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
s920243400
PaddleDetection
提交
4eadfc07
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
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
PaddleDetection
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
提交
4eadfc07
编写于
9月 06, 2017
作者:
X
Xinghai Sun
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Correct typos for dropout operator.
上级
963a4f3c
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
2 addition
and
4 deletion
+2
-4
paddle/operators/dropout_op.cc
paddle/operators/dropout_op.cc
+2
-4
未找到文件。
paddle/operators/dropout_op.cc
浏览文件 @
4eadfc07
...
@@ -41,9 +41,7 @@ class DropoutOpMaker : public framework::OpProtoAndCheckerMaker {
...
@@ -41,9 +41,7 @@ class DropoutOpMaker : public framework::OpProtoAndCheckerMaker {
DropoutOpMaker
(
framework
::
OpProto
*
proto
,
DropoutOpMaker
(
framework
::
OpProto
*
proto
,
framework
::
OpAttrChecker
*
op_checker
)
framework
::
OpAttrChecker
*
op_checker
)
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddAttr
<
float
>
(
"dropout_prob"
,
AddAttr
<
float
>
(
"dropout_prob"
,
"Probability for dropping out units."
)
"Probability of randomly setting elements "
"to zero."
)
.
SetDefault
(
.5
f
);
.
SetDefault
(
.5
f
);
AddAttr
<
int
>
(
"seed"
,
"Dropout random seed."
).
SetDefault
(
0
);
AddAttr
<
int
>
(
"seed"
,
"Dropout random seed."
).
SetDefault
(
0
);
AddInput
(
"X"
,
"The input of dropout op."
);
AddInput
(
"X"
,
"The input of dropout op."
);
...
@@ -56,7 +54,7 @@ Dropout Operator.
...
@@ -56,7 +54,7 @@ Dropout Operator.
"Dropout" refers to randomly dropping out units in a nerual network. It is a
"Dropout" refers to randomly dropping out units in a nerual network. It is a
regularization technique for reducing overfitting by preventing neuron
regularization technique for reducing overfitting by preventing neuron
co-adaption during training. The dropout operator randomly set (according to
co-adaption during training. The dropout operator randomly set (according to
the given dropout probability) the output of some units to zero, while others
the given dropout probability) the output
s
of some units to zero, while others
being set to their inputs.
being set to their inputs.
)DOC"
);
)DOC"
);
}
}
...
...
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