope 1725178 Jun 7 09:21 lenet.data
|
||||
```
|
||||
|
||||
## config.sh 预处理配置文件生成
|
||||
|
||||
使用 config.sh 生成 inputmeta 文件
|
||||
|
||||
- config.sh 以模型文件名命名的模型数据文件夹，例如：
|
||||
|
||||
```bash
|
||||
config.sh lenet
|
||||
```
|
||||
|
||||
inputmeta 文件生成会打印相关日志信息，成功后会打印SUCESS。导入后lenet文件夹应该有 "lenet_inputmeta.yml" 文件:
|
||||
|
||||
```shell
|
||||
$ ls -lrt lenet
|
||||
total 3400
|
||||
-rwxr-xr-x 1 hope hope 1727201 Nov 5 2018 lenet.pb
|
||||
-rw-r--r-- 1 hope hope 553 Nov 5 2018 0.jpg
|
||||
-rwxr--r-- 1 hope hope 6 Apr 21 17:04 dataset.txt
|
||||
-rw-rw-r-- 1 hope hope 69 Jun 7 09:19 inputs_outputs.txt
|
||||
-rw-r--r-- 1 hope hope 5553 Jun 7 09:21 lenet.json
|
||||
-rw-r--r-- 1 hope hope 1725178 Jun 7 09:21 lenet.data
|
||||
-rw-r--r-- 1 hope hope 948 Jun 7 09:35 lenet_inputmeta.yml
|
||||
```
|
||||
|
||||
可以看到，最终生成的是*.yml文件，该文件用于为Netrans中间模型配置输入层数据集合。<b>Netrans中的量化、推理、导出和图片转dat的操作都需要用到这个文件。因此，此步骤不可跳过。</b>
|
||||
|
||||
Inputmeta.yml文件结构如下：
|
||||
|
||||
```yaml
|
||||
%YAML 1.2
|
||||
---
|
||||
# !!!This file disallow TABs!!!
|
||||
# "category" allowed values: "image, undefined"
|
||||
# "database" allowed types: "H5FS, SQLITE, TEXT, LMDB, NPY, GENERATOR"
|
||||
# "tensor_name" only support in H5FS database
|
||||
# "preproc_type" allowed types:"IMAGE_RGB, IMAGE_RGB888_PLANAR, IMAGE_RGB888_PLANAR_SEP,
|
||||
IMAGE_I420,
|
||||
# IMAGE_NV12, IMAGE_YUV444, IMAGE_GRAY, IMAGE_BGRA, TENSOR"
|
||||
input_meta:
|
||||
databases:
|
||||
- path: dataset.txt
|
||||
type: TEXT
|
||||
ports:
|
||||
- lid: data_0
|
||||
category: image
|
||||
dtype: float32
|
||||
sparse: false
|
||||
tensor_name:
|
||||
layout: nhwc
|
||||
shape:
|
||||
- 50
|
||||
- 224
|
||||
- 224
|
||||
- 3
|
||||
preprocess:
|
||||
reverse_channel: false
|
||||
mean:
|
||||
- 103.94
|
||||
- 116.78
|
||||
- 123.67
|
||||
scale: 0.017
|
||||
preproc_node_params:
|
||||
preproc_type: IMAGE_RGB
|
||||
add_preproc_node: false
|
||||
preproc_perm:
|
||||
- 0
|
||||
- 1
|
||||
- 2
|
||||
- 3
|
||||
- lid: label_0
|
||||
redirect_to_output: true
|
||||
category: undefined
|
||||
tensor_name:
|
||||
dtype: float32
|
||||
shape:
|
||||
- 1
|
||||
- 1
|
||||
```
|
||||
|
||||
上面示例文件的各个参数解释：
|
||||
|
||||
```{table}
|
||||
:widths: 20, 80
|
||||
:align: left
|
||||
| 参数 | 说明 |
|
||||
| :--- | --- |
|
||||
| input_meta | 预处理参数配置申明。 |
|
||||
| databases | 数据配置，包括设置 path、type 和 ports 。|
|
||||
| path | 数据集文件的相对（执行目录）或绝对路径。默认为 dataset.txt, 不建议修改。 |
|
||||
| type | 数据集文件格式，固定为TEXT。 |
|
||||
| ports | 指向网络中的输入或重定向的输入，目前只支持一个输入，如果网络存在多个输入，请与@ccyh联系。 |
|
||||
| lid | 输入层的lid |
|
||||
| category | 输入的类别。将此参数设置为以下值之一：image（图像输入）或 undefined（其他类型的输入）。 |
|
||||
| dtype | 输入张量的数据类型，用于将数据发送到 Pnna 网络的输入端口。支持的数据类型包括 float32 和 quantized。 |
|
||||
| sparse | 指定网络张量是否以稀疏格式存在。将此参数设置为以下值之一：true（稀疏格式）或 false（压缩格式）。 |
|
||||
| tensor_name | 留空此参数 |
|
||||
| layout | 输入张量的格式，使用 nchw 用于 Caffe、Darknet、ONNX 和 PyTorch 模型。使用 nhwc 用于 TensorFlow、TensorFlow Lite 和 Keras 模型。 |
|
||||
| shape | 此张量的形状。第一维，shape[0]，表示每批的输入数量，允许在一次推理操作之前将多个输入发送到网络。如果batch维度设置为0，则需要从命令行指定--batch-size。如果 batch维度设置为大于1的值，则直接使用inputmeta.yml中的batch size并忽略命令行中的--batch-size。 |
|
||||
| fitting | 保留字段 |
|
||||
| preprocess | 预处理步骤和顺序。预处理支持下面的四个键，键的顺序代表预处理的顺序。您可以相应地调整顺序。 |
|
||||
| reverse_channel | 指定是否保留通道顺序。将此参数设置为以下值之一：true（保留通道顺序）或 false（不保留通道顺序）。对于 TensorFlow 和 TensorFlow Lite 框架的模型使用 true。 |
|
||||
| mean | 用于每个通道的均值。 |
|
||||
| scale | 张量的缩放值。均值和缩放值用于根据公式 (inputTensor - mean) × scale 归一化输入张量。|
|
||||
| preproc_node_params | 预处理节点参数，在 OVxlib C 项目案例中启用预处理任务 |
|
||||
| add_preproc_node | 用于处理 OVxlib C 项目案例中预处理节点的插入。[true, false] 中的布尔值，表示通过配置以下参数将预处理层添加到导出的应用程序中。此参数仅在 add_preproc_node 参数设置为 true 时有效。|
|
||||
| preproc_type | 预处理节点输入类型。 [IMAGE_RGB, IMAGE_RGB888_PLANAR,IMAGE_YUV420, IMAGE_GRAY, IMAGE_BGRA, TENSOR] 中的字符串值 |
|
||||
| preproc_perm | 预处理节点输入的置换参数。 |
|
||||
| redirect_to_output | 将database张量重定向到图形输出的特殊属性。如果为该属性设置了一个port，网络构建器将自动为该port生成一个输出层，以便后处理文件可以直接处理来自database的张量。 如果使用网络进行分类，则上例中的lid“input_0”表示输入数据集的标签lid。 您可以设置其他名称来表示标签的lid。 请注意，redirect_to_output 必须设置为 true，以便后处理文件可以直接处理来自database的张量。 标签的lid必须与后处理文件中定义的 labels_tensor 的lid相同。 [true, false] 中的布尔值。 指定是否将由张量表示的输入端口的数据直接发送到网络输出。true（直接发送到网络输出）或 false（不直接发送到网络输出）|
|
||||
```
|
||||
|
||||
可以根据实际情况对生成的inputmeta文件进行修改。
|
||||
|
||||
## quantize.sh 模型量化
|
||||
|
||||
如果我们训练好的模型的数据类型是float32的，为了使模型以更高的效率在Pnna上运行，我们可以对模型进行量化操作，量化操作可能会带来一定程度的精度损失。
|
||||
|
||||
- 在netrans_cli目录下使用quantize.sh脚本进行量化操作。
|
||||
|
||||
用法：./quantize.sh 以模型文件名命名的模型数据文件夹 量化类型，例如：
|
||||
建议使用 mamba 作为环境隔离管理工具，避免安装 Netrans 导致污染系统环境。安装并激活 mamba 步骤如下：
|
||||
|
||||
```bash
|
||||
quantize.sh lenet uint8
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.10
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
支持的量化类型有：uint8、int8、int16
|
||||
|
||||
## export.sh 模型导出
|
||||
|
||||
使用 export.sh 导出模型生成nbg文件。
|
||||
|
||||
用法：export.sh 以模型文件名命名的模型数据文件夹 数据类型，例如：
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
export.sh lenet uint8
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
导出支持的数据类型：float、uint8、int8、int16，其中使用uint8、int8、int16导出时需要先进行模型量化。导出的工程会在模型所在的目录下面的wksp目录里。
|
||||
network_binary.nb文件在"asymmetric_affine"文件夹中：
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```shell
|
||||
ls -lrt lenet/wksp/asymmetric_affine/
|
||||
-rw-r--r-- 1 hope hope 694912 Jun 7 09:55 network_binary.nb
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
目前支持将生成的network_binary.nb文件部署到Pnna硬件平台。具体部署方法请参阅模型部署相关文档。
|
||||
## 模型准备
|
||||
|
||||
不同框架下训练的模型需要准备不同的数据，所有的数据都需要与模型放在同一个文件夹下。具体参照 example 中不同框架的示例说明。
|
||||
如 ONNX 格式保存的 yolov8s 模型，目录结构如下：
|
||||
|
||||
```
|
||||
yolov8s/
|
||||
├── channel_mean_value.txt # 定义预处理中 mean & scale 的配置参数
|
||||
├── dataset.txt # 定义量化数据的文件
|
||||
├── input_image
|
||||
│ ├── 0.jpg
|
||||
│ ├── 1.jpg
|
||||
│ ├── 2.jpg
|
||||
│ ├── 3.jpg
|
||||
│ ├── 4.jpg
|
||||
│ ├── 5.jpg
|
||||
│ ├── 6.jpg
|
||||
│ ├── 7.jpg
|
||||
│ ├── 8.jpg
|
||||
│ └── 9.jpg
|
||||
└── yolov8s.onnx # 模型结构 & 权重
|
||||
```
|
||||
|
||||
## 命令介绍
|
||||
|
||||
### load
|
||||
|
||||
描述：
|
||||
|
||||
使用 load 导入模型，同时生成配置文件。导入会打印相关日志信息，成功后会打印 SUCESS。
|
||||
|
||||
用法：
|
||||
|
||||
```bash
|
||||
netrans load model_path [--mean MEAN [MEAN ...]] [--scale SCALE [SCALE ...]]
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
| model_path | str | 第一位置参数，模型文件的路径 |
|
||||
| --mean | float | 通道均值 (例如: 128 或 128 128 128) |
|
||||
| --scale | float | 通道缩放 (例如: 1 或 1 1 1) |
|
||||
|
||||
输出
|
||||
|
||||
成功执行 load 后会打印 SUCESS 。在 model_path 目录下生成 ：
|
||||
|
||||
- 网络结构文件`*.json`
|
||||
- 网络权重`*.data`文件
|
||||
- 前处理配置文件`*_inputmeta.yml`
|
||||
- 后处理配置文件`*_postprocess_file.yml`
|
||||
|
||||
## quantize
|
||||
|
||||
描述：
|
||||
|
||||
使用 `quantize` 对模型进行量化，以提高在 Pnna 上的运行效率。量化操作可能会带来一定程度的精度损失。
|
||||
|
||||
用法：
|
||||
|
||||
```bash
|
||||
netrans quantize model_path quant_type [--pre] [--post]
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
| :----------------- | --- | -------------- |
|
||||
| model_path | str | 第一位置参数，模型文件的路径 |
|
||||
| quant_type | str | 第二位置参数，量化类型 |
|
||||
| --pre | action | 将前处理做进推理网络计算图 |
|
||||
| --post | action | 将后处理做进推理网络计算图 |
|
||||
|
||||
如果我们训练好的模型的数据类型是float32的，为了使模型以更高的效率在 PNNA 上运行，我们可以对模型进行量化操作，量化操作可能会带来一定程度的精度损失。
|
||||
|
||||
支持的量化类型有：
|
||||
- symi8: 对称量化算法，使用 int8 类型
|
||||
- asymu8: 非对称量化算法，使用 uint8 类型
|
||||
- symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
输出
|
||||
成功执行 quantize 后会打印 SUCCESS 。在 model_path 目录下生成量化后的模型文件 `*.quantize`。
|
||||
|
||||
## add_pre_post
|
||||
|
||||
描述：
|
||||
|
||||
使用 `add_pre_post` 将前后处理加入推理计算图，提升整体工程性能效率。
|
||||
|
||||
用法：
|
||||
|
||||
```bash
|
||||
netrans add_pre_post model_path quant_type
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
| :----------------- | --- | -------------- |
|
||||
| model_path | str | 第一位置参数，模型文件的路径 |
|
||||
| quant_type | str | 第二位置参数，量化类型 |
|
||||
|
||||
|
||||
quant_type 和 `quantize` 命令中的该参数保持一致。
|
||||
|
||||
输出
|
||||
成功执行 `add_pre_post` 后会打印 SUCCESS 。
|
||||
|
||||
## export
|
||||
|
||||
描述：
|
||||
|
||||
使用 `export` 导出模型生成 `nbg` 文件，以便在 PNNA 上部署和运行。
|
||||
|
||||
用法：
|
||||
|
||||
```bash
|
||||
netrans export model_path quant_type
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
| :---------- | --- | ---------------- |
|
||||
| model_path | str | 第一位置参数，模型文件的路径 |
|
||||
| quant_type | str | 第二位置参数，量化类型 |
|
||||
|
||||
支持的量化类型有：
|
||||
- symi8: 对称量化算法，使用 int8 类型
|
||||
- asymu8: 非对称量化算法，使用 uint8 类型
|
||||
- symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
输出
|
||||
成功执行 export 后会打印 SUCCESS 。在 model_path 目录下生成量化后的模型文件 `network_binary.nb`。
|
||||
|
||||
目前支持将生成的 network_binary.nb 文件部署到 PNNA 硬件平台。具体部署方法请参阅模型部署相关文档。
|
||||
|
||||
## 使用示例
|
||||
|
||||
请参照examples，examples 提供 [caffe 模型转换示例](./examples/caffe_model.md),[darknet 模型转换示例](./examples/darknet_model.md),[tensorflow 模型转换示例](./examples/tensorflow_model.md),[onnx 模型转换示例](./examples/onnx_model.md)。
|
||||
以 YOLOv8s 模型为例，演示使用 Netrans 命令行工具完成转换的全过程：
|
||||
|
||||
```bash
|
||||
# 1. 定义模型路径，模型路径默认为工作路径
|
||||
work_path='~/app/netrans/examples/infer_with_pre_post_process/yolov8s'
|
||||
cd ${work_path}
|
||||
|
||||
# 2. 激活环境
|
||||
mamba activate netrans
|
||||
|
||||
# 3. 模型导入
|
||||
netrans load ./ --mean 0 0 0 --scale 1 1 1
|
||||
|
||||
# 4. 模型量化
|
||||
netrans quantize ./ asymu8
|
||||
|
||||
# 5. 将前后处理加入推理网络
|
||||
netrans add_pre_post ./ asymu8
|
||||
|
||||
# 6. 导出 nbg 文件
|
||||
netrans export ./ asymu8
|
||||
```
|
||||
|
||||
请参照examples，examples 提供 [caffe 模型转换示例](../examples/caffe_model.md),[darknet 模型转换示例](../examples/darknet_model.md),[tensorflow 模型转换示例](../examples/tensorflow_model.md),[onnx 模型转换示例](../examples/onnx_model.md)。
|
||||
|
|
@ -1,177 +1,237 @@
|
|||
# netrans_py 使用
|
||||
# Netrans_py 使用
|
||||
|
||||
netrans_py 为 Netrans 编译器的 python 调用接口。
|
||||
使用 ntrans_py 完成模型转换的步骤如下：
|
||||
Netrans_py 是针对 PNNA 芯片的模型处理工具的 Python 调用接口，用于将模型权重转换成在 PNNA 芯片上运行的 nbg（network binary graph）格式（.nb 为后缀），nbg 文件可用于后续模型部署和推理工程的交叉编译。
|
||||
|
||||
1. 导入模型
|
||||
2. 生成并修改前处理配置文件 *_inputmeta.yml
|
||||
使用 Netrans_py 完成模型转换的步骤如下：
|
||||
|
||||
1. 初始化 Netrans
|
||||
2. 导入模型并配置预处理参数
|
||||
3. 量化模型
|
||||
4. 导出模型
|
||||
4. 前后处理加入推理计算图
|
||||
5. 导出模型
|
||||
|
||||
## 系统依赖
|
||||
|
||||
- CPU ： Intel® Core™ i5-6500 CPU @ 3.2 GHz x4 支持 the Intel® Advanced Vector Extensions.
|
||||
- RAM ： 至少8GB
|
||||
- 硬盘 ： 160GB
|
||||
- 操作系统 ： Ubuntu 20.04 LTS 64-bit with Python 3.10，不推荐使用其他版本
|
||||
|
||||
## 安装 Netrans_py
|
||||
|
||||
建议使用 mamba 作为环境隔离管理工具，避免安装 Netrans 导致污染系统环境。安装并激活 mamba 步骤如下：
|
||||
|
||||
```bash
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.8 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
# 安装 Netrans 及 依赖
|
||||
pip install bin/netrans-6.42.3-cp310-none-manylinux2010_x86_64.whl
|
||||
pip install -r requirements_py3.10.txt
|
||||
```
|
||||
|
||||
## 模型准备
|
||||
|
||||
不同框架下训练的模型需要准备不同的数据，所有的数据都需要与模型放在同一个文件夹下。具体参照 example 中不同框架的示例说明。
|
||||
如 ONNX 格式保存的 yolov8s 模型，目录结构如下：
|
||||
|
||||
```
|
||||
yolov4_tiny/
|
||||
├── channel_mean_value.txt # 定义预处理中 mean & scale 的配置参数
|
||||
├── dataset.txt # 定义量化数据的文件
|
||||
├── input_image
|
||||
│ ├── 0.jpg
|
||||
│ ├── 1.jpg
|
||||
│ ├── 2.jpg
|
||||
│ ├── 3.jpg
|
||||
│ ├── 4.jpg
|
||||
│ ├── 5.jpg
|
||||
│ ├── 6.jpg
|
||||
│ ├── 7.jpg
|
||||
│ ├── 8.jpg
|
||||
│ └── 9.jpg
|
||||
├── yolov4_tiny.cfg # 模型结构
|
||||
└── yolov4_tiny.weights # 模型权重
|
||||
```
|
||||
|
||||
|
||||
## Netrans 类
|
||||
|
||||
创建 Netrans
|
||||
### 创建 Netrans
|
||||
|
||||
描述： 实例化 Netrans 类。
|
||||
代码示例：
|
||||
**描述**：实例化 Netrans 类。
|
||||
|
||||
```py3
|
||||
from netrans import Netrans
|
||||
yolo_netrans = Netrans("../examples/darknet/yolov4_tiny")
|
||||
```
|
||||
**代码示例**：
|
||||
|
||||
参数
|
||||
```python
|
||||
from netrans import Netrans
|
||||
yolo_netrans = Netrans()
|
||||
```
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|model_path| str| 第一位置参数，模型文件的路径|
|
||||
|netrans| str | 如果 NETRANS_PATH 没有设置，可通过该参数指定netrans的路径|
|
||||
**参数**
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---|:---|:---|
|
||||
| 无 | 无 | 无 |
|
||||
|
||||
<!-- <font color="#dd0000">注意：</font> 模型目录准备需要和netrans_cli一致，具体数据准备要求见[introduction](./introduction.md)。 -->
|
||||
**输出返回**：无。
|
||||
|
||||
## Netrans.load 模型导入
|
||||
|
||||
描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：
|
||||
**描述**：导入模型并配置预处理参数，将模型转换成 PNNA 支持的格式。
|
||||
|
||||
```py3
|
||||
yolo_netrans.load()
|
||||
```
|
||||
**代码示例**：
|
||||
|
||||
参数：
|
||||
无。
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
在工程目录下生成 Pnna 支持的模型格式，以.json结尾的模型文件和 .data结尾的权重文件。
|
||||
|
||||
## Netrans.config 预处理配置文件生成
|
||||
|
||||
描述： 将模型转换成 Pnna 支持的格式。
|
||||
代码示例：
|
||||
|
||||
```py3
|
||||
# 没有直接可用的 inputmeta,需要生成.
|
||||
yolo_netrans.config()
|
||||
# 指定复用的 inputmeta.
|
||||
yolo_netrans.config(inputmeta="../examples/darknet/yolov4_tiny/yolov4_tiny_inputmeta.yml")
