forked from huawei/mindspore2022
fix the documentation of GRU, L2Loss, NLLLoss, etc.
This commit is contained in:
parent
6096c06b23
commit
d9c3d6e5b7
|
|
@ -17,6 +17,8 @@ mindspore.nn.GRU
|
|||
|
||||
其中 :math:`\sigma` 是sigmoid激活函数, :math:`*` 是乘积。 :math:`W,b` 是公式中输出和输入之间的可学习权重。例如, :math:`W_{ir}, b_{ir}` 是用于将输入 :math:`x` 转换为 :math:`r` 的权重和偏置。详见论文 `Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation <https://aclanthology.org/D14-1179.pdf>`_ 。
|
||||
|
||||
.. note:: 当GRU运行在Ascend上时,hidden size仅支持16的倍数。
|
||||
|
||||
**参数:**
|
||||
|
||||
- **input_size** (int) - 输入的大小。
|
||||
|
|
|
|||
|
|
@ -20,7 +20,7 @@ mindspore.nn.LSTMCell
|
|||
其中 :math:`\sigma` 是sigmoid函数, :math:`*` 是乘积。 :math:`W,b` 是公式中输出和输入之间的可学习权重。例如,:math:`W_{ix}, b_{ix}` 是用于从输入 :math:`x` 转换为 :math:`i` 的权重和偏置。详见论文 `LONG SHORT-TERM MEMORY <https://www.bioinf.jku.at/publications/older/2604.pdf>`_ 和 `Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling <https://static.googleusercontent.com/media/research.google.com/zh-CN//pubs/archive/43905.pdf>`_ 。
|
||||
|
||||
**参数:**
|
||||
|
||||
|
||||
- **input_size** (int) - 输入的大小。
|
||||
- **hidden_size** (int)- 隐藏状态大小。
|
||||
- **has_bias** (bool) - cell是否有偏置 `b_ih` 和 `b_hh` 。默认值:True。
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@
|
|||
|
||||
**参数:**
|
||||
|
||||
- **num_true** (int):每个训练样本的目标类数。默认值:1。
|
||||
- **num_true** (int) - 每个训练样本的目标类数。默认值:1。
|
||||
|
||||
**输入:**
|
||||
|
||||
|
|
|
|||
|
|
@ -13,7 +13,7 @@
|
|||
|
||||
**参数:**
|
||||
|
||||
- **keep_prob** (float):输入通道保留率,数值范围在0到1之间,例如 `keep_prob` = 0.8,意味着过滤20%的通道。默认值:0.5。
|
||||
- **keep_prob** (float) - 输入通道保留率,数值范围在0到1之间,例如 `keep_prob` = 0.8,意味着过滤20%的通道。默认值:0.5。
|
||||
|
||||
**输入:**
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ mindspore.ops.L2Loss
|
|||
|
||||
.. py:class:: mindspore.ops.L2Loss()
|
||||
|
||||
用于计算L2范数,但不对结果进行开方操作。
|
||||
用于计算L2范数的一半,但不对结果进行开方操作。
|
||||
|
||||
把输入设为x,输出设为loss。
|
||||
|
||||
|
|
|
|||
|
|
@ -30,4 +30,4 @@ mindspore.ops.NotEqual
|
|||
**异常:**
|
||||
|
||||
- **TypeError** - `x` 和 `y` 不是以下之一:Tensor、Number、bool。
|
||||
- **TypeError** - `x` 和 `y` 都不是Tensor。
|
||||
- **TypeError** - `x` 和 `y` 都不是Tensor。
|
||||
|
|
|
|||
|
|
@ -1852,6 +1852,7 @@ class ArgMaxWithValue(PrimitiveWithInfer):
|
|||
Outputs:
|
||||
tuple (Tensor), tuple of 2 tensors, containing the corresponding index and the maximum value of the input
|
||||
tensor.
|
||||
|
||||
- index (Tensor) - The index for the maximum value of the input tensor. If `keep_dims` is true, the shape of
|
||||
output tensors is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Otherwise, the shape is
|
||||
:math:`(x_1, x_2, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
|
||||
|
|
@ -1920,6 +1921,7 @@ class ArgMinWithValue(PrimitiveWithInfer):
|
|||
Outputs:
|
||||
tuple (Tensor), tuple of 2 tensors, containing the corresponding index and the minimum value of the input
|
||||
tensor.
|
||||
|
||||
- index (Tensor) - The index for the minimum value of the input tensor. If `keep_dims` is true, the shape of
|
||||
output tensors is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Otherwise, the shape is
|
||||
:math:`(x_1, x_2, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
|
||||
|
|
|
|||
|
|
@ -2337,7 +2337,7 @@ class SparseSoftmaxCrossEntropyWithLogits(PrimitiveWithInfer):
|
|||
.. math::
|
||||
\begin{array}{ll} \\
|
||||
p_{ij} = softmax(X_{ij}) = \frac{\exp(x_i)}{\sum_{j = 0}^{N-1}\exp(x_j)} \\
|
||||
loss_{ij} = \begin{cases} -ln(p_{ij}), &j = y_i \cr -ln(1 - p_{ij}), & j \neq y_i \end{cases} \\
|
||||
loss_{ij} = \begin{cases} -ln(p_{ij}), &j = y_i \cr 0, & j \neq y_i \end{cases} \\
|
||||
loss = \sum_{ij} loss_{ij}
|
||||
\end{array}
|
||||
|
||||
|
|
@ -2601,7 +2601,7 @@ class SoftMarginLoss(Primitive):
|
|||
|
||||
class L2Loss(Primitive):
|
||||
r"""
|
||||
Calculates the L2 norm, but do not square the result.
|
||||
Calculates half of the L2 norm, but do not square the result.
|
||||
|
||||
Set input as x and output as loss.
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue