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
暴走的小小菜鸟
Paddle
提交
e2c2652f
P
Paddle
项目概览
暴走的小小菜鸟
/
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
e2c2652f
编写于
12月 27, 2017
作者:
Y
Yibing Liu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
amend comments in cross_entropy_op
上级
4177e805
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
16 addition
and
16 deletion
+16
-16
paddle/operators/cross_entropy_op.cc
paddle/operators/cross_entropy_op.cc
+3
-3
python/paddle/v2/fluid/layers/nn.py
python/paddle/v2/fluid/layers/nn.py
+13
-13
未找到文件。
paddle/operators/cross_entropy_op.cc
浏览文件 @
e2c2652f
...
...
@@ -114,15 +114,15 @@ class CrossEntropyOpMaker : public framework::OpProtoAndCheckerMaker {
CrossEntropyOpMaker
(
OpProto
*
proto
,
OpAttrChecker
*
op_checker
)
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddInput
(
"X"
,
"(Tensor, default Tensor<float>), a 2-D tensor with shape
N x D,
"
"where N is the batch size and D is the number of classes. "
"(Tensor, default Tensor<float>), a 2-D tensor with shape
[N x D],
"
"
where N is the batch size and D is the number of classes. "
"This input is a probability computed by the previous operator, "
"which is almost always the result of a softmax operator."
);
AddInput
(
"Label"
,
"(Tensor), the ground truth which is a 2-D tensor. When "
"soft_label is set to false, Label is a Tensor<int64> with shape "
"[N x 1]. When soft_label is set to true, Label is a "
"Tensor<float/double> with shape [N x
K
]."
);
"Tensor<float/double> with shape [N x
D
]."
);
AddOutput
(
"Y"
,
"(Tensor, default Tensor<float>), a 2-D tensor with shape "
"[N x 1]. The cross entropy loss."
);
...
...
python/paddle/v2/fluid/layers/nn.py
浏览文件 @
e2c2652f
...
...
@@ -365,47 +365,47 @@ def cross_entropy(input, label, **kwargs):
both standard cross-entropy and soft-label cross-entropy loss computation.
1) One-hot cross-entropy:
`soft_label =
f
alse`, `Label[i, 0]` indicates the class index for sample i:
`soft_label =
F
alse`, `Label[i, 0]` indicates the class index for sample i:
.. math::
Y[i] = -\log(X[i, Label[i]])
2) Soft-label cross-entropy:
`soft_label =
t
rue`, `Label[i, j]` indicates the soft label of class j
`soft_label =
T
rue`, `Label[i, j]` indicates the soft label of class j
for sample i:
.. math::
Y[i] = \sum_j{-Label[i, j] * log(X[i, j])}
Please make sure that in this case the summ
u
ation of each row of `label`
Please make sure that in this case the summation of each row of `label`
equals one.
3) One-hot cross-entropy with vecterized `label`:
As a special case of 2), when each row of 'label' has only one
non-zero element
(equals 1), soft-label cross-entropy degenerates to a
one-hot cross-entropy with one-hot label representation.
non-zero element
which is equal to 1, soft-label cross-entropy degenerates
to a
one-hot cross-entropy with one-hot label representation.
Args:
input (Variable|list): a 2-D tensor with shape
N x D
, where N is the
input (Variable|list): a 2-D tensor with shape
[N x D]
, where N is the
batch size and D is the number of classes. This input is a probability
computed by the previous operator, which is almost always the result
of a softmax operator.
label (Variable|list): the ground truth which is a 2-D tensor. When
`soft_label` is set to `
f
alse`, `label` is a tensor<int64> with shape
[N x 1]. When `soft_label` is set to `
t
rue`, `label` is a
tensor<float/double> with shape [N x
K
].
`soft_label` is set to `
F
alse`, `label` is a tensor<int64> with shape
[N x 1]. When `soft_label` is set to `
T
rue`, `label` is a
tensor<float/double> with shape [N x
D
].
soft_label (bool, via `**kwargs`): a flag indicating whether to interpretate
the given labels as soft labels, default `
f
alse`.
the given labels as soft labels, default `
F
alse`.
Returns:
A 2-D tensor with shape [N x 1], the cross entropy loss.
Raises:
`ValueError`: 1)
If the 1st dimension of `input` and `label` are not equal; 2) If
\
`soft_label ==
t
rue`, and the 2nd dimension of `input` and `label` are not
\
equal; 3)
If `soft_label == f
alse`, and the 2nd dimension of `label` is not 1.
`ValueError`: 1)
the 1st dimension of `input` and `label` are not equal; 2) when
\
`soft_label ==
T
rue`, and the 2nd dimension of `input` and `label` are not
\
equal; 3)
when `soft_label == F
alse`, and the 2nd dimension of `label` is not 1.
Examples:
.. code-block:: python
...
...
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