|
||||
# 指定预处理参数 mean 和 scale. 支持 int, float 和 list.
|
||||
yolo_netrans.config(mean=128, scale = 0.0039)
|
||||
# 需要对数据分通道进行normlize, menas为128,127,125,scale 为 0.0039, 且reverse_channel 为 True
|
||||
yolo_netrans.config(mean=[128, 127, 125], scale = 0.0039, reverse_channel= True)
|
||||
```
|
||||
|
||||
参数：
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
```python
|
||||
model_path = '../examples/darknet/yolov4_tiny'
|
||||
# 导入 model_path 下的模型，并配置参 mean 为 129，scale 为 1
|
||||
yolo_netrans.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
# 导入 model_path 下的模型，并配置参 mean 为 129，scale 为 1
|
||||
yolo_netrans.load(model_path, mean=[128, 128, 128], scale=[1])
|
||||
```
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
**参数**
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---|:---|:---|
|
||||
| model_path | str | 模型目录路径 |
|
||||
| mean | None，list, tuple | 通道均值，可以是单个数字或数字列表/元组，列表/元组长度和输入的通道数保持一致。默认为 None |
|
||||
| scale | None，list, tuple | 通道缩放比例，可以是单个数字或数字列表/元组，列表/元组长度和输入的通道数保持一致。默认为 None |
|
||||
|
||||
**输出返回**：无。
|
||||
|
||||
**注意**：在工程目录下生成 PNNA 支持的模型格式，以.json结尾的模型文件和 .data结尾的权重文件。
|
||||
|
||||
## Netrans.quantize 模型量化
|
||||
|
||||
描述： 对模型生成量化配置文件。
|
||||
代码示例：
|
||||
**描述**：对模型进行量化。
|
||||
|
||||
```py3
|
||||
yolo_netrans.quantize("uint8")
|
||||
**代码示例**：
|
||||
|
||||
```python
|
||||
yolo_netrans.quantize('asymu8')
|
||||
```
|
||||
|
||||
参数：
|
||||
**参数**
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str| 第一位置参数，模型量化类型，仅支持 "uint8", "int8", "int16"|
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---|:---|:---|
|
||||
| quantized | str | 量化类型 |
|
||||
| model_path | str | 模型目录路径（可选），如果传入且与当前已加载目录不一致，则重新加载模型 |
|
||||
<!-- | algorithm | int | 量化算法，取值范围为 0~3，默认为 1 |
|
||||
| iterations | int | 迭代次数，默认为 1 |
|
||||
| entropy | bool | 是否计算张量熵，默认为 False |
|
||||
| mle | bool | 是否最小化逐层误差，默认为 False |
|
||||
| lid | str | 输入/输出层名 JSON 文件路径，默认为 None |
|
||||
| in_out_quantized | str | 输入/输出量化类型 JSON 文件，默认为 None |
|
||||
| quantize_file | str | 若 is_qat 为 True，则必须给出量化文件路径，默认为 None | -->
|
||||
| pre | bool | 是否将前处理做进推理网络计算图，默认为 False |
|
||||
| post | bool | 是否将后处理做进推理网络计算图，默认为 False |
|
||||
|
||||
支持的量化类型有：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
**输出返回**：无。
|
||||
|
||||
## Netrans.add_pre_post 前后处理加入推理计算图
|
||||
|
||||
**描述**：配置将前后处理做进推理网络计算图。
|
||||
|
||||
**代码示例**：
|
||||
|
||||
```python
|
||||
yolo_netrans.add_pre_post('asymu8')
|
||||
```
|
||||
|
||||
输出返回：
|
||||
无。
|
||||
**参数**
|
||||
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---|:---|:---|
|
||||
| quantized | str | 量化类型 |
|
||||
| model_path | str | 模型目录路径（可选），如果传入且与当前已加载目录不一致，则重新加载模型 |
|
||||
| pre | bool | 是否将前处理做进推理网络计算图，默认为 True |
|
||||
| post | bool | 是否将后处理做进推理网络计算图，默认为 True |
|
||||
|
||||
支持的量化类型有：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
**输出返回**：无。
|
||||
|
||||
## Netrans.export 模型导出
|
||||
|
||||
描述： 对模型生成量化配置文件。
|
||||
代码示例：
|
||||
**描述**：将量化后的模型导出为 nbg 文件。
|
||||
|
||||
```py3
|
||||
yolo_netrans.export()
|
||||
**代码示例**：
|
||||
|
||||
```python
|
||||
yolo_netrans.export('asymu8')
|
||||
```
|
||||
|
||||
参数：
|
||||
quantize_type (可选): 定义导出的量化类型, 默认和 quantize() 一致.
|
||||
**参数**
|
||||
|
||||
输出返回：
|
||||
无。请在目录 “wksp/*/” 下检查是否生成nbg文件。
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---|:---|:---|
|
||||
| quantized | str | 量化类型，默认为 "float32" |
|
||||
| model_path | str | 模型目录路径（可选），如果传入且与当前已加载目录不一致，则重新加载模型 |
|
||||
|
||||
## Netrans.model2nbg 模型生成nbg文件
|
||||
支持的量化类型有：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
描述： 模型导入、量化、及nbg文件生产
|
||||
代码示例：
|
||||
**输出返回**：无。
|
||||
|
||||
```py3
|
||||
# 无预处理
|
||||
yolo_netrans.model2nbg(quantize_type='uint8')
|
||||
# 需要对数据进行normlize, menas为128, scale 为 0.0039
|
||||
yolo_netrans.model2nbg(quantize_type='uint8',mean=128, scale = 0.0039)
|
||||
# 需要对数据分通道进行normlize, menas为128,127,125,scale 为 0.0039, 且reverse_channel 为 True
|
||||
yolo_netrans.model2nbg(quantize_type='uint8',mean=[128, 127, 125], scale = 0.0039, reverse_channel= True)
|
||||
# 已经进行初始化设置
|
||||
yolo_netrans.model2nbg(quantize_type='uint8', inputmeta=True)
|
||||
|
||||
```
|
||||
|
||||
参数
|
||||
|
||||
```{table}
|
||||
:widths: 20, 30, 50
|
||||
:align: left
|
||||
| 参数名 | 类型 | 说明 |
|
||||
|:---| -- | -- |
|
||||
|quantize_type| str, ["uint8", "int8", "int16" ] | 量化类型，将模型量化成该参数指定的类型 |
|
||||
|inputmeta| bool,str, [Fasle, True, "inputmeta_filepath"] | 指定 inputmeta, 默认为False。 <br/> 如果为False，则会生成inputmeta模板，可使用mean、scale、reverse_channel 配合修改常用参数。<br/>如果已有现成的 inputmeta 文件，则可通过该参数进行指定，也可使用True, 则会自动索引 model_name_inputmeta.yml |
|
||||
|mean| float, int, list | 设置预处理中 normalize 的 mean 参数 |
|
||||
|scale| float, int, list | 设置预处理中 normalize 的 scale 参数 |
|
||||
|reverse_channel | bool | 设置预处理中的 reverse_channel 参数 |
|
||||
```
|
||||
|
||||
输出返回：
|
||||
请在目录 “wksp/*/” 下检查是否生成nbg文件。
|
||||
**注意**：请在目录 “wksp/*/” 下检查是否生成 nbg 文件。
|
||||
|
||||
## 使用示例
|
||||
|
||||
```py3
|
||||
from nertans import Netrans
|
||||
model_path = 'example/darknet/yolov4_tiny'
|
||||
netrans_path = "netrans/bin" # 如果进行了export定义申明，这一步可以不用
|
||||
```python
|
||||
from netrans import Netrans
|
||||
|
||||
# 初始化 Netrans
|
||||
model_path = '../examples/darknet/yolov4_tiny'
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 初始化netrans
|
||||
net = Netrans(model_path,netrans=netrans_path)
|
||||
# 模型载入
|
||||
net.load()
|
||||
# 配置预处理 normlize 的参数
|
||||
net.config(scale=1,mean=0)
|
||||
# 模型量化
|
||||
net.quantize("uint8")
|
||||
# 模型导出
|
||||
net.export()
|
||||
net.quantize('asymu8')
|
||||
|
||||
# 模型直接量化成 int16 并导出, 直接复用刚配置好的 inputmeta
|
||||
net.model2nbg(quantize_type = "int16", inputmeta=True)
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post('asymu8')
|
||||
|
||||
# 模型导出
|
||||
net.export('asymu8')
|
||||
```
|
||||
|
||||
------
|
||||
> *作者 {{xujiao}}*
|
||||
*作者：{{xujiao}}*
|
||||
|
|
@ -1,160 +0,0 @@
|
|||
# 快速入门
|
||||
|
||||
本文档以 onnx 格式的 yolov5s 为例，演示如何快速安装Nertans 并使用 Netrans 量化、编译模型并生成 nbg 文件。
|
||||
|
||||
## 系统环境
|
||||
|
||||
- Linux操作系统，推荐 Ubuntu 20.04 或 Debian12
|
||||
- Python 3.8
|
||||
- RAM 至少 8GB
|
||||
|
||||
## 安装Netrans
|
||||
|
||||
创建 python3.8 环境
|
||||
|
||||
```bash
|
||||
wget "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"
|
||||
mkdir -p ~/app
|
||||
INSTALL_PATH="${HOME}/app/miniforge3"
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${INSTALL_PATH}
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/conda.sh"" >> ${HOME}/.bashrc
|
||||
echo "source "${INSTALL_PATH}/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
source ${HOME}/.bashrc
|
||||
mamba create -n netrans python=3.8 -y
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
配置 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
```
|
||||
|
||||
## 使用 Netrans 编译 yolov5s 模型
|
||||
|
||||
进入工作目录
|
||||
|
||||
```bash
|
||||
cd ～/app/netrans/examples/onnx
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
||||
```text
|
||||
onnx/
|
||||
├── README.md
|
||||
└── yolov5s
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
### 使用 netrans_cli 编译 yolov5s
|
||||
|
||||
#### 导入模型
|
||||
|
||||
```bash
|
||||
load.sh yolov5s
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
|
||||
此时 yolov5s 的目录结构如下
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── yolov5s.data
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
#### 生成配置文件模板
|
||||
|
||||
配置文件定义输入数据前处理相关参数。Netrans预定义了配置文件模板生成脚本，用户需根据模型前处理参数对配置文件进行修改。
|
||||
|
||||
```bash
|
||||
config.sh yolov5s
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
|
||||
```
|
||||
|
||||
根据 yolov5s 的前处理参数 ，修改 yml 中的 scale 为 0.003921568627。
|
||||
打开 ` yolov5s_inputmeta.yml ` 文件，修改第30-33行：
|
||||
|
||||
```text
|
||||
scale:
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
```
|
||||
|
||||
#### 量化模型
|
||||
|
||||
生成 unit8 量化的量化参数文件
|
||||
|
||||
```bash
|
||||
quantize.sh yolov5s uint8
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
#### 导出模型
|
||||
|
||||
导出 unit8 量化的模型项目工程
|
||||
|
||||
```bash
|
||||
export.sh yolov5s uint8
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```text
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ └── asymmetric_affine
|
||||
│ └── network_binary.nb
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
### 使用 netrans_py 编译 yolov5s 模型
|
||||
|
||||
```bash
|
||||
example.py yolov5s -q uint8 -m 0 -s 0.003921568627
|
||||
```
|
||||
|
|
@ -1,43 +1,68 @@
|
|||
# Caffe模型转换示例
|
||||
# Caffe 模型转换示例
|
||||
|
||||
本文档以 lenet_caffe 为例，介绍如何使用 Netrans 对 Caffe 模型进行转换。
|
||||
本文档以 `lenet_caffe` 为例，介绍如何使用 Netrans 对 Caffe 模型进行转换。
|
||||
|
||||
Netrans 支持所有的 Caffe 模型。
|
||||
|
||||
## 安装Netrans
|
||||
创建 conda 环境 .
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
```bash
|
||||
conda create -n netrans python=3.8 -y
|
||||
conda activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans .
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
mkdir -p ~/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
安装 Netrans。
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
## 数据准备
|
||||
转换 Caffe 模型时，模型工程目录应包含以下文件：
|
||||
- 以 .prototxt 结尾的模型结构定义文件
|
||||
- 以 .caffemode 结尾的模型权重文件
|
||||
- dataset.txt 包含数据路径的文本文件（支持图像和NPY格式）
|
||||
|
||||
我们的示例 已经完成数据准备，可以使用下面命令进入目录执行。
|
||||
转换 Caffe 模型时，模型工程目录应包含以下文件：
|
||||
|
||||
- 以 `.prototxt` 结尾的模型结构定义文件
|
||||
- 以 `.caffemodel` 结尾的模型权重文件
|
||||
- `dataset.txt` 包含数据路径的文本文件（支持图像和 NPY 格式）
|
||||
|
||||
我们的示例已经完成数据准备，可以使用以下命令进入目录执行。
|
||||
|
||||
```bash
|
||||
cd netrans/
|
||||
cd examples/caffe
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg # 校准数据
|
||||
|
|
@ -45,32 +70,19 @@ lenet_caffe/
|
|||
├── lenet_caffe.caffemodel # caffe 模型权重
|
||||
└── lenet_caffe.prototxt # caffe 模型结构
|
||||
```
|
||||
## 使用 nertans_cli 命令行工具
|
||||
|
||||
## 使用 Netrans_cli 命令行工具
|
||||
|
||||
### 模型导入
|
||||
```bash
|
||||
import.sh lenet_caffe
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 lenet_caffe 的目录结构如下：
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── lenet_caffe.caffemodel
|
||||
├── lenet_caffe.data
|
||||
├── lenet_caffe.json
|
||||
└── lenet_caffe.prototxt
|
||||
```
|
||||
|
||||
### 配置文件生成
|
||||
数据在推理前一般会经过预处理，为了确保模型可以正确的输入数据，需要生产对应的配置文件。
|
||||
|
||||
```bash
|
||||
config.sh lenet_caffe
|
||||
load lenet_caffe
|
||||
```
|
||||
|
||||
此时 lenet_caffe 的目录结构如下：
|
||||
该命令会在工程目录下生成包含模型信息的 `.json` 和 `.data` 数据文件。
|
||||
|
||||
此时 `lenet_caffe` 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg
|
||||
|
|
@ -79,68 +91,144 @@ lenet_caffe/
|
|||
├── lenet_caffe.data
|
||||
├── lenet_caffe_inputmeta.yml
|
||||
├── lenet_caffe.json
|
||||
├── lenet_caffe_postprocess_file.yml
|
||||
└── lenet_caffe.prototxt
|
||||
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
为了优化模型的推理效率，加快模型的推理速度，我们使用下行命令对模型进行量化处理。
|
||||
量化模型需要两个参数，目录（模型）名字和量化类型。量化类型包括：float,int16, int8 和 uint8。
|
||||
### 模型量化
|
||||
|
||||
为了优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
```bash
|
||||
quantize.sh lenet_caffe uint8
|
||||
|
||||
quantize lenet_caffe asymu8
|
||||
```
|
||||
|
||||
此时 lenet_caffe 的目录结构如下：
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── lenet_caffe_asymmetric_affine.quantize
|
||||
├── lenet_caffe.caffemodel
|
||||
├── lenet_caffe.data
|
||||
├── lenet_caffe_inputmeta.yml
|
||||
├── lenet_caffe.json
|
||||
└── lenet_caffe.prototxt
|
||||
```
|
||||
## 模型导出
|
||||
使用 export.sh 将模型导出到nbg格式并生成应用程序工程。
|
||||
```bash
|
||||
export.sh lenet_caffe uint8
|
||||
```
|
||||
此时 lenet_caffe 的目录结构如下：
|
||||
此时 `lenet_caffe` 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── lenet_caffe_asymmetric_affine.quantize
|
||||
├── lenet_caffe_asymu8.quantize
|
||||
├── lenet_caffe.caffemodel
|
||||
├── lenet_caffe.data
|
||||
├── lenet_caffe_inputmeta.yml
|
||||
├── lenet_caffe.json
|
||||
├── lenet_caffe_postprocess_file.yml
|
||||
└── lenet_caffe.prototxt
|
||||
```
|
||||
|
||||
### 前后处理加入推理计算图
|
||||
|
||||
将前后处理加入推理计算图，提升整体工程性能效率。
|
||||
|
||||
```bash
|
||||
add_pre_post lenet_caffe asymu8 --preprocess --postprocess
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export lenet_caffe asymu8
|
||||
```
|
||||
|
||||
此时 `lenet_caffe` 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet_caffe/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── lenet_caffe_asymu8.quantize
|
||||
├── lenet_caffe.caffemodel
|
||||
├── lenet_caffe.data
|
||||
├── lenet_caffe_inputmeta.yml
|
||||
├── lenet_caffe.json
|
||||
├── lenet_caffe_postprocess_file.yml
|
||||
├── lenet_caffe.prototxt
|
||||
└── wksp
|
||||
└── asymmetric_affine
|
||||
├── lenet_caffe_asymu8
|
||||
│ ├── analysis.json
|
||||
│ ├── BUILD
|
||||
│ ├── dump_core_graph.json
|
||||
│ ├── graph.json
|
||||
│ ├── lenetcaffeasymu8.2012.vcxproj
|
||||
│ ├── lenet_caffe_asymu8.export.data
|
||||
│ ├── lenetcaffeasymu8.vcxproj
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_lenetcaffeasymu8.c
|
||||
│ ├── vnn_lenetcaffeasymu8.h
|
||||
│ ├── vnn_lenetcaffeasymu8_tensor.c
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ └── vnn_pre_process.h
|
||||
└── lenet_caffe_asymu8_nbg_unify
|
||||
├── BUILD
|
||||
├── dump_core_graph.json
|
||||
├── graph.json
|
||||
├── lenetcaffeasymmetricaffine.2012.vcxproj
|
||||
├── lenet_caffe_asymmetric_affine.export.data
|
||||
├── lenetcaffeasymmetricaffine.vcxproj
|
||||
├── cmd.sh
|
||||
├── lenetcaffeasymu8.2012.vcxproj
|
||||
├── lenetcaffeasymu8.vcxproj
|
||||
├── main.c
|
||||
├── makefile.linux
|
||||
├── nbg_meta.json
|
||||
├── network_binary.nb
|
||||
├── vnn_global.h
|
||||
├── vnn_lenetcaffeasymmetricaffine.c
|
||||
├── vnn_lenetcaffeasymmetricaffine.h
|
||||
├── vnn_lenetcaffeasymu8.c
|
||||
├── vnn_lenetcaffeasymu8.h
|
||||
├── vnn_lenetcaffeasymu8_tensor.c
|
||||
├── vnn_post_process.c
|
||||
├── vnn_post_process.h
|
||||
├── vnn_pre_process.c
|
||||
└── vnn_pre_process.h
|
||||
```
|
||||
## 使用 netrans_py python api
|
||||
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
example.py lenet_caffe -q uint8
|
||||
python example.py lenet_caffe -q asymu8
|
||||
```
|
||||
|
||||
|
||||
*作者：{{xujiao}}*
|
||||
|
|
@ -4,27 +4,48 @@
|
|||
|
||||
Netrans 支持 Darknet[官网](https://pjreddie.com/darknet/)列出 darknet 模型
|
||||
|
||||
## 安装Netrans
|
||||
创建 conda 环境 .
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
```bash
|
||||
conda create -n netrans python=3.8 -y
|
||||
conda activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans .
