Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
wmsofts
Paddle
提交
8b88960d
P
Paddle
项目概览
wmsofts
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
提交
8b88960d
编写于
3月 09, 2019
作者:
D
dengkaipeng
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix doc. test=develop
上级
2ddd23da
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
10 addition
and
8 deletion
+10
-8
paddle/fluid/operators/softmax_op.cc
paddle/fluid/operators/softmax_op.cc
+4
-4
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+6
-4
未找到文件。
paddle/fluid/operators/softmax_op.cc
浏览文件 @
8b88960d
...
...
@@ -86,7 +86,7 @@ class SoftmaxOpMaker : public framework::OpProtoAndCheckerMaker {
void
Make
()
override
{
AddInput
(
"X"
,
"The input tensor of softmax, "
"whose
:attr:`axis` dimension
is the input_feature_dimensions."
);
"whose
dimension :attr:`axis`
is the input_feature_dimensions."
);
AddOutput
(
"Out"
,
"The normalized values with the same shape as X."
);
AddAttr
<
int
>
(
"axis"
,
"The dimension index of Input(x) to perform softmax,"
...
...
@@ -116,13 +116,13 @@ Softmax Operator.
The input of the softmax operator is a tensor of any rank. The output tensor
has the same shape as the input.
The
:attr:`axis` th dimension
of the input tensor will be permuted to the last.
The
dimension :attr:`axis`
of the input tensor will be permuted to the last.
Then the input tensor will be logically flattened to a 2-D matrix. The matrix's
second dimension(row length) is as same as the
:attr:`axis` dimension
of the input
second dimension(row length) is as same as the
dimension :attr:`axis`
of the input
tensor, and the first dimension(column length) is the product of all other
dimensions of the input tensor. For each row of the matrix, the softmax operator
squashes the K-dimensional(K is the width of the matrix, which is also the size
of the input tensor's
:attr:`axis` dimension
) vector of arbitrary real values to a
of the input tensor's
dimension :attr:`axis`
) vector of arbitrary real values to a
K-dimensional vector of real values in the range [0, 1] that add up to 1.
It computes the exponential of the given dimension and the sum of exponential
values of all the other dimensions in the K-dimensional vector input.
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
8b88960d
...
...
@@ -1824,13 +1824,13 @@ def softmax(input, use_cudnn=False, name=None, axis=-1):
The input of the softmax operator is a tensor of any rank. The output tensor
has the same shape as the input.
The
:attr:`axis` th dimension
of the input tensor will be permuted to the last.
The
dimension :attr:`axis`
of the input tensor will be permuted to the last.
Then the input tensor will be logically flattened to a 2-D matrix. The matrix's
second dimension(row length) is as same as the
:attr:`axis` th dimension
of the input
second dimension(row length) is as same as the
dimension :attr:`axis`
of the input
tensor, and the first dimension(column length) is the product of all other
dimensions of the input tensor. For each row of the matrix, the softmax operator
squashes the K-dimensional(K is the width of the matrix, which is also the size
of the input tensor's
:attr:`axis` th dimension
) vector of arbitrary real values to a
of the input tensor's
dimension :attr:`axis`
) vector of arbitrary real values to a
K-dimensional vector of real values in the range [0, 1] that add up to 1.
It computes the exponential of the given dimension and the sum of exponential
...
...
@@ -1852,7 +1852,9 @@ def softmax(input, use_cudnn=False, name=None, axis=-1):
False by default. Default: False
name (str|None): A name for this layer(optional). If set None, the layer
will be named automatically. Default: None.
axis (int): The index of dimension to perform softmax calculation. Default: -1.
axis (int): The index of dimension to perform softmax calculations, it should
be in range :math:`[-1, rank - 1]`, while :math:`rank` is the rank of
input variable. Default: -1.
Returns:
Variable: output of softmax
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录