vilc
/
mindspore2022
forked from huawei/mindspore2022
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

!7921 update googlenet readme 

Merge pull request !7921 from caojian05/ms_r1.0_googlenet_bugfix
This commit is contained in:
mindspore-ci-bot 2020-10-30 19:15:25 +08:00 committed by Gitee
parent 766caf637d 0d38e7118c
commit 3cffa273de
1 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
model_zoo/official/cv/googlenet/README.md
View File

@ -41,6 +41,7 @@ Specifically, the GoogleNet contains numerous inception modules, which are conne
# [Dataset](#contents)
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
Dataset used: [CIFAR-10](<http://www.cs.toronto.edu/~kriz/cifar.html>)
@ -160,11 +161,11 @@ Parameters for both training and evaluation can be set in config.py
'image_width': 224 # image width used as input to the model
'data_path': './cifar10' # absolute full path to the train and evaluation datasets
'device_target': 'Ascend' # device running the program
'device_id': 4 # device ID used to train or evaluate the dataset. Ignore it when you use run_train.sh for distributed training
'device_id': 0 # device ID used to train or evaluate the dataset. Ignore it when you use run_train.sh for distributed training
'keep_checkpoint_max': 10 # only keep the last keep_checkpoint_max checkpoint
'checkpoint_path': './train_googlenet_cifar10-125_390.ckpt' # the absolute full path to save the checkpoint file
'onnx_filename': 'googlenet.onnx' # file name of the onnx model used in export.py
'geir_filename': 'googlenet.geir' # file name of the geir model used in export.py
'air_filename': 'googlenet.air' # file name of the air model used in export.py
```
@ -257,7 +258,7 @@ Parameters for both training and evaluation can be set in config.py
Note that for evaluation after distributed training, please set the checkpoint_path to be the last saved checkpoint file such as "username/googlenet/train_parallel0/train_googlenet_cifar10-125_48.ckpt". The accuracy of the test dataset will be as follows:
```
# grep "accuracy: " dist.eval.log
# grep "accuracy: " eval.log
accuracy: {'acc': 0.9217}
```
@ -301,8 +302,8 @@ Parameters for both training and evaluation can be set in config.py
| -------------------------- | ----------------------------------------------------------- | ---------------------- |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，56cores；Memory，314G | NV SMX2 V100-32G |
| uploaded Date | 08/31/2020 (month/day/year) | 08/20/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha | 0.6.0-alpha |
| uploaded Date | 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year) |
| MindSpore Version | 1.0.0 | 1.0.0 |
| Dataset | CIFAR-10 | CIFAR-10 |
| Training Parameters | epoch=125, steps=390, batch_size = 128, lr=0.1 | epoch=125, steps=390, batch_size=128, lr=0.1 |
| Optimizer | SGD | SGD |
@ -314,7 +315,7 @@ Parameters for both training and evaluation can be set in config.py
| Parameters (M) | 13.0 | 13.0 |
| Checkpoint for Fine tuning | 43.07M (.ckpt file) | 43.07M (.ckpt file) |
| Model for inference | 21.50M (.onnx file), 21.60M(.air file) | |
| Scripts | [googlenet script](https://gitee.com/mindspore/mindspore/tree/r0.7/model_zoo/official/cv/googlenet) | [googlenet script](https://gitee.com/mindspore/mindspore/tree/r0.6/model_zoo/official/cv/googlenet) |
| Scripts | [googlenet script](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/googlenet) | [googlenet script](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/googlenet) |
### Inference Performance
@ -323,8 +324,8 @@ Parameters for both training and evaluation can be set in config.py
| ------------------- | --------------------------- | --------------------------- |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 | GPU |
| Uploaded Date | 08/31/2020 (month/day/year) | 08/20/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha | 0.6.0-alpha |
| Uploaded Date | 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year) |
| MindSpore Version | 1.0.0 | 1.0.0 |
| Dataset | CIFAR-10, 10,000 images | CIFAR-10, 10,000 images |
| batch_size | 128 | 128 |
| outputs | probability | probability |