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
mkdir -p ~/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
安装 Netrans。
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
## 数据准备
|
||||
|
||||
转换 Darknet 模型时，模型工程目录应包含以下文件：
|
||||
- .cfg 文件：网络结构配置文件
|
||||
- .weights 文件：训练权重文件
|
||||
|
|
@ -35,6 +56,8 @@ cd ~/app/netrans
|
|||
```bash
|
||||
cd netrans/
|
||||
cd examples/darknet
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
|
@ -45,32 +68,18 @@ yolov4_tiny/
|
|||
├── yolov4_tiny.cfg # 网络结构配置文件
|
||||
└── yolov4_tiny.weights # 预训练权重文件
|
||||
```
|
||||
|
||||
## 使用 nertans_cli 命令行工具
|
||||
|
||||
### 模型导入
|
||||
|
||||
```bash
|
||||
import.sh yolov4_tiny
|
||||
load yolov4_tiny
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 yolov4_tiny 的目录结构如下：
|
||||
```bash
|
||||
yolov4_tiny/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov4_tiny.cfg
|
||||
├── yolov4_tiny.data
|
||||
├── yolov4_tiny.json
|
||||
└── yolov4_tiny.weights
|
||||
```
|
||||
|
||||
### 配置文件生成
|
||||
数据在推理前一般会经过预处理，为了确保模型可以正确的输入数据，需要生产对应的配置文件。
|
||||
|
||||
```bash
|
||||
config.sh yolov4_tiny
|
||||
```
|
||||
|
||||
此时 yolov4_tiny 的目录结构如下：
|
||||
```bash
|
||||
yolov4_tiny/
|
||||
├── 0.jpg
|
||||
|
|
@ -79,67 +88,143 @@ yolov4_tiny/
|
|||
├── yolov4_tiny.data
|
||||
├── yolov4_tiny_inputmeta.yml
|
||||
├── yolov4_tiny.json
|
||||
├── yolov4_tiny_postprocess_file.yml
|
||||
└── yolov4_tiny.weights
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
|
||||
|
||||
量化处理可优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
|
||||
```bash
|
||||
quantize.sh yolov4_tiny uint8
|
||||
quantize yolov4_tiny asymu8
|
||||
|
||||
```
|
||||
|
||||
此时 yolov4_tiny 的目录结构如下：
|
||||
|
||||
```bash
|
||||
yolov4_tiny/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov4_tiny_asymmetric_affine.quantize
|
||||
├── yolov4_tiny_asymu8.quantize
|
||||
├── yolov4_tiny.cfg
|
||||
├── yolov4_tiny.data
|
||||
├── yolov4_tiny_inputmeta.yml
|
||||
├── yolov4_tiny.json
|
||||
├── yolov4_tiny_postprocess_file.yml
|
||||
└── yolov4_tiny.weights
|
||||
```
|
||||
### 模型导出
|
||||
使用 export.sh 将模型导出到nbg格式并生成应用程序工程。
|
||||
|
||||
|
||||
### 前后处理加入推理计算图
|
||||
|
||||
将前后处理加入推理计算图，提升整体工程性能效率。
|
||||
|
||||
```bash
|
||||
export.sh yolov4_tiny uint8
|
||||
add_pre_post yolov4_tiny asymu8 --preprocess --postprocess
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export yolov4_tiny asymu8
|
||||
```
|
||||
此时 yolov4_tiny 的目录结构如下：
|
||||
|
||||
```bash
|
||||
yolov4_tiny/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── yolov4_tiny_asymmetric_affine.quantize
|
||||
├── wksp
|
||||
│ ├── yolov4_tiny_asymu8
|
||||
│ │ ├── analysis.json
|
||||
│ │ ├── BUILD
|
||||
│ │ ├── dump_core_graph.json
|
||||
│ │ ├── graph.json
|
||||
│ │ ├── main.c
|
||||
│ │ ├── makefile.linux
|
||||
│ │ ├── vnn_global.h
|
||||
│ │ ├── vnn_post_process.c
|
||||
│ │ ├── vnn_post_process.h
|
||||
│ │ ├── vnn_pre_process.c
|
||||
│ │ ├── vnn_pre_process.h
|
||||
│ │ ├── vnn_yolov4tinyasymu8.c
|
||||
│ │ ├── vnn_yolov4tinyasymu8.h
|
||||
│ │ ├── vnn_yolov4tinyasymu8_tensor.c
|
||||
│ │ ├── yolov4tinyasymu8.2012.vcxproj
|
||||
│ │ ├── yolov4_tiny_asymu8.export.data
|
||||
│ │ └── yolov4tinyasymu8.vcxproj
|
||||
│ └── yolov4_tiny_asymu8_nbg_unify
|
||||
│ ├── BUILD
|
||||
│ ├── cmd.sh
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── nbg_meta.json
|
||||
│ ├── network_binary.nb
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ ├── vnn_pre_process.h
|
||||
│ ├── vnn_yolov4tinyasymu8.c
|
||||
│ ├── vnn_yolov4tinyasymu8.h
|
||||
│ ├── vnn_yolov4tinyasymu8_tensor.c
|
||||
│ ├── yolov4tinyasymu8.2012.vcxproj
|
||||
│ └── yolov4tinyasymu8.vcxproj
|
||||
├── yolov4_tiny_asymu8.quantize
|
||||
├── yolov4_tiny.cfg
|
||||
├── yolov4_tiny.data
|
||||
├── yolov4_tiny_inputmeta.yml
|
||||
├── yolov4_tiny.json
|
||||
├── yolov4_tiny.weights
|
||||
└── wksp
|
||||
└── asymmetric_affine
|
||||
├── BUILD
|
||||
├── dump_core_graph.json
|
||||
├── graph.json
|
||||
├── yolov4_tinyasymmetricaffine.2012.vcxproj
|
||||
├── yolov4_tiny_asymmetric_affine.export.data
|
||||
├── yolov4_tinyasymmetricaffine.vcxproj
|
||||
├── main.c
|
||||
├── makefile.linux
|
||||
├── network_binary.nb
|
||||
├── vnn_global.h
|
||||
├── vnn_yolov4_tinyasymmetricaffine.c
|
||||
├── vnn_yolov4_tinyasymmetricaffine.h
|
||||
├── vnn_post_process.c
|
||||
├── vnn_post_process.h
|
||||
├── vnn_pre_process.c
|
||||
└── vnn_pre_process.h
|
||||
├── yolov4_tiny_postprocess_file.yml
|
||||
└── yolov4_tiny.weights
|
||||
```
|
||||
## 使用 netrans_py python api
|
||||
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
example.py yolov4_tiny -q uint8
|
||||
python example.py yolov4_tiny -q asymu8
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,218 @@
|
|||
# 模型转换
|
||||
|
||||
本文档以 yolov8s 为例，介绍使用 Netrans 对模型进行转换时在推理计算图中添加前/后处理节点。
|
||||
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
```bash
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
## 数据准备
|
||||
|
||||
示例使用 ONNX 格式的 yolov8s 模型，已经完成数据准备，可以使用下面命令进入目录执行。
|
||||
|
||||
```bash
|
||||
cd netrans/
|
||||
cd examples/infer_with_pre_post_process
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
```bash
|
||||
yolov8s/
|
||||
└── yolov8s.onnx
|
||||
```
|
||||
|
||||
## 使用 nertans_cli 命令行工具
|
||||
|
||||
### 模型导入
|
||||
|
||||
```bash
|
||||
load yolov8s
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 yolov8s 的目录结构如下：
|
||||
|
||||
```bash
|
||||
yolov8s/
|
||||
├── inputs # 未定义量化校准数据会随机生成一个npy文件作为输入
|
||||
│ └── images_238_1_3_640_640_0.npy
|
||||
├── yolov8s.data
|
||||
├── yolov8s_inputmeta.yml
|
||||
├── yolov8s.json
|
||||
├── yolov8s.onnx
|
||||
└── yolov8s_postprocess_file.yml
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
|
||||
量化处理可优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
|
||||
```bash
|
||||
quantize yolov8s asymu8
|
||||
|
||||
```
|
||||
|
||||
此时 yolov8s 的目录结构如下：
|
||||
|
||||
```bash
|
||||
yolov8s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov8s_asymu8.quantize
|
||||
├── yolov8s.cfg
|
||||
├── yolov8s.data
|
||||
├── yolov8s_inputmeta.yml
|
||||
├── yolov8s.json
|
||||
├── yolov8s_postprocess_file.yml
|
||||
└── yolov8s.weights
|
||||
```
|
||||
|
||||
|
||||
### 前后处理加入推理计算图
|
||||
|
||||
将前后处理加入推理计算图，提升整体工程性能效率。
|
||||
|
||||
```bash
|
||||
add_pre_post yolov8s asymu8 --preprocess --postprocess
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export yolov8s asymu8
|
||||
```
|
||||
此时 yolov8s 的目录结构如下：
|
||||
|
||||
```bash
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ ├── yolov8s_asymu8
|
||||
│ │ ├── analysis.json
|
||||
│ │ ├── BUILD
|
||||
│ │ ├── dump_core_graph.json
|
||||
│ │ ├── graph.json
|
||||
│ │ ├── main.c
|
||||
│ │ ├── makefile.linux
|
||||
│ │ ├── vnn_global.h
|
||||
│ │ ├── vnn_post_process.c
|
||||
│ │ ├── vnn_post_process.h
|
||||
│ │ ├── vnn_pre_process.c
|
||||
│ │ ├── vnn_pre_process.h
|
||||
│ │ ├── vnn_yolov4tinyasymu8.c
|
||||
│ │ ├── vnn_yolov4tinyasymu8.h
|
||||
│ │ ├── vnn_yolov4tinyasymu8_tensor.c
|
||||
│ │ ├── yolov4tinyasymu8.2012.vcxproj
|
||||
│ │ ├── yolov8s_asymu8.export.data
|
||||
│ │ └── yolov4tinyasymu8.vcxproj
|
||||
│ └── yolov8s_asymu8_nbg_unify
|
||||
│ ├── BUILD
|
||||
│ ├── cmd.sh
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── nbg_meta.json
|
||||
│ ├── network_binary.nb
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ ├── vnn_pre_process.h
|
||||
│ ├── vnn_yolov4tinyasymu8.c
|
||||
│ ├── vnn_yolov4tinyasymu8.h
|
||||
│ ├── vnn_yolov4tinyasymu8_tensor.c
|
||||
│ ├── yolov4tinyasymu8.2012.vcxproj
|
||||
│ └── yolov4tinyasymu8.vcxproj
|
||||
├── yolov8s_asymu8.quantize
|
||||
├── yolov8s.cfg
|
||||
├── yolov8s.data
|
||||
├── yolov8s_inputmeta.yml
|
||||
├── yolov8s.json
|
||||
├── yolov8s_postprocess_file.yml
|
||||
└── yolov8s.weights
|
||||
```
|
||||
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
python example.py yolov8s -q asymu8
|
||||
```
|
||||
|
||||
Binary file not shown.
|
|
@ -3,26 +3,45 @@
|
|||
|
||||
Netrans 支持 ONNX 至 1.14.0， opset支持至19。
|
||||
|
||||
## 安装Netrans
|
||||
创建 conda 环境 .
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
```bash
|
||||
conda create -n netrans python=3.8 -y
|
||||
conda activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans .
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
mkdir -p ~/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
安装 Netrans。
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
```
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
## 数据准备
|
||||
|
||||
转换ONNX模型需准备：
|
||||
|
|
@ -35,54 +54,36 @@ cd ~/app/netrans
|
|||
```bash
|
||||
cd netrans/
|
||||
cd examples/onnx
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
||||
```
|
||||
yolov5s/
|
||||
├── 0.jpg # 校准数据
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
└── yolov5s.onnx # 网络模型
|
||||
├── 0.jpg # 校准数据
|
||||
├── channel_mean_value.txt # 预处理参数配置文件
|
||||
├── dataset.txt # 指定数据地址的文件
|
||||
└── yolov5s.onnx # 网络模型
|
||||
```
|
||||
|
||||
### 3.1 使用 netrans_cli 转换 onnx 示例模型 yolov5s
|
||||
## 使用 Netrans_cli 命令行工具
|
||||
|
||||
示例目录如下：
|
||||
### 模型导入
|
||||
|
||||
```
|
||||
onnx/
|
||||
└── yolov5s
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
yolov5s 需要定义前处理 normalize 的参数. 创建 channel_mean_value.txt，写入输入的均值与缩放因子。
|
||||
依次填写每个通道的均值，再填写一个统一缩放值或各通道独立缩放值.具体的
|
||||
|
||||
#### 3.1.1 导入模型
|
||||
|
||||
```bash
|
||||
import.sh yolov5s
|
||||
echo 0 0 0 0.003921568627451 > yolov5s/channel_mean_value.txt
|
||||
load yolov5s
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 yolov5s 的目录结构如下
|
||||
```
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── yolov5s.data
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
```
|
||||
|
||||
#### 3.1.2 生成配置文件
|
||||
数据在推理前一般会经过预处理，为了确保模型可以正确的输入数据，需要生产对应的配置文件。
|
||||
|
||||
```bash
|
||||
config.sh yolov5s
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
```
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
|
|
@ -90,79 +91,142 @@ yolov5s/
|
|||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
|
||||
```
|
||||
根据 yolov5s 的实际情况 ，我们需要修改yml中的 mean 为 0，scale为 0.003921568627。
|
||||
打开 ` yolov5s_inputmeta.yml ` 文件，
|
||||
修改第30-33行为：
|
||||
```
|
||||
scale:
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
|
||||
├── yolov5s.onnx
|
||||
└── yolov5s_postprocess_file.yml
|
||||
```
|
||||
|
||||
#### 3.1.3 量化模型
|
||||
### 模型量化
|
||||
|
||||
量化处理可优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
```bash
|
||||
quantize.sh yolov5s uint8
|
||||
quantize yolov5s asymu8
|
||||
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
此时 yolov8s 的目录结构如下：
|
||||
|
||||
```
|
||||
```bash
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── channel_mean_value.txt
|
||||
├── dataset.txt
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
├── yolov5s_asymu8.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
├── yolov5s.onnx
|
||||
└── yolov5s_postprocess_file.yml
|
||||
```
|
||||
|
||||
#### 3.1.4 导出模型
|
||||
### 前后处理加入推理计算图
|
||||
|
||||
将前后处理加入推理计算图，提升整体工程性能效率。
|
||||
|
||||
```bash
|
||||
./export.sh yolov5s uint8
|
||||
add_pre_post yolov5s asymu8 --preprocess --postprocess
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export yolov5s asymu8
|
||||
```
|
||||
|
||||
此时 yolov5s 的目录结构如下：
|
||||
|
||||
```
|
||||
yolov5s/
|
||||
├── 0.jpg
|
||||
├── channel_mean_value.txt
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ └── asymmetric_affine
|
||||
│ ├── yolov5s_asymu8
|
||||
│ │ ├── analysis.json
|
||||
│ │ ├── BUILD
|
||||
│ │ ├── dump_core_graph.json
|
||||
│ │ ├── graph.json
|
||||
│ │ ├── main.c
|
||||
│ │ ├── makefile.linux
|
||||
│ │ ├── vnn_global.h
|
||||
│ │ ├── vnn_post_process.c
|
||||
│ │ ├── vnn_post_process.h
|
||||
│ │ ├── vnn_pre_process.c
|
||||
│ │ ├── vnn_pre_process.h
|
||||
│ │ ├── vnn_yolov5sasymu8.c
|
||||
│ │ ├── vnn_yolov5sasymu8.h
|
||||
│ │ ├── vnn_yolov5sasymu8_tensor.c
|
||||
│ │ ├── yolov5sasymu8.2012.vcxproj
|
||||
│ │ ├── yolov5s_asymu8.export.data
|
||||
│ │ └── yolov5sasymu8.vcxproj
|
||||
│ └── yolov5s_asymu8_nbg_unify
|
||||
│ ├── BUILD
|
||||
│ ├── dump_core_graph.json
|
||||
│ ├── graph.json
|
||||
│ ├── cmd.sh
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── nbg_meta.json
|
||||
│ ├── network_binary.nb
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ ├── vnn_pre_process.h
|
||||
│ ├── vnn_yolov5sasymmetricaffine.c
|
||||
│ ├── vnn_yolov5sasymmetricaffine.h
|
||||
│ ├── yolov5sasymmetricaffine.2012.vcxproj
|
||||
│ ├── yolov5s_asymmetric_affine.export.data
|
||||
│ └── yolov5sasymmetricaffine.vcxproj
|
||||
├── yolov5s_asymmetric_affine.quantize
|
||||
│ ├── vnn_yolov5sasymu8.c
|
||||
│ ├── vnn_yolov5sasymu8.h
|
||||
│ ├── vnn_yolov5sasymu8_tensor.c
|
||||
│ ├── yolov5sasymu8.2012.vcxproj
|
||||
│ └── yolov5sasymu8.vcxproj
|
||||
├── yolov5s_asymu8.quantize
|
||||
├── yolov5s.data
|
||||
├── yolov5s_inputmeta.yml
|
||||
├── yolov5s.json
|
||||
└── yolov5s.onnx
|
||||
├── yolov5s.onnx
|
||||
└── yolov5s_postprocess_file.yml
|
||||
```
|
||||
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 3.2 使用 netrans_py 转换 onnx 示例模型 yolov5s
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[0, 0, 0], scale=[0.003921568627451])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
example.py yolov5s -q uint8 -m 0 -s 0.003921568627
|
||||
python example.py yolov5s -q asymu8
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -1,37 +1,59 @@
|
|||
# Onnx模型转换示例
|
||||
本文档以 resnet50 为例介绍如何使用 Netrans 对 pytorch 模型进行转换。
|
||||
由于pytorch 的动态图特征，需要将 pytorch 模型转换成 onnx 格式后，再以 onnx 格式的模型进行转换。
|
||||
# ONNX模型转换示例
|
||||
本文档以 resnet50 为例介绍如何使用 Netrans 对 Pytorch 模型进行转换。
|
||||
由于Pytorch 的动态图特征，需要将 Pytorch 模型转换成 ONNX 格式后，再以 ONNX 格式的模型进行转换。
|
||||
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
## 安装Netrans
|
||||
创建 conda 环境 .
|
||||
```bash
|
||||
conda create -n netrans python=3.8 -y
|
||||
conda activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans .
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
mkdir -p ~/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
安装 Netrans。
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
## 数据准备
|
||||
|
||||
将 pytorch 模型导出成 onnx 模型
|
||||
将 Pytorch 模型导出成 ONNX 模型
|
||||
|
||||
```bash
|
||||
cd examples/pytorch/resnet50
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
cd ~/app/netrans/examples/pytorch/resnet50
|
||||
python3 export_resnet50_2_onnx.py
|
||||
cd ..
|
||||
```
|
||||
|
||||
转换 onnx 模型需准备：
|
||||
转换 ONNX 模型需准备：
|
||||
|
||||
- .onnx 文件：网络模型
|
||||
- dataset.txt：数据路径配置文件
|
||||
|
|
@ -39,139 +61,168 @@ cd ..
|
|||
我们的示例 已经完成数据准备，可以使用下面命令进入目录执行。
|
||||
|
||||
```bash
|
||||
cd netrans/
|
||||
cd examples/pytorch
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
cd ~/app/netrans/examples/pytorch
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
||||
```
|
||||
resnet50
|
||||
├── dataset.txt
|
||||
├── dog.jpg
|
||||
├── export_resnet50_2_onnx.py
|
||||
└── resnet50.onnx
|
||||
```
|
||||
|
||||
## 使用 Netrans_cli 命令行工具
|
||||
|
||||
### 模型导入
|
||||
|
||||
```bash
|
||||
load resnet50
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 resnet50 的目录结构如下：
|
||||
|
||||
```bash
|
||||
resnet50/
|
||||
├── dataset.txt
|
||||
├── dog.jpg
|
||||
├── export_resnet50_2_onnx.py
|
||||
├── resnet50.data
|
||||
├── resnet50_inputmeta.yml
|
||||
├── resnet50.json
|
||||
├── resnet50.onnx
|
||||
└── resnet50_postprocess_file.yml
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
|
||||
量化处理可优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
```bash
|
||||
quantize resnet50 asymu8
|
||||
|
||||
```
|
||||
|
||||
此时 resnet50 的目录结构如下：
|
||||
|
||||
```bash
|
||||
resnet50/
|
||||
├── dataset.txt
|
||||
├── dog.jpg
|
||||
├── export_resnet50_2_onnx.py
|
||||
├── resnet50_asymu8.quantize
|
||||
├── resnet50.data
|
||||
├── resnet50_inputmeta.yml
|
||||
├── resnet50.json
|
||||
├── resnet50.onnx
|
||||
└── resnet50_postprocess_file.yml
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export resnet50 asymu8
|
||||
```
|
||||
此时 resnet50 的目录结构如下：
|
||||
|
||||
```
|
||||
resnet50/
|
||||
├── dataset.txt
|
||||
├── dog.jpg
|
||||
└── export_resnet50_2_onnx.py
|
||||
└── resnet_50.onnx # 网络模型
|
||||
```
|
||||
|
||||
### 3.1 使用 netrans_cli 转换 示例模型 resnet50
|
||||
|
||||
示例目录如下：
|
||||
|
||||
```
|
||||
pytorch/
|
||||
└── resnet50
|
||||
├── export_resnet50_2_onnx.py
|
||||
├── dataset.txt
|
||||
├── dog.jpg
|
||||
└── resnet50.onnx
|
||||
```
|
||||
|
||||
#### 3.1.1 导入模型
|
||||
|
||||
```bash
|
||||
import.sh resnet50
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 resnet50 的目录结构如下
|
||||
```
|
||||
resnet50/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── resnet50.data
|
||||
├── resnet50.json
|
||||
└── resnet50.onnx
|
||||
```
|
||||
|
||||
#### 3.1.2 生成配置文件
|
||||
数据在推理前一般会经过预处理，为了确保模型可以正确的输入数据，需要生产对应的配置文件。
|
||||
|
||||
```bash
|
||||
config.sh resnet50
|
||||
```
|
||||
|
||||
此时 resnet50 的目录结构如下：
|
||||
```
|
||||
resnet50/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── export_resnet50_2_onnx.py
|
||||
├── resnet50_asymu8.quantize
|
||||
├── resnet50.data
|
||||
├── resnet50_inputmeta.yml
|
||||
├── resnet50.json
|
||||
└── resnet50.onnx
|
||||
|
||||
```
|
||||
根据 resnet50 的实际情况 ，我们需要修改yml中的 mean 为 0，scale为 0.003921568627。
|
||||
打开 ` resnet50_inputmeta.yml ` 文件，
|
||||
修改第30-33行为：
|
||||
```
|
||||
scale:
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
- 0.003921568627
|
||||
├── resnet50.onnx
|
||||
├── resnet50_postprocess_file.yml
|
||||
└── wksp
|
||||
├── resnet50_asymu8
|
||||
│ ├── analysis.json
|
||||
│ ├── BUILD
|
||||
│ ├── dump_core_graph.json
|
||||
│ ├── graph.json
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── resnet50asymu8.2012.vcxproj
|
||||
│ ├── resnet50_asymu8.export.data
|
||||
│ ├── resnet50asymu8.vcxproj
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ ├── vnn_pre_process.h
|
||||
│ ├── vnn_resnet50asymu8.c
|
||||
│ ├── vnn_resnet50asymu8.h
|
||||
│ └── vnn_resnet50asymu8_tensor.c
|
||||
└── resnet50_asymu8_nbg_unify
|
||||
├── BUILD
|
||||
├── cmd.sh
|
||||
├── main.c
|
||||
├── makefile.linux
|
||||
├── nbg_meta.json
|
||||
├── network_binary.nb
|
||||
├── resnet50asymu8.2012.vcxproj
|
||||
├── resnet50asymu8.vcxproj
|
||||
├── vnn_global.h
|
||||
├── vnn_post_process.c
|
||||
├── vnn_post_process.h
|
||||
├── vnn_pre_process.c
|
||||
├── vnn_pre_process.h
|
||||
├── vnn_resnet50asymu8.c
|
||||
├── vnn_resnet50asymu8.h
|
||||
└── vnn_resnet50asymu8_tensor.c
|
||||
|
||||
```
|
||||
|
||||
#### 3.1.3 量化模型
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
quantize.sh resnet50 uint8
|
||||
|
||||
python example.py resnet50 -q asymu8
|
||||
```
|
||||
|
||||
此时 resnet50 的目录结构如下：
|
||||
|
||||
```
|
||||
resnet50/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── resnet50_asymmetric_affine.quantize
|
||||
├── resnet50.data
|
||||
├── resnet50_inputmeta.yml
|
||||
├── resnet50.json
|
||||
└── resnet50.onnx
|
||||
```
|
||||
|
||||
#### 3.1.4 导出模型
|
||||
|
||||
```bash
|
||||
./export.sh resnet50 uint8
|
||||
```
|
||||
此时 resnet50 的目录结构如下：
|
||||
|
||||
```
|
||||
resnet50/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── wksp
|
||||
│ └── asymmetric_affine
|
||||
│ ├── BUILD
|
||||
│ ├── dump_core_graph.json
|
||||
│ ├── graph.json
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── network_binary.nb
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ ├── vnn_pre_process.h
|
||||
│ ├── vnn_resnet50asymmetricaffine.c
|
||||
│ ├── vnn_resnet50asymmetricaffine.h
|
||||
│ ├── resnet50asymmetricaffine.2012.vcxproj
|
||||
│ ├── resnet50_asymmetric_affine.export.data
|
||||
│ └── resnet50asymmetricaffine.vcxproj
|
||||
├── resnet50_asymmetric_affine.quantize
|
||||
├── resnet50.data
|
||||
├── resnet50_inputmeta.yml
|
||||
├── resnet50.json
|
||||
└── resnet50.onnx
|
||||
```
|
||||
|
||||
|
||||
### 3.2 使用 netrans_py 转换 onnx 示例模型 resnet50
|
||||
|
||||
```bash
|
||||
cd ..
|
||||
example.py resnet50 -q uint8 -m 0 -s 0.003921568627
|
||||
```
|
||||
|
|
|
|||
|
|
@ -4,24 +4,55 @@
|
|||
|
||||
Netrans 支持 TensorFlow 版本1.4.x, 2.0.x, 2.3.x, 2.6.x, 2.8.x, 2.10.x, 2.12.x 以tf.io.write_graph()保存的模型。
|
||||
|
||||
## 安装Netrans
|
||||
创建 conda 环境 .
|
||||
## 安装 Netrans
|
||||
|
||||
创建虚拟环境。
|
||||
|
||||
```bash
|
||||
conda create -n netrans python=3.8 -y
|
||||
conda activate netrans
|
||||
# 下载 mamba 安装脚本
|
||||
wget "https://mirrors.tuna.tsinghua.edu.cn/github-release/conda-forge/miniforge/LatestRelease//Miniforge3-$(uname)-$(uname -m).sh"
|
||||
# 创建 mamba 的安装目录
|
||||
mkdir -p ~/app
|
||||
# 安装 mamba 到 ~/app/
|
||||
bash Miniforge3-Linux-x86_64.sh -b -p ${HOME}/app/miniforge3
|
||||
# 添加 mamba 的初始化脚本到环境配置文件
|
||||
echo "source " ${HOME}/app/miniforge3/etc/profile.d/mamba.sh"" >> ${HOME}/.bashrc
|
||||
# 重新加载 ~/.bashrc 文件，使 mamba 初始化生效
|
||||
source ${HOME}/.bashrc
|
||||
# 创建一个名为 netrans 的虚拟环境，并安装 Python 3.8
|
||||
mamba create -n netrans python=3.10 -y
|
||||
# 激活 netrans 虚拟环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
下载 Netrans .
|
||||
下载 Netrans
|
||||
|
||||
```bash
|
||||
mkdir -p ~/app
|
||||
cd ~/app
|
||||
git clone https://gitlink.org.cn/nudt_dsp/netrans.git
|
||||
```
|
||||
|
||||
安装 Netrans。
|
||||
Netrans_cli 是基于 Netrans_api 封装的命令行工具，执行 `setup.sh` 可安装 Netrans_cli。
|
||||
|
||||
```bash
|
||||
cd ~/app/netrans
|
||||
./setup.sh
|
||||
cd ~/app/netrans
|
||||
# 执行 setup.sh
|
||||
bash setup.sh
|
||||
# setup.sh 会修改系统环境变量，需要 source 重新生效
|
||||
source ~/.bashrc
|
||||
# 重新激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
## 数据准备
|
||||
|
||||
示例使用 ONNX 格式的 yolov8s 模型，已经完成数据准备，可以使用下面命令进入目录执行。
|
||||
|
||||
```bash
|
||||
cd netrans/
|
||||
cd examples/infer_with_pre_post_process
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
|
||||
|
|
@ -34,8 +65,9 @@ cd ~/app/netrans
|
|||
我们的示例 已经完成数据准备，可以使用下面命令进入目录执行。
|
||||
|
||||
```bash
|
||||
cd netrans/
|
||||
cd examples/tensorflow
|
||||
cd ~/app/netrans/examples/tensorflow
|
||||
# 激活 netrans 环境
|
||||
mamba activate netrans
|
||||
```
|
||||
|
||||
此时目录如下：
|
||||
|
|
@ -52,98 +84,147 @@ lenet/
|
|||
|
||||
### 模型导入
|
||||
```bash
|
||||
import.sh lenet
|
||||
load lenet
|
||||
```
|
||||
|
||||
该命令会在工程目录下生成包含模型信息的 .json 和 .data 数据文件。
|
||||
此时 lenet 的目录结构如下：
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet.data
|
||||
├── lenet.json
|
||||
└── lenet.pb
|
||||
```
|
||||
|
||||
### 配置文件生成
|
||||
数据在推理前一般会经过预处理，为了确保模型可以正确的输入数据，需要生产对应的配置文件。
|
||||
|
||||
```bash
|
||||
config.sh lenet
|
||||
```
|
||||
|
||||
此时 lenet 的目录结构如下：
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet.data
|
||||
├── lenet_inputmeta.yml
|
||||
├── lenet.json
|
||||
└── lenet.pb
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
|
||||
```bash
|
||||
quantize.sh lenet uint8
|
||||
|
||||
```
|
||||
|
||||
此时 lenet 的目录结构如下：
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet_asymmetric_affine.quantize
|
||||
├── lenet.data
|
||||
├── lenet_inputmeta.yml
|
||||
├── lenet.json
|
||||
└── lenet.pb
|
||||
```
|
||||
### 模型导出
|
||||
使用 export.sh 将模型导出到nbg格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export.sh lenet uint8
|
||||
```
|
||||
此时 lenet 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet_asymmetric_affine.quantize
|
||||
├── lenet.data
|
||||
├── lenet_inputmeta.yml
|
||||
├── lenet.json
|
||||
├── lenet.pb
|
||||
└── lenet_postprocess_file.yml
|
||||
```
|
||||
|
||||
### 模型量化
|
||||
|
||||
量化处理可优化模型的推理效率，加快模型的推理速度，我们使用以下命令对模型进行量化处理。量化模型需要两个参数：目录（模型）名字和量化类型。支持的量化类型包括：
|
||||
symi8: 对称量化算法，使用 int8 类型
|
||||
asymu8: 非对称量化算法，使用 uint8 类型
|
||||
symi16: 对称量化算法，使用 int16 类型
|
||||
|
||||
```bash
|
||||
quantize lenet asymu8
|
||||
```
|
||||
|
||||
此时 lenet 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet_asymu8.quantize
|
||||
├── lenet.data
|
||||
├── lenet_inputmeta.yml
|
||||
├── lenet.json
|
||||
├── lenet.pb
|
||||
└── lenet_postprocess_file.yml
|
||||
```
|
||||
|
||||
### 模型导出
|
||||
|
||||
使用 `export` 将模型导出为 `nbg` 格式并生成应用程序工程。
|
||||
|
||||
```bash
|
||||
export lenet asymu8
|
||||
```
|
||||
|
||||
此时 lenet 的目录结构如下：
|
||||
|
||||
```bash
|
||||
lenet/
|
||||
├── 0.jpg
|
||||
├── dataset.txt
|
||||
├── inputs_outputs.txt
|
||||
├── lenet_asymu8.quantize
|
||||
├── lenet.data
|
||||
├── lenet_inputmeta.yml
|
||||
├── lenet.json
|
||||
├── lenet.pb
|
||||
├── lenet_postprocess_file.yml
|
||||
└── wksp
|
||||
└── asymmetric_affine
|
||||
├── lenet_asymu8
|
||||
│ ├── analysis.json
|
||||
│ ├── BUILD
|
||||
│ ├── dump_core_graph.json
|
||||
│ ├── graph.json
|
||||
│ ├── lenetasymu8.2012.vcxproj
|
||||
│ ├── lenet_asymu8.export.data
|
||||
│ ├── lenetasymu8.vcxproj
|
||||
│ ├── main.c
|
||||
│ ├── makefile.linux
|
||||
│ ├── vnn_global.h
|
||||
│ ├── vnn_lenetasymu8.c
|
||||
│ ├── vnn_lenetasymu8.h
|
||||
│ ├── vnn_lenetasymu8_tensor.c
|
||||
│ ├── vnn_post_process.c
|
||||
│ ├── vnn_post_process.h
|
||||
│ ├── vnn_pre_process.c
|
||||
│ └── vnn_pre_process.h
|
||||
└── lenet_asymu8_nbg_unify
|
||||
├── BUILD
|
||||
├── dump_core_graph.json
|
||||
├── graph.json
|
||||
├── lenetasymmetricaffine.2012.vcxproj
|
||||
├── lenet_asymmetric_affine.export.data
|
||||
├── lenetasymmetricaffine.vcxproj
|
||||
├── cmd.sh
|
||||
├── lenetasymu8.2012.vcxproj
|
||||
├── lenetasymu8.vcxproj
|
||||
├── main.c
|
||||
├── makefile.linux
|
||||
├── nbg_meta.json
|
||||
├── network_binary.nb
|
||||
├── vnn_global.h
|
||||
├── vnn_lenetasymmetricaffine.c
|
||||
├── vnn_lenetasymmetricaffine.h
|
||||
├── vnn_lenetasymu8.c
|
||||
├── vnn_lenetasymu8.h
|
||||
├── vnn_lenetasymu8_tensor.c
|
||||
├── vnn_post_process.c
|
||||
├── vnn_post_process.h
|
||||
├── vnn_pre_process.c
|
||||
└── vnn_pre_process.h
|
||||
```
|
||||
## 使用 netrans_py python api
|
||||
|
||||
## 使用 Netrans_py Python API
|
||||
|
||||
### 示例代码
|
||||
|
||||
```python
|
||||
# example.py
|
||||
from netrans import Netrans
|
||||
|
||||
def main(model_path: str, quantize_type: str):
|
||||
# 初始化 Netrans
|
||||
net = Netrans()
|
||||
|
||||
# 导入模型并配置预处理参数
|
||||
net.load(model_path, mean=[128, 128, 128], scale=[1, 1, 1])
|
||||
|
||||
# 模型量化
|
||||
net.quantize(quantize_type)
|
||||
|
||||
# 配置前后处理加入推理计算图
|
||||
net.add_pre_post(quantize_type, pre=True, post=True)
|
||||
|
||||
# 模型导出
|
||||
net.export(quantize_type)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
|
||||
parser = argparse.ArgumentParser(description="Netrans Model Conversion")
|
||||
parser.add_argument("model_path", type=str, help="Path to the model directory")
|
||||
parser.add_argument("-q", "--quantize", type=str, default="asymu8", help="Quantization type (default: asymu8)")
|
||||
args = parser.parse_args()
|
||||
|
||||
main(args.model_path, args.quantize)
|
||||
```
|
||||
|
||||
### 运行示例
|
||||
|
||||
```bash
|
||||
python3 example.py lenet -q uint8
|
||||
python example.py lenet -q asymu8
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -1,30 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ "$#" -ne 1 ]; then
|
||||
echo "Enter a network name !"
|
||||
exit 2
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit 3
|
||||
fi
|
||||
|
||||
|
||||
netrans=$NETRANS_PATH/pnnacc
|
||||
|
||||
|
||||
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
echo $(pwd)
|
||||
$netrans generate \
|
||||
inputmeta \
|
||||
--model ${NAME}.json \
|
||||
--separated-database
|
||||
popd
|
||||
|
|
@ -1,67 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import argparse
|
||||
from netrans import Netrans
|
||||
|
||||
def main():
|
||||
# 创建参数解析器
|
||||
parser = argparse.ArgumentParser(
|
||||
description='神经网络模型转换工具',
|
||||
formatter_class=argparse.ArgumentDefaultsHelpFormatter # 自动显示默认值
|
||||
)
|
||||
|
||||
# 必填位置参数
|
||||
parser.add_argument(
|
||||
'model_path',
|
||||
type=str,
|
||||
help='输入模型路径（必须参数）'
|
||||
)
|
||||
|
||||
# 可选参数组
|
||||
quant_group = parser.add_argument_group('量化参数')
|
||||
quant_group.add_argument(
|
||||
'-q', '--quantize_type',
|
||||
type=str,
|
||||
choices=['uint8', 'int8', 'int16', 'float'],
|
||||
default='uint8',
|
||||
metavar='TYPE',
|
||||
help='量化类型（可选值：%(choices)s）'
|
||||
)
|
||||
quant_group.add_argument(
|
||||
'-m', '--mean',
|
||||
type=int,
|
||||
default=0,
|
||||
help='归一化均值（默认：%(default)s）'
|
||||
)
|
||||
quant_group.add_argument(
|
||||
'-s', '--scale',
|
||||
type=float,
|
||||
default=1.0,
|
||||
help='量化缩放系数（默认：%(default)s）'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-p', '--profile',
|
||||
action='store_true', # 设置为True当参数存在时
|
||||
help='启用性能分析模式（默认：%(default)s）'
|
||||
)
|
||||
|
||||
|
||||
# 解析参数
|
||||
args = parser.parse_args()
|
||||
|
||||
# 执行模型转换
|
||||
try:
|
||||
model = Netrans(model_path=args.model_path)
|
||||
model.model2nbg(
|
||||
quantize_type=args.quantize_type,
|
||||
mean=args.mean,
|
||||
scale=args.scale,
|
||||
profile=args.profile
|
||||
)
|
||||
print(f"模型 {args.model_path} 转换成功")
|
||||
except FileNotFoundError:
|
||||
print(f"错误：模型文件 {args.model_path} 不存在")
|
||||
exit(1)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
@ -1,133 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
OVXGENERATOR=$NETRANS_PATH/pnnacc
|
||||
|
||||
OVXGENERATOR="$OVXGENERATOR export ovxlib"
|
||||
|
||||
DATASET=dataset.txt
|
||||
|
||||
VERIFT='FLASE'
|
||||
function export_network()
|
||||
{
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
|
||||
QUANTIZED=$2
|
||||
|
||||
if [ ${QUANTIZED} = 'float' ]; then
|
||||
TYPE=float;
|
||||
quantization_type="none_quantized"
|
||||
generate_path='./wksp/none_quantized'
|
||||
elif [ ${QUANTIZED} = 'uint8' ]; then
|
||||
quantization_type="asymmetric_affine"
|
||||
generate_path='./wksp/asymmetric_affine'
|
||||
TYPE=quantized;
|
||||
elif [ ${QUANTIZED} = 'int8' ]; then
|
||||
quantization_type="dynamic_fixed_point-8"
|
||||
generate_path='./wksp/dynamic_fixed_point-8'
|
||||
TYPE=quantized;
|
||||
elif [ ${QUANTIZED} = 'int16' ]; then
|
||||
quantization_type="dynamic_fixed_point-16"
|
||||
generate_path='./wksp/dynamic_fixed_point-16'
|
||||
TYPE=quantized;
|
||||
else
|
||||
echo "=========== wrong quantization_type ! ( float / uint8 / int8 / int16 )==========="
|
||||
exit -1
|
||||
fi
|
||||
|
||||
echo " ======================================================================="
|
||||
echo " =========== Start Generate $NAME ovx C code with type of ${quantization_type} ==========="
|
||||
echo " ======================================================================="
|
||||
|
||||
mkdir -p "${generate_path}"
|
||||
|
||||
# if want to import c code into win IDE , change --target-ide-project command-line param from 'linux64' -> 'win32'
|
||||
if [ ${QUANTIZED} = 'float' ]; then
|
||||
cmd="$OVXGENERATOR \
|
||||
--model ${NAME}.json \
|
||||
--model-data ${NAME}.data \
|
||||
--model-quantize ${NAME}.quantize \
|
||||
--dtype ${TYPE} \
|
||||
--pack-nbg-viplite \
|
||||
--model-quantize ${NAME}_${quantization_type}.quantize \
|
||||
--with-input-meta ${NAME}_inputmeta.yml\
|
||||
--optimize 'VIP8000NANOQI_PLUS_PID0XB1'\
|
||||
--target-ide-project 'linux64' \
|
||||
--viv-sdk ${NETRANS_PATH}/pnna_sdk \
|
||||
--output-path ${generate_path}/${NAME}_${quantization_type}"
|
||||
else
|
||||
|
||||
if [ -f ${NAME}_${quantization_type}.quantize ]; then
|
||||
echo -e "\033[31m using ${NAME}_${quantization_type}.quantize \033[0m"
|
||||
else
|
||||
echo -e "\033[31m Can not find ${NAME}_${quantization_type}.quantize \033[0m"
|
||||
exit -1;
|
||||
fi
|
||||
|
||||
cmd="$OVXGENERATOR \
|
||||
--model ${NAME}.json \
|
||||
--model-data ${NAME}.data \
|
||||
--model-quantize ${NAME}.quantize \
|
||||
--dtype ${TYPE} \
|
||||
--pack-nbg-viplite \
|
||||
--model-quantize ${NAME}_${quantization_type}.quantize \
|
||||
--with-input-meta ${NAME}_inputmeta.yml\
|
||||
--optimize 'VIP8000NANOQI_PLUS_PID0XB1'\
|
||||
--target-ide-project 'linux64' \
|
||||
--viv-sdk ${NETRANS_PATH}/pnna_sdk \
|
||||
--output-path ${generate_path}/${NAME}_${quantization_type}"
|
||||
fi
|
||||
|
||||
# if [ "${VERIFY}"='TRUE' ]; then
|
||||
# echo $cmd
|
||||
# fi
|
||||
eval $cmd
|
||||
|
||||
# 检查是否有至少三个参数
|
||||
if [ $# -ge 3 ]; then
|
||||
# 检查第三个参数是否为 "profile"
|
||||
if [ "$3" == "profile" ]; then
|
||||
cpcmd="cp ${generate_path}_nbg_viplite/network_binary.nb ${generate_path}/"
|
||||
eval $cpcmd
|
||||
|
||||
delcmd="rm -rf ${generate_path}_nbg_viplite"
|
||||
eval $delcmd
|
||||
fi
|
||||
else
|
||||
# mvcmd="mv ${generate_path}_nbg_viplite ${generate_path}"
|
||||
# eval $mvcmd
|
||||
tmp='wksp/tmp'
|
||||
mkdir -p ${tmp}
|
||||
cpcmd="cp ${generate_path}_nbg_viplite/network_binary.nb ${tmp}/"
|
||||
eval $cpcmd
|
||||
|
||||
delcmd="rm -rf ${generate_path} ${generate_path}_nbg_viplite"
|
||||
eval $delcmd
|
||||
mv ${tmp} ${generate_path}
|
||||
fi
|
||||
|
||||
|
||||
echo " ======================================================================="
|
||||
echo " =========== End Generate $NAME ovx C code with type of ${quantization_type} ==========="
|
||||
echo " ======================================================================="
|
||||
|
||||
popd
|
||||
}
|
||||
|
||||
if [ "$#" -lt 2 ]; then
|
||||
echo "Input a network name and quantized type ( float / uint8 / int8 / int16 )"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit -2
|
||||
fi
|
||||
|
||||
echo $1,$2,$3
|
||||
export_network ${1%/} ${2%/} ${3%/}
|
||||
|
|
@ -1,208 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
function import_caffe_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTCAFFE=$NETRANS_PATH/pnnacc
|
||||
|
||||
CONVERTCAFFE="$CONVERTCAFFE import caffe"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME Caffe model ==========="
|
||||
if [ -f ${NAME}.caffemodel ]; then
|
||||
cmd="$CONVERTCAFFE \
|
||||
--model ${NAME}.prototxt \
|
||||
--weights ${NAME}.caffemodel \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
else
|
||||
echo "=========== fake Caffe model data file==========="
|
||||
cmd="$CONVERTCAFFE \
|
||||
--model ${NAME}.prototxt \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
fi
|
||||
}
|
||||
|
||||
function import_tensorflow_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTF=$NETRANS_PATH/pnnacc
|
||||
|
||||
CONVERTF="$CONVERTF import tensorflow"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME Tensorflow model ==========="
|
||||
cmd="$CONVERTF \
|
||||
--model ${NAME}.pb \
|
||||
--output-data ${NAME}.data \
|
||||
--output-model ${NAME}.json \
|
||||
$(cat inputs_outputs.txt)"
|
||||
}
|
||||
|
||||
function import_onnx_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTONNX=$NETRANS_PATH/pnnacc
|
||||
CONVERTONNX="$CONVERTONNX import onnx"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME ONNX model ==========="
|
||||
cmd="$CONVERTONNX \
|
||||
--model ${NAME}.onnx \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_tflite_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTTFLITE=$NETRANS_PATH/pnnacc
|
||||
CONVERTTFLITE="$CONVERTTFLITE import tflite"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME TFLite model ==========="
|
||||
cmd="$CONVERTTFLITE \
|
||||
--model ${NAME}.tflite \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_darknet_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTDARKNET=$NETRANS_PATH/pnnacc
|
||||
CONVERTDARKNET="$CONVERTDARKNET import darknet"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME darknet model ==========="
|
||||
cmd="$CONVERTDARKNET \
|
||||
--model ${NAME}.cfg \
|
||||
--weight ${NAME}.weights \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_pytorch_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTPYTORCH=$NETRANS_PATH/pnnacc
|
||||
CONVERTPYTORCH="$CONVERTPYTORCH import pytorch"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME pytorch model ==========="
|
||||
cmd="$CONVERTPYTORCH \
|
||||
--model ${NAME}.pt \q
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data \
|
||||
$(cat input_size.txt)"
|
||||
}
|
||||
|
||||
function import_network()
|
||||
{
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
|
||||
if [ -f ${NAME}.prototxt ]; then
|
||||
import_caffe_network ${NAME%/}
|
||||
elif [ -f ${NAME}.pb ]; then
|
||||
import_tensorflow_network ${NAME%/}
|
||||
elif [ -f ${NAME}.onnx ]; then
|
||||
import_onnx_network ${NAME%/}
|
||||
elif [ -f ${NAME}.tflite ]; then
|
||||
import_tflite_network ${NAME%/}
|
||||
elif [ -f ${NAME}.weights ]; then
|
||||
import_darknet_network ${NAME%/}
|
||||
elif [ -f ${NAME}.pt ]; then
|
||||
import_pytorch_network ${NAME%/}
|
||||
else
|
||||
echo "=========== can not find suitable model files ==========="
|
||||
fi
|
||||
|
||||
echo $cmd
|
||||
eval $cmd
|
||||
|
||||
if [ -f ${NAME}.data -a -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m SUCCESS \033[0m"
|
||||
else
|
||||
echo -e "\033[31m ERROR ! \033[0m"
|
||||
fi
|
||||
popd
|
||||
}
|
||||
|
||||
if [ "$#" -ne 1 ]; then
|
||||
echo "Input a network name !"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit -2
|
||||
fi
|
||||
|
||||
import_network ${1%/}
|
||||
|
|
@ -1,65 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
TENSORZONX=$NETRANS_PATH/pnnacc
|
||||
|
||||
TENSORZONX="$TENSORZONX inference"
|
||||
|
||||
DATASET=./dataset.txt
|
||||
|
||||
function inference_network()
|
||||
{
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
QUANTIZED=$2
|
||||
inf_path='./inf'
|
||||
|
||||
if [ ${QUANTIZED} = 'float' ]; then
|
||||
TYPE=float32;
|
||||
quantization_type="float32"
|
||||
elif [ ${QUANTIZED} = 'uint8' ]; then
|
||||
quantization_type="asymmetric_affine"
|
||||
TYPE=quantized;
|
||||
elif [ ${QUANTIZED} = 'int8' ]; then
|
||||
quantization_type="dynamic_fixed_point-8"
|
||||
TYPE=quantized;
|
||||
elif [ ${QUANTIZED} = 'int16' ]; then
|
||||
quantization_type="dynamic_fixed_point-16"
|
||||
TYPE=quantized;
|
||||
else
|
||||
echo "=========== wrong quantization_type ! ( float / uint8 / int8 / int16 )==========="
|
||||
exit -1
|
||||
fi
|
||||
|
||||
cmd="$TENSORZONX \
|
||||
--dtype ${TYPE} \
|
||||
--batch-size 1 \
|
||||
--model-quantize ${NAME}_${quantization_type}.quantize \
|
||||
--model ${NAME}.json \
|
||||
--model-data ${NAME}.data \
|
||||
--output-dir ${inf_path} \
|
||||
--with-input-meta ${NAME}_inputmeta.yml \
|
||||
--device CPU"
|
||||
|
||||
echo $cmd
|
||||
eval $cmd
|
||||
echo "=========== End inference $NAME model ==========="
|
||||
|
||||
popd
|
||||
}
|
||||
|
||||
if [ "$#" -lt 2 ]; then
|
||||
echo "Input a network name and quantized type ( float / uint8 / int8 / int16 )"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit -2
|
||||
fi
|
||||
|
||||
inference_network ${1%/} ${2%/}
|
||||
|
|
@ -1,208 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
function import_caffe_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTCAFFE=$NETRANS_PATH/pnnacc
|
||||
|
||||
CONVERTCAFFE="$CONVERTCAFFE import caffe"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME Caffe model ==========="
|
||||
if [ -f ${NAME}.caffemodel ]; then
|
||||
cmd="$CONVERTCAFFE \
|
||||
--model ${NAME}.prototxt \
|
||||
--weights ${NAME}.caffemodel \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
else
|
||||
echo "=========== fake Caffe model data file==========="
|
||||
cmd="$CONVERTCAFFE \
|
||||
--model ${NAME}.prototxt \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
fi
|
||||
}
|
||||
|
||||
function import_tensorflow_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTF=$NETRANS_PATH/pnnacc
|
||||
|
||||
CONVERTF="$CONVERTF import tensorflow"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME Tensorflow model ==========="
|
||||
cmd="$CONVERTF \
|
||||
--model ${NAME}.pb \
|
||||
--output-data ${NAME}.data \
|
||||
--output-model ${NAME}.json \
|
||||
$(cat inputs_outputs.txt)"
|
||||
}
|
||||
|
||||
function import_onnx_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTONNX=$NETRANS_PATH/pnnacc
|
||||
CONVERTONNX="$CONVERTONNX import onnx"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME ONNX model ==========="
|
||||
cmd="$CONVERTONNX \
|
||||
--model ${NAME}.onnx \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_tflite_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTTFLITE=$NETRANS_PATH/pnnacc
|
||||
CONVERTTFLITE="$CONVERTTFLITE import tflite"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME TFLite model ==========="
|
||||
cmd="$CONVERTTFLITE \
|
||||
--model ${NAME}.tflite \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_darknet_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTDARKNET=$NETRANS_PATH/pnnacc
|
||||
CONVERTDARKNET="$CONVERTDARKNET import darknet"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME darknet model ==========="
|
||||
cmd="$CONVERTDARKNET \
|
||||
--model ${NAME}.cfg \
|
||||
--weight ${NAME}.weights \
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data"
|
||||
}
|
||||
|
||||
function import_pytorch_network()
|
||||
{
|
||||
NAME=$1
|
||||
CONVERTPYTORCH=$NETRANS_PATH/pnnacc
|
||||
CONVERTPYTORCH="$CONVERTPYTORCH import pytorch"
|
||||
|
||||
|
||||
if [ -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m rm ${NAME}.json \033[0m"
|
||||
rm ${NAME}.json
|
||||
fi
|
||||
|
||||
if [ -f ${NAME}.data ]; then
|
||||
echo -e "\033[31m rm ${NAME}.data \033[0m"
|
||||
rm ${NAME}.data
|
||||
fi
|
||||
|
||||
echo "=========== Converting $NAME pytorch model ==========="
|
||||
cmd="$CONVERTPYTORCH \
|
||||
--model ${NAME}.pt \q
|
||||
--output-model ${NAME}.json \
|
||||
--output-data ${NAME}.data \
|
||||
$(cat input_size.txt)"
|
||||
}
|
||||
|
||||
function import_network()
|
||||
{
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
|
||||
if [ -f ${NAME}.prototxt ]; then
|
||||
import_caffe_network ${NAME%/}
|
||||
elif [ -f ${NAME}.pb ]; then
|
||||
import_tensorflow_network ${NAME%/}
|
||||
elif [ -f ${NAME}.onnx ]; then
|
||||
import_onnx_network ${NAME%/}
|
||||
elif [ -f ${NAME}.tflite ]; then
|
||||
import_tflite_network ${NAME%/}
|
||||
elif [ -f ${NAME}.weights ]; then
|
||||
import_darknet_network ${NAME%/}
|
||||
elif [ -f ${NAME}.pt ]; then
|
||||
import_pytorch_network ${NAME%/}
|
||||
else
|
||||
echo "=========== can not find suitable model files ==========="
|
||||
fi
|
||||
|
||||
echo $cmd
|
||||
eval $cmd
|
||||
|
||||
if [ -f ${NAME}.data -a -f ${NAME}.json ]; then
|
||||
echo -e "\033[31m SUCCESS \033[0m"
|
||||
else
|
||||
echo -e "\033[31m ERROR ! \033[0m"
|
||||
fi
|
||||
popd
|
||||
}
|
||||
|
||||
if [ "$#" -ne 1 ]; then
|
||||
echo "Input a network name !"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit -2
|
||||
fi
|
||||
|
||||
import_network ${1%/}
|
||||
|
|
@ -1,76 +0,0 @@
|
|||
#!/bin/bash
|
||||
|
||||
if [ -z "$NETRANS_PATH" ]; then
|
||||
echo "Need to set enviroment variable NETRANS_PATH"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
TENSORZONEX=$NETRANS_PATH/pnnacc
|
||||
TENSORZONEX="$TENSORZONEX quantize"
|
||||
|
||||
|
||||
DATASET=./dataset.txt
|
||||
|
||||
function quantize_network()
|
||||
{
|
||||
NAME=$(basename "$1")
|
||||
pushd $1
|
||||
|
||||
QUANTIZED=$2
|
||||
|
||||
if [ ${QUANTIZED} = 'float' ]; then
|
||||
echo "=========== do not need quantied==========="
|
||||
exit -1
|
||||
elif [ ${QUANTIZED} = 'uint8' ]; then
|
||||
quantization_type="asymmetric_affine"
|
||||
elif [ ${QUANTIZED} = 'int8' ]; then
|
||||
quantization_type="dynamic_fixed_point-8"
|
||||
elif [ ${QUANTIZED} = 'int16' ]; then
|
||||
quantization_type="dynamic_fixed_point-16"
|
||||
else
|
||||
echo "=========== wrong quantization_type ! ( uint8 / int8 / int16 )==========="
|
||||
exit -1
|
||||
fi
|
||||
|
||||
echo " ======================================================================="
|
||||
echo " ==== Start Quantizing $NAME model with type of ${quantization_type} ==="
|
||||
echo " ======================================================================="
|
||||
|
||||
if [ -f ${NAME}_${quantization_type}.quantize ]; then
|
||||
echo -e "\033[31m rm ${NAME}_${quantization_type}.quantize \033[0m"
|
||||
rm ${NAME}_${quantization_type}.quantize
|
||||
fi
|
||||
|
||||
cmd="$TENSORZONEX \
|
||||
--batch-size 1 \
|
||||
--qtype ${QUANTIZED} \
|
||||
--rebuild \
|
||||
--quantizer ${quantization_type%-*} \
|
||||
--model-quantize ${NAME}_${quantization_type}.quantize \
|
||||
--model ${NAME}.json \
|
||||
--model-data ${NAME}.data \
|
||||
--with-input-meta ${NAME}_inputmeta.yml \
|
||||
--device CPU"
|
||||
echo $cmd
|
||||
eval $cmd
|
||||
|
||||
if [ -f ${NAME}_${quantization_type}.quantize ]; then
|
||||
echo -e "\033[31m SUCCESS \033[0m"
|
||||
else
|
||||
echo -e "\033[31m ERROR ! \033[0m"
|
||||
fi
|
||||
|
||||
popd
|
||||
}
|
||||
|
||||
if [ "$#" -lt 2 ]; then
|
||||
echo "Input a network name and quantized type ( uint8 / int8 / int16 )"
|
||||
exit -1
|
||||
fi
|
||||
|
||||
if [ ! -e "${1%/}" ]; then
|
||||
echo "Directory ${1%/} does not exist !"
|
||||
exit -2
|
||||
fi
|
||||
|
||||
quantize_network ${1%/} ${2%/}
|
||||
|
|
@ -1,60 +0,0 @@
|
|||
|
||||
import os
|
||||
import sys
|
||||
from utils import check_path, AttributeCopier, create_cls
|
||||
import subprocess
|
||||
|
||||
class Config(AttributeCopier):
|
||||
"""从实例化的 Netrans 中解析模型参数,并基于pnnacc 生成配置文件模板
|
||||
|
||||
Args:
|
||||
Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
"""
|
||||
def __init__(self, source_obj) -> None:
|
||||
"""从实例化的 Netrans 中解析模型参数
|
||||
|
||||
Args:
|
||||
source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
|
||||
"""
|
||||
super().__init__(source_obj)
|
||||
|
||||
@check_path
|
||||
def inputmeta_gen(self):
|
||||
"""生成配置文件模板
|
||||
|
||||
Return:
|
||||
None
|
||||
"""
|
||||
netrans_path = self.netrans
|
||||
network_name = self.model_name
|
||||
# 进入网络名称指定的目录
|
||||
# os.chdir(network_name)
|
||||
# check_env(network_name)
|
||||
|
||||
# 执行 pegasus 命令
|
||||
cmd = f"{netrans_path} generate inputmeta --model {network_name}.json --separated-database"
|
||||
try :
|
||||
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
except :
|
||||
raise RuntimeError('config failed')
|
||||
# os.chdir("..")
|
||||
|
||||
# def main():
|
||||
|
||||
# # 检查命令行参数数量是否正确
|
||||
# if len(sys.argv) != 2:
|
||||
# print("Enter a network name!")
|
||||
# sys.exit(2)
|
||||
|
||||
# # 检查提供的目录是否存在
|
||||
# network_name = sys.argv[1]
|
||||
# # 构建 netrans 可执行文件的路径
|
||||
# netrans_path =os.getenv('NETRANS_PATH')
|
||||
# cla = create_cls(netrans_path, network_name)
|
||||
# func = InputmetaGen(cla)
|
||||
# func.inputmeta_gen()
|
||||
|
||||
|
||||
# if __name__ == '__main__':
|
||||
# main()
|
||||
|
|
@ -1,176 +0,0 @@
|
|||
import os
|
||||
import sys
|
||||
import subprocess
|
||||
import shutil
|
||||
from utils import check_path, AttributeCopier, create_cls
|
||||
# 检查 NETRANS_PATH 环境变量是否设置
|
||||
|
||||
# 定义数据集文件路径
|
||||
dataset = 'dataset.txt'
|
||||
|
||||
class Export(AttributeCopier):
|
||||
"""从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导出模型ngb文件
|
||||
|
||||
Args:
|
||||
Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
"""
|
||||
def __init__(self, source_obj) -> None:
|
||||
"""从实例化的 Netrans 中解析模型参数
|
||||
|
||||
Args:
|
||||
source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
|
||||
"""
|
||||
super().__init__(source_obj)
|
||||
|
||||
@check_path
|
||||
def export_network(self):
|
||||
"""基于 pnnacc 导出模型
|
||||
"""
|
||||
|
||||
netrans = self.netrans
|
||||
quantized = self.quantize_type
|
||||
name = self.model_name
|
||||
netrans_path = self.netrans_path
|
||||
|
||||
ovxgenerator = netrans + " export ovxlib"
|
||||
# 进入模型目录
|
||||
# os.chdir(name)
|
||||
|
||||
# 根据量化类型设置参数
|
||||
if quantized == 'float':
|
||||
type_ = 'float'
|
||||
quantization_type = 'none_quantized'
|
||||
generate_path = './wksp/none_quantized'
|
||||
elif quantized == 'uint8':
|
||||
type_ = 'quantized'
|
||||
quantization_type = 'asymmetric_affine'
|
||||
generate_path = './wksp/asymmetric_affine'
|
||||
elif quantized == 'int8':
|
||||
type_ = 'quantized'
|
||||
quantization_type = 'dynamic_fixed_point-8'
|
||||
generate_path = './wksp/dynamic_fixed_point-8'
|
||||
elif quantized == 'int16':
|
||||
type_ = 'quantized'
|
||||
quantization_type = 'dynamic_fixed_point-16'
|
||||
generate_path = './wksp/dynamic_fixed_point-16'
|
||||
else:
|
||||
print("=========== wrong quantization_type ! ( float / uint8 / int8 / int16 )===========")
|
||||
sys.exit(1)
|
||||
|
||||
# 创建输出目录
|
||||
os.makedirs(generate_path, exist_ok=True)
|
||||
|
||||
# 构建命令
|
||||
if quantized == 'float':
|
||||
cmd = f"{ovxgenerator} \
|
||||
--model {name}.json \
|
||||
--model-data {name}.data \
|
||||
--dtype {type_} \
|
||||
--pack-nbg-viplite \
|
||||
--optimize 'VIP8000NANOQI_PLUS_PID0XB1'\
|
||||
--target-ide-project 'linux64' \
|
||||
--viv-sdk {netrans_path}/pnna_sdk \
|
||||
--output-path {generate_path}/{name}_{quantization_type}"
|
||||
else:
|
||||
if not os.path.exists(f"{name}_{quantization_type}.quantize"):
|
||||
print(f"\033[31m Can not find {name}_{quantization_type}.quantize \033[0m")
|
||||
sys.exit(1)
|
||||
else :
|
||||
if not os.path.exists(f"{name}_postprocess_file.yml"):
|
||||
cmd = f"{ovxgenerator} \
|
||||
--model {name}.json \
|
||||
--model-data {name}.data \
|
||||
--dtype {type_} \
|
||||
--pack-nbg-viplite \
|
||||
--optimize 'VIP8000NANOQI_PLUS_PID0XB1'\
|
||||
--viv-sdk {netrans_path}/pnna_sdk \
|
||||
--model-quantize {name}_{quantization_type}.quantize \
|
||||
--with-input-meta {name}_inputmeta.yml \
|
||||
--target-ide-project 'linux64' \
|
||||
--output-path {generate_path}/{quantization_type}"
|
||||
else:
|
||||
cmd = f"{ovxgenerator} \
|
||||
--model {name}.json \
|
||||
--model-data {name}.data \
|
||||
--dtype {type_} \
|
||||
--pack-nbg-viplite \
|
||||
--optimize 'VIP8000NANOQI_PLUS_PID0XB1'\
|
||||
--viv-sdk {netrans_path}/pnna_sdk \
|
||||
--model-quantize {name}_{quantization_type}.quantize \
|
||||
--with-input-meta {name}_inputmeta.yml \
|
||||
--target-ide-project 'linux64' \
|
||||
--postprocess-file {name}_postprocess_file.yml \
|
||||
--output-path {generate_path}/{quantization_type}"
|
||||
|
||||
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
if result.returncode == 0:
|
||||
print("\033[31m SUCCESS \033[0m")
|
||||
else:
|
||||
print(f"\033[31m ERROR ! {result.stderr} \033[0m")
|
||||
|
||||
|
||||
# temp='wksp/temp'
|
||||
# os.makedirs(temp, exist_ok=True)
|
||||
|
||||
source_dir = f"{generate_path}_nbg_viplite"
|
||||
target_dir = generate_path
|
||||
src_ngb = f"{source_dir}/network_binary.nb"
|
||||
if self.profile:
|
||||
try:
|
||||
# 如果目标路径已存在，先删除（确保移动操作能成功）
|
||||
if os.path.exists(target_dir):
|
||||
shutil.rmtree(target_dir)
|
||||
# 移动整个目录到目标位置
|
||||
shutil.move(source_dir, target_dir)
|
||||
# print(f"Successfully moved directory {source_dir} to {target_dir}")
|
||||
except Exception as e:
|
||||
sys.exit(1) # 非零退出码表示错误
|
||||
# print(f"Error moving directory: {e}")
|
||||
else:
|
||||
try:
|
||||
# 仅复制network_binary.nb文件
|
||||
shutil.rmtree(generate_path)
|
||||
os.mkdir(generate_path)
|
||||
shutil.copy(src_ngb, generate_path)
|
||||
|
||||
# print(f"Successfully copied {src_ngb} to {generate_path}")
|
||||
except FileNotFoundError:
|
||||
print(f"Error: {src_ngb} is not found")
|
||||
except Exception as e:
|
||||
print(f"Error occurred: {e}")
|
||||
|
||||
try:
|
||||
# 清理源目录
|
||||
shutil.rmtree(source_dir)
|
||||
# print(f"Removed source directory {source_dir}")
|
||||
except Exception as e:
|
||||
# print(f"Error removing directory: {e}")
|
||||
sys.exit(1) # 非零退出码表示错误
|
||||
|
||||
def main():
|
||||
# 检查命令行参数数量
|
||||
if len(sys.argv) < 3:
|
||||
print("Input a network name and quantized type ( float / uint8 / int8 / int16 )")
|
||||
sys.exit(1)
|
||||
# 检查网络目录是否存在
|
||||
network_name = sys.argv[1]
|
||||
# check_env(network_name)
|
||||
if not os.path.exists(os.path.exists(network_name)):
|
||||
print(f"Directory {network_name} does not exist !")
|
||||
sys.exit(2)
|
||||
|
||||
netrans_path = os.environ['NETRANS_PATH']
|
||||
# netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')
|
||||
# 调用导出函数ss
|
||||
cla = create_cls(netrans_path, network_name, sys.argv[2])
|
||||
func = Export(cla)
|
||||
func.export_network()
|
||||
|
||||
# export_network(netrans, network_name, sys.argv[2])
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
__all__ = ['extensions']
|
||||
|
||||
class model_extensions:
|
||||
def __init__(self, model, model_data, model_quantize, input_meta, output_meta):
|
||||
self._model = model
|
||||
self._model_data = model_data
|
||||
self._model_quantize = model_quantize
|
||||
self._input_meta = input_meta
|
||||
self._output_meta = output_meta
|
||||
|
||||
@property
|
||||
def model(self):
|
||||
return self._model
|
||||
|
||||
@property
|
||||
def model_data(self):
|
||||
return self._model_data
|
||||
|
||||
@property
|
||||
def model_quantize(self):
|
||||
return self._model_quantize
|
||||
|
||||
@property
|
||||
def input_meta(self):
|
||||
return self._input_meta
|
||||
|
||||
@property
|
||||
def output_meta(self):
|
||||
return self._output_meta
|
||||
|
||||
class file_model:
|
||||
def __init__(self,extensions):
|
||||
self._extensions = extensions
|
||||
|
||||
@property
|
||||
def extensions(self):
|
||||
return self._extensions
|
||||
|
||||
x_extensions = model_extensions(
|
||||
'.json',
|
||||
'.data',
|
||||
'.quantize',
|
||||
'_inputmeta.yml',
|
||||
'.yml'
|
||||
)
|
||||
|
||||
_file_model = file_model(x_extensions)
|
||||
|
||||
extensions = _file_model.extensions
|
||||
|
|
@ -1,316 +0,0 @@
|
|||
import os
|
||||
import sys
|
||||
import subprocess
|
||||
from utils import check_path, AttributeCopier, create_cls
|
||||
|
||||
def check_status(result):
|
||||
"""解析命令执行情况
|
||||
|
||||
Args:
|
||||
result (return of subprocrss.run): subprocess.run的返回值
|
||||
"""
|
||||
if result.returncode == 0:
|
||||
print("\033[31m LOAD MODEL SUCCESS \033[0m")
|
||||
else:
|
||||
print(f"\033[31m ERROR: {result.stderr} \033[0m")
|
||||
|
||||
|
||||
def import_caffe_network(name, netrans_path):
|
||||
"""导入 caffe 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的路径
|
||||
convert_caffe =netrans_path + " import caffe"
|
||||
|
||||
# 定义模型文件路径
|
||||
model_json_path = f"{name}.json"
|
||||
model_data_path = f"{name}.data"
|
||||
model_prototxt_path = f"{name}.prototxt"
|
||||
model_caffemodel_path = f"{name}.caffemodel"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} Caffe model ===========")
|
||||
|
||||
# 构建转换命令
|
||||
if os.path.isfile(model_caffemodel_path):
|
||||
cmd = f"{convert_caffe} \
|
||||
--model {model_prototxt_path} \
|
||||
--weights {model_caffemodel_path} \
|
||||
--output-model {model_json_path} \
|
||||
--output-data {model_data_path}"
|
||||
else:
|
||||
print("=========== fake Caffe model data file =============")
|
||||
cmd = f"{convert_caffe} \
|
||||
--model {model_prototxt_path} \
|
||||
--output-model {model_json_path} \
|
||||
--output-data {model_data_path}"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
# os.system(cmd)
|
||||
return cmd
|
||||
|
||||
def import_tensorflow_network(name, netrans_path):
|
||||
"""导入 tensorflow 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的命令
|
||||
convertf_cmd = f"{netrans_path} import tensorflow"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} Tensorflow model ===========")
|
||||
|
||||
# 读取 inputs_outputs.txt 文件中的参数
|
||||
with open('inputs_outputs.txt', 'r') as f:
|
||||
inputs_outputs_params = f.read().strip()
|
||||
|
||||
# 构建转换命令
|
||||
cmd = f"{convertf_cmd} \
|
||||
--model {name}.pb \
|
||||
--output-data {name}.data \
|
||||
--output-model {name}.json \
|
||||
{inputs_outputs_params}"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
return cmd
|
||||
|
||||
# result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
# check_status(result)
|
||||
|
||||
def import_onnx_network(name, netrans_path):
|
||||
"""导入 onnx 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的命令
|
||||
convert_onnx_cmd = f"{netrans_path} import onnx"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} ONNX model ===========")
|
||||
if os.path.exists(f"{name}_outputs.txt"):
|
||||
output_path = os.path.join(os.getcwd(), name+"_outputs.txt")
|
||||
with open(output_path, 'r', encoding='utf-8') as file:
|
||||
outputs = str(file.readline().strip())
|
||||
|
||||
cmd = f"{convert_onnx_cmd} \
|
||||
--model {name}.onnx \
|
||||
--output-model {name}.json \
|
||||
--output-data {name}.data \
|
||||
--outputs '{outputs}'"
|
||||
else:
|
||||
# 构建转换命令
|
||||
cmd = f"{convert_onnx_cmd} \
|
||||
--model {name}.onnx \
|
||||
--output-model {name}.json \
|
||||
--output-data {name}.data"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
return cmd
|
||||
|
||||
# result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
# check_status(result)
|
||||
|
||||
####### TFLITE
|
||||
def import_tflite_network(name, netrans_path):
|
||||
"""导入 tflite 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的路径或命令
|
||||
convert_tflite = f"{netrans_path} import tflite"
|
||||
|
||||
# 定义模型文件路径
|
||||
model_json_path = f"{name}.json"
|
||||
model_data_path = f"{name}.data"
|
||||
model_tflite_path = f"{name}.tflite"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} TFLite model ===========")
|
||||
|
||||
# 构建转换命令
|
||||
cmd = f"{convert_tflite} \
|
||||
--model {model_tflite_path} \
|
||||
--output-model {model_json_path} \
|
||||
--output-data {model_data_path}"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
return cmd
|
||||
|
||||
# result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
# check_status(result)
|
||||
|
||||
|
||||
def import_darknet_network(name, netrans_path):
|
||||
"""导入 darknet 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的命令
|
||||
convert_darknet_cmd = f"{netrans_path} import darknet"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} darknet model ===========")
|
||||
|
||||
# 构建转换命令
|
||||
cmd = f"{convert_darknet_cmd} \
|
||||
--model {name}.cfg \
|
||||
--weight {name}.weights \
|
||||
--output-model {name}.json \
|
||||
--output-data {name}.data"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
return cmd
|
||||
|
||||
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
check_status(result)
|
||||
|
||||
def import_pytorch_network(name, netrans_path):
|
||||
"""导入 pytorch 模型
|
||||
|
||||
Args:
|
||||
name (str): 模型名字
|
||||
netrans_path (str): 模型路径
|
||||
|
||||
Returns:
|
||||
cmd (str): 生成的pnnacc 命令行, 被subprocesses执行
|
||||
"""
|
||||
# 定义转换工具的命令
|
||||
convert_pytorch_cmd = f"{netrans_path} import pytorch"
|
||||
|
||||
# 打印转换信息
|
||||
print(f"=========== Converting {name} pytorch model ===========")
|
||||
|
||||
# 读取 input_size.txt 文件中的参数
|
||||
try:
|
||||
with open('input_size.txt', 'r') as file:
|
||||
input_size_params = ' '.join(file.readlines())
|
||||
except FileNotFoundError:
|
||||
print("Error: input_size.txt not found.")
|
||||
sys.exit(1)
|
||||
|
||||
# 构建转换命令
|
||||
cmd = f"{convert_pytorch_cmd} \
|
||||
--model {name}.pt \
|
||||
--output-model {name}.json \
|
||||
--output-data {name}.data \
|
||||
{input_size_params}"
|
||||
|
||||
# 执行转换命令
|
||||
# print(cmd)
|
||||
return cmd
|
||||
|
||||
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
|
||||
# 检查执行结果
|
||||
check_status(result)
|
||||
|
||||
# 使用示例
|
||||
# import_tensorflow_network('model_name', '/path/to/NETRANS_PATH')
|
||||
class ImportModel(AttributeCopier):
|
||||
"""从实例化的 Netrans 中解析模型参数,并基于 pnnacc 导入模型
|
||||
|
||||
Args:
|
||||
Netrans (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
"""
|
||||
def __init__(self, source_obj) -> None:
|
||||
"""从实例化的 Netrans 中解析模型参数
|
||||
|
||||
Args:
|
||||
source_obj (class): 实例化的Netrans类,包含 模型信息 和 Netrans 信息
|
||||
|
||||
"""
|
||||
super().__init__(source_obj)
|
||||
# print(source_obj.__dict__)
|
||||
|
||||
@check_path
|
||||
def import_network(self):
|
||||
"""基于 pnnacc 导入模型
|
||||
|
||||
Raises:
|
||||
FileExistsError: 如果不存在模型文件则会报错 FileExistsError
|
||||
RuntimeError: 如果执行导入失败则会报 RuntimeError
|
||||
"""
|
||||
if self.verbose is True :
|
||||
print("begin load model")
|
||||
# print(self.model_path)
|
||||
print(os.getcwd())
|
||||
print(f"{self.model_name}.weights")
|
||||
name = self.model_name
|
||||
netrans_path = self.netrans
|
||||
if os.path.isfile(f"{name}.prototxt"):
|
||||
cmd = import_caffe_network(name, netrans_path)
|
||||
elif os.path.isfile(f"{name}.pb"):
|
||||
cmd = import_tensorflow_network(name, netrans_path)
|
||||
elif os.path.isfile(f"{name}.onnx"):
|
||||
cmd = import_onnx_network(name, netrans_path)
|
||||
elif os.path.isfile(f"{name}.tflite"):
|
||||
cmd = import_tflite_network(name, netrans_path)
|
||||
elif os.path.isfile(f"{name}.weights"):
|
||||
cmd = import_darknet_network(name, netrans_path)
|
||||
elif os.path.isfile(f"{name}.pt"):
|
||||
cmd = import_pytorch_network(name, netrans_path)
|
||||
else :
|
||||
raise FileExistsError("Can not find suitable model files")
|
||||
try :
|
||||
result = subprocess.run(cmd, shell=True, capture_output=True, text=True)
|
||||
except :
|
||||
raise RuntimeError("load model failed")
|
||||
# 检查执行结果
|
||||
check_status(result)
|
||||
# os.chdir("..")
|
||||
|
||||
|
||||
# def main():
|
||||
# if len(sys.argv) != 2 :
|
||||
# print("Input a network")
|
||||
# sys.exit(-1)
|
||||
|
||||
# network_name = sys.argv[1]
|
||||
# # check_env(network_name)
|
||||
|
||||
# netrans_path = os.environ['NETRANS_PATH']
|
||||
# # netrans = os.path.join(netrans_path, 'pnnacc')
|
||||
# clas = create_cls(netrans_path, network_name,verbose=False)
|
||||
# func = ImportModel(clas)
|
||||
# func.import_network()
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
|
|
@ -1,273 +0,0 @@
|
|||
import sys, os
|
||||
import subprocess
|
||||
import warnings
|
||||
|
||||
from ruamel.yaml import YAML
|
||||
from ruamel import yaml
|
||||
import file_model
|
||||
from import_model import ImportModel
|
||||
from quantize import Quantize
|
||||
from export import Export
|
||||
from config import Config
|
||||
from utils import check_path
|
||||
|
||||
# 忽略 ruamel.yaml 的安全加载警告
|
||||
warnings.simplefilter('ignore', yaml.error.UnsafeLoaderWarning)
|
||||
class Netrans():
|
||||
"""Netrans Python API，用于模型转换和量化操作。
|
||||
|
||||
提供模型加载、配置、量化和导出等功能。
|
||||
"""
|
||||
|
||||
def __init__(self, model_path, netrans=None, verbose=False):
|
||||
"""
|
||||
初始化Netrans
|
||||
|
||||
Args:
|
||||
model_path (str) : 要进行编译转换的模型工程目录.
|
||||
netrans (str) : 在没有安装 Netrans 的情况下,指定 Netrans 路径。默认为 None。
|
||||
verbose (bool, optional): 是否启用详细模式。默认为 False。
|
||||
|
||||
Returns :
|
||||
None
|
||||
"""
|
||||
self.verbose = verbose
|
||||
if not os.path.exists(model_path):
|
||||
raise FileNotFoundError(f"Directory not found: {model_path}")
|
||||
self.model_path = os.path.abspath(model_path)
|
||||
self.model_name = os.path.basename(self.model_path)
|
||||
self._set_netrans_path(netrans)
|
||||
|
||||
def model2nbg(self, quantize_type, inputmeta=False, **kargs):
|
||||
"""
|
||||
模型快速转换成NBG
|
||||
|
||||
Args:
|
||||
quantize_type (_type_): 量化类型，支持 uint8, int8, int16。
|
||||
inputmeta (bool, optional): 是否进行参数配置。默认为 False。
|
||||
**kwargs: 其他可选参数。
|
||||
"""
|
||||
self.load()
|
||||
self.config(inputmeta, **kargs)
|
||||
self.quantize(quantize_type, **kargs)
|
||||
self.export(**kargs)
|
||||
|
||||
|
||||
def _get_os_netrans_path(self):
|
||||
"""
|
||||
获取系统环境变量中的 NETRANS_PATH。
|
||||
|
||||
Returns:
|
||||
str: 如果存在 NETRANS_PATH，则返回路径；否则返回 None
|
||||
"""
|
||||
return os.environ.get('NETRANS_PATH')
|
||||
|
||||
def _set_netrans_path(self, netrans_path=None):
|
||||
"""
|
||||
设置 Netrans 路径。
|
||||
如果未设置环境变量 NETRANS_PATH，则可以通过此参数指定。
|
||||
|
||||
Args:
|
||||
netrans_path (str, optional): 如果未设置环境变量 NETRANS_PATH，则可以通过此参数指定。
|
||||
"""
|
||||
if netrans_path is not None :
|
||||
netrans_path = os.path.abspath(netrans_path)
|
||||
else :
|
||||
netrans_path = self._get_os_netrans_path()
|
||||
if not os.path.exists(netrans_path):
|
||||
raise FileExistsError('未找到 Netrans 路径，请设置 NETRANS_PATH 或指定 netrans_path 参数')
|
||||
self.netrans = os.path.join(netrans_path, 'pnnacc')
|
||||
self.netrans_path = netrans_path
|
||||
|
||||
def config(self, inputmeta=False, **kwargs):
|
||||
"""
|
||||
用户处理inputmate的入口,和shell一致所以叫config.
|
||||
根据用户的实际场景,设置inputmeta参数swith对应的分支
|
||||
False: 生成inputmeta
|
||||
True:使用原本的inputmeta
|
||||
str:使用指定的inputmeta
|
||||
|
||||
Args:
|
||||
inputmeta (bool or str, optional): 是否更新模型转换配置参数。
|
||||
- 如果为 False，则自动生成配置文件。
|
||||
- 如果为字符串，则直接使用指定的配置文件路径。
|
||||
**kwargs: 其他可选参数，如 mean、scale、reverse_channel 等。
|
||||
Raises:
|
||||
FileNotFoundError: 没有找到指定的模型转换配置文件，请重新生成
|
||||
FileExistsError: 没有找到指定的模型转换配置文件，请重新生成
|
||||
"""
|
||||
self.input_meta = os.path.join(self.model_path,'%s%s'%(self.model_name, file_model.extensions.input_meta))
|
||||
if isinstance(inputmeta, str):
|
||||
self.input_meta = inputmeta
|
||||
elif isinstance(inputmeta, bool):
|
||||
if inputmeta is False :
|
||||
self._config_gen_inputmeta_file()
|
||||
else :
|
||||
raise ValueError("inputmeta 参数无效，请设置为 False 或指定配置文件路径")
|
||||
if not os.path.exists(self.input_meta):
|
||||
raise FileExistsError(f"未找到配置文件: {self.input_meta}")
|
||||
if kwargs:
|
||||
self._update_config(**kwargs)
|
||||
|
||||
def _update_config(self, **kwargs):
|
||||
"""
|
||||
如果用户通过kwargs[配置预处理参数,则调用该函数更新配置文件中的参数。
|
||||
包括文件读写和更新
|
||||
|
||||
Args:
|
||||
kwargs (dict): 包含需要更新的参数，如 mean、scale、reverse_channel 等。
|
||||
"""
|
||||
with open(self.input_meta, 'r') as f:
|
||||
yaml = YAML()
|
||||
data = yaml.load(f)
|
||||
data = self._update_config_data(data, **kwargs)
|
||||
with open(self.input_meta, 'w') as f:
|
||||
yaml.dump(data, f)
|
||||
|
||||
|
||||
def _update_config_data(self, data, **kwargs):
|
||||
"""
|
||||
更新配置文件中的参数。
|
||||
|
||||
Args:
|
||||
data (dict): 加载的配置文件内容。
|
||||
**kwargs: 需要更新的参数。
|
||||
"""
|
||||
grey = data['input_meta']['databases'][0]['ports'][0]['preprocess']['preproc_node_params']['preproc_type'] == 'IMAGE_GRAY'
|
||||
if 'mean' in kwargs:
|
||||
mean = self._format_preprocess_param(kwargs['mean'], grey)
|
||||
data = self._upload_config_mean(data, mean)
|
||||
if 'scale' in kwargs:
|
||||
scale = self._format_preprocess_param(kwargs['scale'], grey)
|
||||
data = self._upload_config_scale(data, scale)
|
||||
if 'reverse_channel' in kwargs:
|
||||
data = self._upload_config_reverse_channel(data, kwargs['reverse_channel'])
|
||||
return data
|
||||
|
||||
|
||||
def _upload_config_mean(self, data, mean):
|
||||
"""
|
||||
更新配置文件中的mean值
|
||||
|
||||
Args:
|
||||
data (yaml): yaml.load 加载的配置文件
|
||||
mean (list): 需要更新的mean值
|
||||
"""
|
||||
for db in data['input_meta']['databases']:
|
||||
db['ports'][0]['preprocess']['mean'] = mean
|
||||
return data
|
||||
def _upload_config_scale(self, data, scale):
|
||||
"""
|
||||
scale
|
||||
|
||||
Args:
|
||||
data (yaml): yaml.load 加载的配置文件
|
||||
scale (list): 需要更新的 scale 值
|
||||
"""
|
||||
for db in data['input_meta']['databases']:
|
||||
db['ports'][0]['preprocess']['scale'] = scale
|
||||
return data
|
||||
|
||||
def _upload_config_reverse_channel(self, data, reverse_channel):
|
||||
"""
|
||||
更新配置文件中的reverse_channel
|
||||
|
||||
Args:
|
||||
data (yaml): yaml.load 加载的配置文件
|
||||
reverse_channel (bool): 需要更新的reverse_channel
|
||||
"""
|
||||
for db in data['input_meta']['databases']:
|
||||
db['ports'][0]['preprocess']['reverse_channel'] = reverse_channel
|
||||
return data
|
||||
|
||||
def _format_preprocess_param(self, param, grey=False):
|
||||
"""
|
||||
用于 update model config.
|
||||
在模型预处理参数更新的时候,灰度图像仅有一个C,而RGB图像存在三个 channel,
|
||||
因此,用户输入的 scale 和 mean 为一个值的时候,需要将其转换成列表
|
||||
同时根据图像类型调整为 list.length() == channel
|
||||
处理参数，根据图像类型调整参数格式。
|
||||
|
||||
Args:
|
||||
param: 参数值，可以是单个值或列表。
|
||||
grey (bool, optional): 是否为灰度图像。默认为 False。
|
||||
|
||||
Returns:
|
||||
list: 处理后的参数值。
|
||||
"""
|
||||
ch = 1 if grey else 3
|
||||
if isinstance(param, (int, float)):
|
||||
return [float(param)] * ch
|
||||
if isinstance(param, (list, tuple)):
|
||||
if len(param) != ch:
|
||||
raise ValueError(
|
||||
f"灰度图需 1 个值，RGB 图需 3 个值，"
|
||||
f"当前通道数={ch}，但提供 {len(param)} 个值"
|
||||
)
|
||||
return [float(v) for v in param]
|
||||
raise TypeError("mean / scale 必须是数字或 list/tuple")
|
||||
|
||||
def _verify_preprocess_value(self):
|
||||
"""单元测试中用于判断是否成功修改配置文件中的参数
|
||||
|
||||
Returns:
|
||||
dict : 获取配置文件中的参数
|
||||
"""
|
||||
with open(self.input_meta,'r') as f :
|
||||
yaml = YAML()
|
||||
data = yaml.load(f)
|
||||
res = {}
|
||||
for db in data['input_meta']['databases']:
|
||||
res['scale'] = db['ports'][0]['preprocess']['scale']
|
||||
res['mean'] = db['ports'][0]['preprocess']['mean']
|
||||
res['reverse_channel'] = db['ports'][0]['preprocess']['reverse_channel']
|
||||
return res
|
||||
|
||||
|
||||
def load(self):
|
||||
"""
|
||||
加载模型
|
||||
"""
|
||||
func = ImportModel(self)
|
||||
func.import_network()
|
||||
|
||||
def _config_gen_inputmeta_file(self):
|
||||
"""
|
||||
自动生成配置文件
|
||||
"""
|
||||
func = Config(self)
|
||||
func.inputmeta_gen()
|
||||
|
||||
|
||||
def quantize(self, quantize_type,**kargs):
|
||||
"""
|
||||
量化模型
|
||||
|
||||
Args:
|
||||
quantize_type (_type_): 量化类型，支持 uint8, int8, int16
|
||||
|
||||
Raises:
|
||||
TypeError: 仅支持量化成 uint8, int8, int16
|
||||
"""
|
||||
if quantize_type not in ['uint8', 'int8', 'int16']:
|
||||
raise TypeError(f"不支持的量化类型: {quantize_type}，仅支持 uint8, int8, int16")
|
||||
self.quantize_type = quantize_type
|
||||
Quantize(self).quantize_network()
|
||||
|
||||
def export(self, **kwargs):
|
||||
"""模型导出
|
||||
"""
|
||||
if 'quantize_type' in kwargs:
|
||||
self.quantize_type = kwargs['quantize_type']
|
||||
if 'profile' in kwargs:
|
||||
self.profile = kwargs['profile']
|
||||
else:
|
||||
self.profile = False
|
||||
Export(self).export_network()
|
||||
|
||||
# 示例用法
|
||||
if __name__ == '__main__':
|
||||
network = '../../model_zoo/yolov4_tiny'
|
||||
yolo = Netrans(network)
|
||||
yolo._config_gen_inputmeta_file()
|
||||
yolo.model2nbg("uint8")
|
||||
|
|
@ -1,105 +0,0 @@
|
|||
import os
|
||||
import sys
|
||||
from utils import check_path, AttributeCopier, create_cls
|
||||
|
||||
class Quantize(AttributeCopier):
|
||||
"""
|
||||
解析 Netrans 参数，基于 pnnacc 量化模型
|
||||
Args:
|
||||
cla (class): 实例化以后的 Netrans 类，需要解析里面包含的参数
|
||||
"""
|
||||
def __init__(self, source_obj) -> None:
|
||||
"""
|
||||
从 Netrans 类中获取模型信息
|
||||
Args:
|
||||
source_obj (class): 实例化以后的 Netrans 类，需要解析里面包含的参数
|
||||
"""
|
||||
super().__init__(source_obj)
|
||||
|
||||
@check_path
|
||||
def quantize_network(self):
|
||||
"""基于 pnnacc 量化模型
|
||||
"""
|
||||
netrans = self.netrans
|
||||
quantized_type = self.quantize_type
|
||||
name = self.model_name
|
||||
# check_env(name)
|
||||
# print(os.getcwd())
|
||||
netrans += " quantize"
|
||||
# 根据量化类型设置量化参数
|
||||
if quantized_type == 'float':
|
||||
print("=========== do not need quantized===========")
|
||||
return
|
||||
elif quantized_type == 'uint8':
|
||||
quantization_type = "asymmetric_affine"
|
||||
elif quantized_type == 'int8':
|
||||
quantization_type = "dynamic_fixed_point-8"
|
||||
elif quantized_type == 'int16':
|
||||
quantization_type = "dynamic_fixed_point-16"
|
||||
else:
|
||||
print("=========== wrong quantization_type ! ( uint8 / int8 / int16 )===========")
|
||||
return
|
||||
|
||||
# 输出量化信息
|
||||
print(" =======================================================================")
|
||||
print(f" ==== Start Quantizing {name} model with type of {quantization_type} ===")
|
||||
print(" =======================================================================")
|
||||
current_directory = os.getcwd()
|
||||
txt_path = current_directory+"/dataset.txt"
|
||||
with open(txt_path, 'r', encoding='utf-8') as file:
|
||||
num_lines = len(file.readlines())
|
||||
|
||||
# 移除已存在的量化文件
|
||||
quantize_file = f"{name}_{quantization_type}.quantize"
|
||||
if os.path.exists(quantize_file):
|
||||
print(f"\033[31m rm {quantize_file} \033[0m")
|
||||
os.remove(quantize_file)
|
||||
|
||||
# 构建并执行量化命令
|
||||
cmd = f"{netrans} \
|
||||
--batch-size 1 \
|
||||
--qtype {quantized_type} \
|
||||
--rebuild \
|
||||
--quantizer {quantization_type.split('-')[0]} \
|
||||
--model-quantize {quantize_file} \
|
||||
--model {name}.json \
|
||||
--model-data {name}.data \
|
||||
--with-input-meta {name}_inputmeta.yml \
|
||||
--device CPU \
|
||||
--algorithm kl_divergence \
|
||||
--iterations {num_lines}"
|
||||
|
||||
os.system(cmd)
|
||||
|
||||
# 检查量化结果
|
||||
if os.path.exists(quantize_file):
|
||||
print("\033[31m QUANTIZED SUCCESS \033[0m")
|
||||
else:
|
||||
print("\033[31m ERROR ! \033[0m")
|
||||
|
||||
|
||||
# def main():
|
||||
# # 检查命令行参数数量
|
||||
# if len(sys.argv) < 3:
|
||||
# print("Input a network name and quantized type ( uint8 / int8 / int16 )")
|
||||
# sys.exit(-1)
|
||||
|
||||
# # 检查网络目录是否存在
|
||||
# network_name = sys.argv[1]
|
||||
|
||||
# # 定义 netrans 路径
|
||||
# # netrans = os.path.join(os.environ['NETRANS_PATH'], 'pnnacc')
|
||||
# # network_name = sys.argv[1]
|
||||
# # check_env(network_name)
|
||||
|
||||
# netrans_path = os.environ['NETRANS_PATH']
|
||||
# # netrans = os.path.join(netrans_path, 'pnnacc')
|
||||
# quantize_type = sys.argv[2]
|
||||
# cla = create_cls(netrans_path, network_name,quantize_type)
|
||||
|
||||
# # 调用量化函数
|
||||
# run = Quantize(cla)
|
||||
# run.quantize_network()
|
||||
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
from setuptools import setup, find_packages
|
||||
|
||||
|
||||
setup(
|
||||
name="netrans",
|
||||
version="0.1.0",
|
||||
author="nudt_dsp",
|
||||
url="https://gitlink.org.cn/gwg_xujiao/netrans",
|
||||
packages=find_packages(include=["netrans_py"]),
|
||||
package_dir={"": "."}, # 指定根目录映射关系[8](@ref)
|
||||
install_requires=[
|
||||
"ruamel.yaml==0.18.6"
|
||||
]
|
||||
)
|
||||
|
|
@ -1,109 +0,0 @@
|
|||
import sys
|
||||
import os
|
||||
# from functools import wraps
|
||||
|
||||
# def check_path(netrans, model_path):
|
||||
# def decorator(func):
|
||||
# @wraps(func)
|
||||
# def wrapper(netrans, model_path, *args, **kargs):
|
||||
# check_dir(model_path)
|
||||
# check_netrans(netrans)
|
||||
# if os.getcwd() != model_path :
|
||||
# os.chdir(model_path)
|
||||
# return func(netrans, model_path, *args, **kargs)
|
||||
# return wrapper
|
||||
# return decorator
|
||||
|
||||
def check_path(func):
|
||||
""" 装饰器, 确保在工程目录运行 nertans
|
||||
|
||||
"""
|
||||
def wrapper(cla, *args, **kargs):
|
||||
check_netrans(cla.netrans)
|
||||
if os.getcwd() != cla.model_path :
|
||||
os.chdir(cla.model_path)
|
||||
return func(cla, *args, **kargs)
|
||||
return wrapper
|
||||
|
||||
|
||||
def check_dir(network_name):
|
||||
"""判断工程目录是否存在
|
||||
|
||||
Args:
|
||||
network_name (str): 工程目录路径
|
||||
|
||||
Raises:
|
||||
NotADirectoryError: 没有那个工程目录
|
||||
"""
|
||||
if not os.path.exists(network_name):
|
||||
raise NotADirectoryError(
|
||||
f"Directory not found: {network_name}"
|
||||
)
|
||||
# print(f"Directory {network_name} does not exist !")
|
||||
# sys.exit(-1)
|
||||
os.chdir(network_name)
|
||||
|
||||
def check_netrans(netrans):
|
||||
"""判断 netrans 是否配置成功
|
||||
|
||||
Args:
|
||||
netrans (str, bool): _netrans 路径, 如果没有配置(默认为False)会去环境变量里找
|
||||
|
||||
Raises:
|
||||
NotADirectoryError: 找不到 Netrans 会返回 NotADirectoryError
|
||||
"""
|
||||
if netrans != None and os.path.exists(netrans) is True:
|
||||
return
|
||||
if 'NETRANS_PATH' in os.environ :
|
||||
return
|
||||
raise NotADirectoryError(
|
||||
f"Netrans not found: {netrans}"
|
||||
)
|
||||
|
||||
|
||||
def remove_history_file(name):
|
||||
os.chdir(name)
|
||||
if os.path.isfile(f"{name}.json"):
|
||||
os.remove(f"{name}.json")
|
||||
if os.path.isfile(f"{name}.data"):
|
||||
os.remove(f"{name}.data")
|
||||
os.chdir('..')
|
||||
|
||||
def check_env(name):
|
||||
check_dir(name)
|
||||
# check_netrans()
|
||||
# remove_history_file(name)
|
||||
|
||||
|
||||
class AttributeCopier:
|
||||
"""快速解析复制 Netrans 信息
|
||||
"""
|
||||
def __init__(self, source_obj) -> None:
|
||||
self.copy_attribute_name(source_obj)
|
||||
|
||||
def copy_attribute_name(self, source_obj):
|
||||
for attribute_name in self._get_attribute_names(source_obj):
|
||||
setattr(self, attribute_name, getattr(source_obj, attribute_name))
|
||||
|
||||
@staticmethod
|
||||
def _get_attribute_names(source_obj):
|
||||
return source_obj.__dict__.keys()
|
||||
|
||||
class create_cls(): #dataclass @netrans_params
|
||||
"""快速测试时候模拟实例化Netrans"""
|
||||
def __init__(self, netrans_path, name, quantized_type = 'uint8',verbose=False) -> None:
|
||||
self.netrans_path = netrans_path
|
||||
self.netrans = os.path.join(self.netrans_path, 'pnnacc')
|
||||
self.model_name=self.model_path = name
|
||||
self.model_path = os.path.abspath(self.model_path)
|
||||
self.verbose=verbose
|
||||
self.quantize_type = quantized_type
|
||||
self.profile = False
|
||||
|
||||
|
||||
# if __name__ == "__main__":
|
||||
# dir_name = "yolo"
|
||||
# os.mkdir(dir_name)
|
||||
# check_dir(dir_name)
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,11 @@
|
|||
scipy==1.14.1
|
||||
tensorflow==2.17.0
|
||||
protobuf==3.20.3
|
||||
networkx==3.3
|
||||
onnx==1.16.2
|
||||
onnxoptimizer==0.3.13
|
||||
dill==0.2.8.2
|
||||
ruamel.yaml==0.17.40
|
||||
ply==3.11
|
||||
numpy==1.26.4
|
||||
torch==2.3.0
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/sh
|
||||
exec python3 -m add_prepost_to_graph "$@"
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/sh
|
||||
exec "$(dirname "$0")/../.venv/bin/python" -m script.dump "$@"
|
||||
|
|
@ -0,0 +1,113 @@
|
|||
#!/usr/bin/env python3
|
||||
from argparse import ArgumentParser
|
||||
import os
|
||||
import sys
|
||||
from quantize_types import QuantizerType
|
||||
from utils import *
|
||||
|
||||
import importlib
|
||||
try:
|
||||
importlib.import_module("acuitylib")
|
||||
except:
|
||||
ACUITY_PATH = os.environ['ACUITY_PATH']
|
||||
sys.path.append(ACUITY_PATH)
|
||||
|
||||
from acuitylib.vsi_nn import VSInn
|
||||
|
||||
def load_net(model_filename, quantized, use_hybrid=False):
|
||||
nn = VSInn()
|
||||
net = nn.create_net()
|
||||
|
||||
if not use_hybrid:
|
||||
model = model_filename + ".json"
|
||||
else:
|
||||
model = model_filename + "_" + quantized + "_hy.quantize.json"
|
||||
data = model_filename + ".data"
|
||||
inputmeta = model_filename + "_inputmeta.yml"
|
||||
|
||||
if os.path.exists(model) is True:
|
||||
nn.load_model(net, model)
|
||||
else:
|
||||
print("{} file does not exists.".format(model))
|
||||
sys.exit(1)
|
||||
|
||||
if os.path.exists(data) is True:
|
||||
nn.load_model_data(net, data)
|
||||
else:
|
||||
print("{} file does not exists.".format(data))
|
||||
sys.exit(1)
|
||||
|
||||
if os.path.exists(inputmeta) is True:
|
||||
nn.load_model_inputmeta(net, inputmeta)
|
||||
else:
|
||||
print("{} file does not exists.".format(inputmeta))
|
||||
sys.exit(1)
|
||||
|
||||
if quantized != "float32":
|
||||
if not use_hybrid:
|
||||
model_quantize = model_filename + '_' + quantized + ".quantize"
|
||||
else:
|
||||
model_quantize = model_filename + '_' + quantized + "_hy.quantize"
|
||||
if os.path.exists(model_quantize) is True:
|
||||
nn.load_model_quantize(net, model_quantize)
|
||||
else:
|
||||
print('{} does not exist'.format(model_quantize))
|
||||
sys.exit(1)
|
||||
return net
|
||||
|
||||
def dump(net, model_filename, quantized='asymu8', use_hybrid=False):
|
||||
nn = VSInn()
|
||||
if not use_hybrid:
|
||||
quantize_file = model_filename + '_' + quantized + ".quantize"
|
||||
model = model_filename + ".json"
|
||||
output_dir = 'dump/{}_{}/'.format(model_filename, quantized)
|
||||
else:
|
||||
# add hybrid quantize for print log
|
||||
quantize_file = model_filename + '_' + quantized + "_hy.quantize"
|
||||
model = model_filename + '_' + quantized + "_hy.quantize.json"
|
||||
# add hybrid quantize output file name
|
||||
output_dir = 'dump/{}_{}/'.format(model_filename, quantized + "_hy")
|
||||
|
||||
if quantized != "float32":
|
||||
print_params(nn.dump, model=model, data=model_filename + ".data", quantize=quantize_file,
|
||||
with_input_meta=model_filename + "_inputmeta.yml", output_path=output_dir)
|
||||
else:
|
||||
print_params(nn.dump, model=model, data=model_filename + ".data",
|
||||
with_input_meta=model_filename + "_inputmeta.yml", output_path=output_dir)
|
||||
nn.dump(net, output_path=output_dir)
|
||||
|
||||
|
||||
def main():
|
||||
options = ArgumentParser()
|
||||
options.add_argument("model", type=str, help="Model directory")
|
||||
options.add_argument("quantized", type=str, help="Quantization type, including float32, " + ', '.join(list(QuantizerType.get_options()))
|
||||
+ ", \'float32\' means not quantized.")
|
||||
options.add_argument("--use_hybrid", action="store_true",
|
||||
help="if you use hybrid quantize,please set this --use_hybrid")
|
||||
|
||||
args = options.parse_args()
|
||||
print(args)
|
||||
if os.path.exists(args.model) and os.path.isdir(os.path.abspath(args.model)):
|
||||
model_filename = get_modelfile_name(args.model)
|
||||
if model_filename is None:
|
||||
print("Please enter the path that includes the model.")
|
||||
os.chdir(args.model)
|
||||
else:
|
||||
model_filename = args.model
|
||||
quantized = args.quantized
|
||||
use_hybrid = args.use_hybrid
|
||||
|
||||
quantized_format = QuantizerType.get_options()
|
||||
if quantized not in quantized_format and quantized != 'float32':
|
||||
print("Please enter the correct quantization format.")
|
||||
quantized_format.insert(0, 'float32')
|
||||
print(list(quantized_format))
|
||||
sys.exit(1)
|
||||
|
||||
# load net
|
||||
net = load_net(model_filename, quantized, use_hybrid)
|
||||
#dump
|
||||
dump(net, model_filename, quantized, use_hybrid)
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
#!/bin/sh
|
||||
|
||||
# 检查参数数量
|
||||
if [ "$#" -eq 2 ]; then
|
||||
exec python3 -m export_nbg "$1" "$2" VIP8000NANOQI_PLUS_PID0XB1
|
||||
else
|
||||
exec python3 -m export_nbg "$1" "$2" VIP8000NANOQI_PLUS_PID0XB1 "${@:3}"
|
||||
fi
|
||||
|
|
@ -0,0 +1,169 @@
|
|||
#!/usr/bin/env python3
|
||||
from argparse import ArgumentParser
|
||||
import os
|
||||
import sys
|
||||
from quantize_types import QuantizerType
|
||||
from utils import *
|
||||
from measure import *
|
||||
|
||||
import importlib
|
||||
try:
|
||||
importlib.import_module("acuitylib")
|
||||
except:
|
||||
ACUITY_PATH = os.environ['ACUITY_PATH']
|
||||
sys.path.append(ACUITY_PATH)
|
||||
|
||||
from acuitylib.vsi_nn import VSInn
|
||||
|
||||
post = None
|
||||
|
||||
# load net
|
||||
def load_net(model_filename, quantized, use_hybrid=False):
|
||||
nn = VSInn()
|
||||
net = nn.create_net()
|
||||
|
||||
if not use_hybrid:
|
||||
model = model_filename + ".json"
|
||||
else:
|
||||
model = model_filename + "_" + quantized + "_hy.quantize.json"
|
||||
data = model_filename + ".data"
|
||||
inputmeta = model_filename + "_inputmeta.yml"
|
||||
postprocess = model_filename + "_postprocess_file.yml"
|
||||
|
||||
if os.path.exists(model) is True:
|
||||
nn.load_model(net, model)
|
||||
else:
|
||||
print("{} file does not exists.".format(model))
|
||||
sys.exit(1)
|
||||
|
||||
if os.path.exists(data) is True:
|
||||
nn.load_model_data(net, data)
|
||||
else:
|
||||
print("{} file does not exists.".format(data))
|
||||
sys.exit(1)
|
||||
|
||||
if os.path.exists(inputmeta) is True:
|
||||
nn.load_model_inputmeta(net, inputmeta)
|
||||
else:
|
||||
print("{} file does not exists.".format(inputmeta))
|
||||
sys.exit(1)
|
||||
|
||||
if os.path.exists(postprocess) is True:
|
||||
nn.load_model_outputmeta(net, postprocess)
|
||||
global post
|
||||
post = postprocess
|
||||
|
||||
if quantized != "float32":
|
||||
if not use_hybrid:
|
||||
model_quantize = model_filename + '_' + quantized + ".quantize"
|
||||
else:
|
||||
model_quantize = model_filename + '_' + quantized + "_hy.quantize"
|
||||
if os.path.exists(model_quantize) is True:
|
||||
nn.load_model_quantize(net, model_quantize)
|
||||
else:
|
||||
print('{} does not exist'.format(model_quantize))
|
||||
sys.exit(1)
|
||||
return net
|
||||
|
||||
# export the NBG application
|
||||
def export_nbg(net, model_filename, quantized, optimize, viv_sdk=None, use_hybrid=False):
|
||||
nn = VSInn()
|
||||
if not use_hybrid:
|
||||
quantize_file = model_filename + '_' + quantized + ".quantize"
|
||||
model = model_filename + ".json"
|
||||
output_dir = 'wksp/{}_{}'.format(model_filename, quantized)
|
||||
else:
|
||||
# add hybrid quantize for print log
|
||||
quantize_file = model_filename + '_' + quantized + "_hy.quantize"
|
||||
model = model_filename + '_' + quantized + "_hy.quantize.json"
|
||||
# add hybrid quantize output file name
|
||||
output_dir = 'wksp/{}_{}'.format(model_filename, quantized + "_hy")
|
||||
output_dir = os.path.join(output_dir, os.path.split(output_dir)[1])
|
||||
|
||||
if quantized != 'float32':
|
||||
print_params(nn.export_ovxlib, model=model, data=model_filename + ".data", quantize=quantize_file,
|
||||
with_input_meta=model_filename + "_inputmeta.yml", postprocess_file=post, output_path=output_dir,
|
||||
optimize=optimize, viv_sdk=viv_sdk, pack_nbg_unify=True)
|
||||
else:
|
||||
print_params(nn.export_ovxlib, model=model, data=model_filename + ".data",
|
||||
with_input_meta=model_filename + "_inputmeta.yml", postprocess_file=post, output_path=output_dir,
|
||||
optimize=optimize, viv_sdk=viv_sdk, pack_nbg_unify=True)
|
||||
nn.export_ovxlib(net, output_path=output_dir, dtype=quantized, optimize=optimize, viv_sdk=viv_sdk, pack_nbg_unify=True)
|
||||
|
||||
# generate the execution file cmd.sh and move the tensors generated by infernece.py
|
||||
def generate_exe_script(net, model_filename, quantized, use_hybrid=False):
|
||||
if use_hybrid:
|
||||
quantized = quantized + "_hy"
|
||||
inputs = net.get_input_layers(ign_variable=True)
|
||||
input_tensor_list = []
|
||||
for l in inputs:
|
||||
if l.is_op('input'):
|
||||
url = l.get_output().url
|
||||
input_tensor = url.replace('@', '').replace(':', '_').replace('/', '_')
|
||||
shape = l.params.shape
|
||||
dims = len(shape)
|
||||
for i in range(dims):
|
||||
if shape[i] == 0:
|
||||
shape[i] = 1
|
||||
input_tensor = input_tensor + '_' + str(shape[i])
|
||||
input_tensor = 'iter_0_' + input_tensor + '.tensor'
|
||||
input_tensor_list.append(input_tensor)
|
||||
if len(input_tensor_list) < 1:
|
||||
print("No input layer!")
|
||||
return
|
||||
else:
|
||||
wksp_dir = 'wksp/{}_{}_nbg_unify'.format(model_filename, quantized)
|
||||
target_name = '{}_{}'.format(model_filename, quantized)
|
||||
cmd_str = './{} network_binary.nb'.format(
|
||||
target_name.replace("_", "").replace("-", "").replace(".", "").replace(" ", "").lower(), target_name)
|
||||
for i in range(len(input_tensor_list)):
|
||||
cmd_str = cmd_str + ' ' + input_tensor_list[i]
|
||||
os.system('echo {} > {}/cmd.sh'.format(cmd_str, wksp_dir))
|
||||
os.system('chmod +x {}/cmd.sh'.format(wksp_dir))
|
||||
print("The executable script cmd.sh is generated.")
|
||||
|
||||
def main():
|
||||
options = ArgumentParser()
|
||||
options.add_argument("model", type=str, help="Model directory")
|
||||
options.add_argument("quantized", type=str, help="Quantization type, including float32, " + ', '.join(list(QuantizerType.get_options()))
|
||||
+ ", \'float32\' means not quantized.")
|
||||
options.add_argument("optimize", type=str,
|
||||
help="The optimization method for the export. Specify a configuration file path or "
|
||||
"a configuration name for this argument")
|
||||
options.add_argument("--viv_sdk", type=str, required=False,
|
||||
help="The file path of the directory that contains the binary SDK of VSimulator. "
|
||||
"During the execution, VSimulator generates NBG files. For example, the file path may be "
|
||||
"'/home/xxx/Verisilicon/VivanteIDEx.x.x/*cmdtools' if VivanteIDE is installed.")
|
||||
options.add_argument("--use_hybrid", action="store_true", help="if you use hybrid quantize,please set this --use_hybrid")
|
||||
|
||||
args = options.parse_args()
|
||||
print(args)
|
||||
|
||||
if os.path.exists(args.model) and os.path.isdir(os.path.abspath(args.model)):
|
||||
model_filename = get_modelfile_name(args.model)
|
||||
if model_filename is None:
|
||||
print("Please enter the path that includes the model.")
|
||||
os.chdir(args.model)
|
||||
else:
|
||||
model_filename = args.model
|
||||
quantized = args.quantized
|
||||
optimize = args.optimize
|
||||
viv_sdk = (None if args.viv_sdk is None else args.viv_sdk)
|
||||
use_hybrid = args.use_hybrid
|
||||
quantized_format = QuantizerType.get_options()
|
||||
if quantized not in quantized_format and quantized != 'float32':
|
||||
print("Please enter the correct quantization format.")
|
||||
quantized_format.insert(0, 'float32')
|
||||
print(list(quantized_format))
|
||||
sys.exit(1)
|
||||
|
||||
net = load_net(model_filename, quantized, use_hybrid)
|
||||
#export
|
||||
export_nbg(net, model_filename, quantized, optimize, viv_sdk, use_hybrid)
|
||||
generate_exe_script(net, model_filename, quantized, use_hybrid)
|
||||
# measure
|
||||
measure(net=net, model_filename=model_filename, quantized=quantized)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
@ -0,0 +1,362 @@
|
|||
#!/usr/bin/env python3
|
||||
from utils import *
|
||||
from argparse import ArgumentParser
|
||||
import numpy as np
|
||||
import os
|
||||
import sys
|
||||
|
||||
import importlib
|
||||
try:
|
||||
importlib.import_module("acuitylib")
|
||||
except:
|
||||
ACUITY_PATH = os.environ['ACUITY_PATH']
|
||||
sys.path.append(ACUITY_PATH)
|
||||
|
||||
from acuitylib.vsi_nn import VSInn
|
||||
|
||||
def read_inputs_outputs_file(inputs_outputs_file):
|
||||
args_dict = {
|
||||
"inputs": None,
|
||||
"outputs": None,
|
||||
"input_size_list": None,
|
||||
"size_with_batch": None,
|
||||
"input_dtype_list": None,
|
||||
"target_onnx_file": None,
|
||||
"predef_file": None,
|
||||
"mean_values": None,
|
||||
"std_values": None
|
||||
}
|
||||
|
||||
with open(inputs_outputs_file, 'r') as inter_file:
|
||||
args = inter_file.readlines()
|
||||
if len(args) == 1:
|
||||
args = args[0].split("--")
|
||||
for arg in args:
|
||||
if "inputs" in arg:
|
||||
args_dict["inputs"] = ' '.join(arg.split()[1:]).strip('\"').strip('\'')
|
||||
elif "outputs" in arg:
|
||||
args_dict["outputs"] = ' '.join(arg.split()[1:]).strip('\"').strip('\'')
|
||||
elif "input-size-list" in arg:
|
||||
args_dict["input_size_list"] = arg.split()[1].strip('\"').strip('\'')
|
||||
elif "size-with-batch" in arg:
|
||||
args_dict["size_with_batch"] = arg.split()[1].strip('\"').strip('\'')
|
||||
elif "input-dtype-list" in arg:
|
||||
args_dict["input_dtype_list"] = arg.split()[1].strip('\"').strip('\'')
|
||||
elif "predef-file" in arg:
|
||||
args_dict["predef_file"] = arg.split()[1]
|
||||
elif "mean-values" in arg:
|
||||
args_dict["mean_values"] = arg.split()[1].strip('\"').strip('\'')
|
||||
elif "std-values" in arg:
|
||||
args_dict["std_values"] = arg.split()[1].strip('\"').strip('\'')
|
||||
return args_dict
|
||||
|
||||
def importer(modelfile_name, save=True):
|
||||
nn = VSInn()
|
||||
|
||||
if os.path.exists(modelfile_name+'.prototxt') is True:
|
||||
prototxt = modelfile_name+'.prototxt'
|
||||
weights = modelfile_name+'.caffemodel'
|
||||
if os.path.exists(weights) is True:
|
||||
print_params(nn.load_caffe, model=prototxt, weights=weights)
|
||||
net = nn.load_caffe(model=prototxt, weights=weights)
|
||||
else:
|
||||
print_params(nn.load_caffe, model=prototxt)
|
||||
net = nn.load_caffe(model=prototxt)
|
||||
elif os.path.exists(modelfile_name+'.pb') is True:
|
||||
tf_model = modelfile_name+'.pb'
|
||||
inputs_outputs_file = 'inputs_outputs.txt'
|
||||
if os.path.exists(inputs_outputs_file) is True:
|
||||
args_dict = read_inputs_outputs_file(inputs_outputs_file)
|
||||
print_params(nn.load_tensorflow, model=tf_model, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"],
|
||||
predef_file=args_dict["predef_file"],
|
||||
mean_values = args_dict["mean_values"],
|
||||
std_values = args_dict["std_values"])
|
||||
net = nn.load_tensorflow(model=tf_model, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"],
|
||||
predef_file=args_dict["predef_file"],
|
||||
mean_values=args_dict["mean_values"],
|
||||
std_values=args_dict["std_values"]
|
||||
)
|
||||
else:
|
||||
print("{} does not exist".format(inputs_outputs_file))
|
||||
sys.exit(1)
|
||||
elif os.path.exists(modelfile_name+'.tflite') is True:
|
||||
lite_model = modelfile_name+'.tflite'
|
||||
inputs_outputs_file = 'inputs_outputs.txt'
|
||||
if os.path.exists(inputs_outputs_file) is True:
|
||||
args_dict = read_inputs_outputs_file(inputs_outputs_file)
|
||||
print_params(nn.load_tflite, model=lite_model, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"])
|
||||
net = nn.load_tflite(model=lite_model, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"])
|
||||
else:
|
||||
net = nn.load_tflite(lite_model)
|
||||
elif os.path.exists(modelfile_name+'.cfg') is True:
|
||||
darknet_file = modelfile_name+'.cfg'
|
||||
weights = modelfile_name+'.weights'
|
||||
if os.path.exists(weights) is True:
|
||||
print_params(nn.load_darknet, model=darknet_file, weights=weights)
|
||||
net = nn.load_darknet(model=darknet_file, weights=weights)
|
||||
else:
|
||||
print("{} does not exist".format(weights))
|
||||
sys.exit(1)
|
||||
elif os.path.exists(modelfile_name+'.onnx') is True:
|
||||
onnx_file = modelfile_name + '.onnx'
|
||||
inputs_outputs_file = 'inputs_outputs.txt'
|
||||
if os.path.exists(inputs_outputs_file) is True:
|
||||
args_dict = read_inputs_outputs_file(inputs_outputs_file)
|
||||
print_params(nn.load_onnx, model=onnx_file, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"],
|
||||
input_dtype_list=args_dict["input_dtype_list"])
|
||||
net = nn.load_onnx(model=onnx_file, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"],
|
||||
input_dtype_list=args_dict["input_dtype_list"])
|
||||
else:
|
||||
net = nn.load_onnx(model=onnx_file)
|
||||
elif os.path.exists(modelfile_name+'.pt') is True:
|
||||
pt_file = modelfile_name + '.pt'
|
||||
inputs_outputs_file = 'inputs_outputs.txt'
|
||||
if os.path.exists(inputs_outputs_file) is True:
|
||||
args_dict = read_inputs_outputs_file(inputs_outputs_file)
|
||||
print_params(nn.load_pytorch_by_onnx_backend, model=pt_file, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"])
|
||||
net = nn.load_pytorch_by_onnx_backend(model=pt_file, inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
size_with_batch=args_dict["size_with_batch"])
|
||||
else:
|
||||
net = nn.load_pytorch_by_onnx_backend(model=pt_file)
|
||||
elif os.path.exists(modelfile_name+".h5") is True:
|
||||
keras_file = modelfile_name+'.h5'
|
||||
inputs_outputs_file = 'inputs_outputs.txt'
|
||||
if os.path.exists(inputs_outputs_file) is True:
|
||||
args_dict = read_inputs_outputs_file(inputs_outputs_file)
|
||||
print_params(nn.load_keras, model=keras_file,
|
||||
inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
convert_engine="Keras")
|
||||
net = nn.load_keras(model=keras_file,
|
||||
inputs=args_dict["inputs"],
|
||||
input_size_list=args_dict["input_size_list"],
|
||||
outputs=args_dict["outputs"],
|
||||
convert_engine="Keras")
|
||||
else:
|
||||
net = nn.load_keras(model=keras_file)
|
||||
else:
|
||||
print("Cannot find model :{}".format(modelfile_name))
|
||||
sys.exit(1)
|
||||
|
||||
if nn.is_quantize_model is True:
|
||||
for tensor in net.tensors:
|
||||
if tensor.quant_param is not None and tensor.quant_param.qtype == 'float16':
|
||||
nn.is_quantize_model = False
|
||||
break
|
||||
|
||||
if save:
|
||||
output_model = modelfile_name + '.json'
|
||||
output_data = modelfile_name + '.data'
|
||||
|
||||
nn.save_model(net, output_model)
|
||||
nn.save_model_data(net, output_data)
|
||||
if nn.is_quantize_model is True:
|
||||
quantize_output = modelfile_name + '_asymu8' + '.quantize'
|
||||
print("!!! It's a quant model. !!!")
|
||||
print("!!! To suit the naming rule , rename to {}!!!".format(quantize_output))
|
||||
nn.save_model_quantize(net, quantize_output)
|
||||
return net, nn.is_quantize_model
|
||||
|
||||
def read_channel_mean_value_file(channel_mean_value_file, channel):
|
||||
mean_scale = []
|
||||
with open(channel_mean_value_file, 'r') as inter_file:
|
||||
line = inter_file.readline().strip()
|
||||
nums = line.split()
|
||||
if len(nums) == 1 and nums[0] == '':
|
||||
print("No data in the {}, Please enter the correct data.".format(channel_mean_value_file))
|
||||
sys.exit(1)
|
||||
else:
|
||||
for num in nums:
|
||||
mean_scale.append(float(num))
|
||||
|
||||
if len(mean_scale) == (channel + 1):
|
||||
mean = mean_scale[0:channel]
|
||||
scale_r = mean_scale[channel]
|
||||
# The scale in inputmeta.yml is equal to 1/(the scale in channel_mean_value_file)
|
||||
# the scale in channel_mean_value_file is the scale of origin platform
|
||||
scale = [1.0 / scale_r] * channel
|
||||
elif len(mean_scale) == (channel * 2):
|
||||
mean = mean_scale[0:channel]
|
||||
scale_r = mean_scale[channel:]
|
||||
scale = [1.0 / s for s in scale_r]
|
||||
else:
|
||||
print("Please enter the correct data in channel_mean_value.txt file for model preprocess.")
|
||||
sys.exit(1)
|
||||
return mean, scale
|
||||
|
||||
def preprocess(net, modelfile_name, save=True):
|
||||
nn = VSInn()
|
||||
inputs_shape = []
|
||||
inputs_lid = []
|
||||
inputs_name = []
|
||||
inputs_type = []
|
||||
preprocess_dict = {}
|
||||
inputs = net.get_input_layers(ign_variable=True)
|
||||
for l in inputs:
|
||||
if l.is_op('input'):
|
||||
inputs_lid.append(l.lid)
|
||||
preprocess_params = {}
|
||||
shape = l.params.shape
|
||||
inputs_shape.append(shape)
|
||||
inputs_name.append(l.name)
|
||||
inputs_type.append(l.params.type)
|
||||
if shape[0] == 0:
|
||||
shape[0] = 1
|
||||
preprocess_params['shape'] = shape
|
||||
fmt = net.get_org_platform_mode()
|
||||
if fmt == 'nchw':
|
||||
print("The default layout of your model is nchw, please note if it needs to changed!")
|
||||
preprocess_params['reverse_channel'] = fmt == 'nchw'
|
||||
|
||||
if len(shape) == 4:
|
||||
if fmt == 'nchw':
|
||||
channel = shape[1]
|
||||
else:
|
||||
channel = shape[-1]
|
||||
if channel == 3 or channel == 1 or channel == 4:
|
||||
channel_mean_value_file = 'channel_mean_value.txt'
|
||||
if os.path.exists(channel_mean_value_file) is True:
|
||||
mean, scale = read_channel_mean_value_file(channel_mean_value_file, channel)
|
||||
else:
|
||||
mean = [0] * channel
|
||||
scale = [1.0] * channel
|
||||
preprocess_params['mean'] = mean
|
||||
preprocess_params['scale'] = scale
|
||||
else:
|
||||
preprocess_params['scale'] = 1.0
|
||||
preprocess_dict[l.name] = preprocess_params
|
||||
|
||||
num = len(inputs_shape)
|
||||
if num == 1:
|
||||
if os.path.exists('dataset.txt') is True:
|
||||
nn.set_database(net, dataset_files='dataset.txt', dataset_type="TEXT")
|
||||
else:
|
||||
if os.path.exists("inputs") is False:
|
||||
os.system("mkdir inputs")
|
||||
input = np.random.random(inputs_shape[0]).astype(inputs_type[0])
|
||||
shape = '_'.join(str(inputs_shape[0][i]) for i in range(len(inputs_shape[0])))
|
||||
dataset_name = '{}_{}_{}.npy'.format(inputs_lid[0], shape, 0)
|
||||
dataset_name = dataset_name.replace('@', '').replace(':', '_').replace('/', '_')
|
||||
dataset_name = "./inputs/" + dataset_name
|
||||
if os.path.exists(dataset_name) is False:
|
||||
np.save(dataset_name, input)
|
||||
nn.set_database(net, dataset_files=dataset_name, dataset_type='NPY')
|
||||
preprocess_dict[inputs_name[0]]['reverse_channel'] = False
|
||||
else:
|
||||
dataset_files = []
|
||||
for i in range(num):
|
||||
if os.path.exists('dataset{}.txt'.format(i)) is True:
|
||||
dataset_files.append('dataset{}.txt'.format(i))
|
||||
dataset_type = "TEXT"
|
||||
else:
|
||||
if os.path.exists("inputs") is False:
|
||||
os.system("mkdir inputs")
|
||||
input = np.random.random(inputs_shape[i]).astype(inputs_type[i])
|
||||
shape = '_'.join(str(inputs_shape[i][j]) for j in range(len(inputs_shape[i])))
|
||||
dataset_name = '{}_shape_{}.npy'.format(inputs_lid[i], shape, i)
|
||||
dataset_name = dataset_name.replace('@', '').replace(':', '_').replace('/', '_')
|
||||
dataset_name = "./inputs/" + dataset_name
|
||||
if os.path.exists(dataset_name) is False:
|
||||
np.save(dataset_name, input)
|
||||
dataset_files.append(dataset_name)
|
||||
dataset_type = "NPY"
|
||||
preprocess_dict[inputs_name[i]]['reverse_channel'] = False
|
||||
nn.set_database(net, dataset_files=dataset_files, dataset_type=dataset_type)
|
||||
|
||||
# preprocess
|
||||
nn.set_preprocess(net, preprocess_dict)
|
||||
inputmeta_serialize = nn.get_inputmeta(net)
|
||||
inputmeta_serialize['databases'][0]['ports'][0]['redirect_to_output'] = False
|
||||
nn.set_inputmeta(net, inputmeta_serialize)
|
||||
|
||||
if save:
|
||||
inputmeta_yml = modelfile_name + '_inputmeta.yml'
|
||||
nn.save_model_inputmeta(net, inputmeta_yml)
|
||||
return net
|
||||
|
||||
def postprocess(net, modelfile_name, save=True):
|
||||
nn = VSInn()
|
||||
acuity_postprocess_list = [
|
||||
{'dump_results': {'file_type': 'TENSOR'}},
|
||||
{'print_topn': {'topn': 5}},
|
||||
]
|
||||
nn.set_acuity_postprocess(net, acuity_postprocess_list)
|
||||
|
||||
app_postprocess_list = []
|
||||
outputs = net.get_output_layers()
|
||||
net.compute_shape()
|
||||
for l in outputs:
|
||||
if l.is_op('output'):
|
||||
app_sublist = []
|
||||
app_params = {}
|
||||
add_postproc_node = False
|
||||
dim_num = len(l.get_output().shape.dims)
|
||||
perm = []
|
||||
for i in range(dim_num):
|
||||
perm.append(i)
|
||||
app_params['add_postproc_node'] = add_postproc_node
|
||||
app_params['perm'] = perm
|
||||
app_params['force_float32'] = True
|
||||
|
||||
app_sublist.append(l.lid)
|
||||
app_sublist.append([app_params])
|
||||
app_postprocess_list.append(app_sublist)
|
||||
|
||||
nn.set_app_postprocess(net, app_postprocess_list, set_by_lid=True)
|
||||
|
||||
if save:
|
||||
postprocess_file_yml = modelfile_name + '_postprocess_file.yml'
|
||||
nn.save_model_outputmeta(net, postprocess_file_yml)
|
||||
|
||||
return net
|
||||
|
||||
def main():
|
||||
options = ArgumentParser()
|
||||
options.add_argument("model", type=str, help="Model directory")
|
||||
|
||||
args = options.parse_args()
|
||||
print(args)
|
||||
if os.path.exists(args.model) and os.path.isdir(os.path.abspath(args.model)):
|
||||
model_filename = get_modelfile_name(args.model)
|
||||
if model_filename is None:
|
||||
print("Please enter the path that includes the model.")
|
||||
os.chdir(args.model)
|
||||
else:
|
||||
model_filename = args.model
|
||||
|
||||
#import
|
||||
net, _ = importer(model_filename)
|
||||
#prepocess
|
||||
preprocess(net, model_filename)
|
||||
#postprocess
|
||||
postprocess(net, model_filename)
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue