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
weixin_52226395
Paddle
提交
acf37ad6
P
Paddle
项目概览
weixin_52226395
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
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
acf37ad6
编写于
1月 15, 2018
作者:
F
fengjiayi
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Complete elementwise_max_op
上级
76a74f1f
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
87 addition
and
10 deletion
+87
-10
paddle/operators/elementwise_max_op.cc
paddle/operators/elementwise_max_op.cc
+1
-1
paddle/operators/elementwise_max_op.cu
paddle/operators/elementwise_max_op.cu
+32
-0
paddle/operators/elementwise_max_op.h
paddle/operators/elementwise_max_op.h
+54
-9
未找到文件。
paddle/operators/elementwise_max_op.cc
浏览文件 @
acf37ad6
...
...
@@ -42,4 +42,4 @@ REGISTER_OP_CPU_KERNEL(
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
float
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
double
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int64_t
>
);
\ No newline at end of file
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int64_t
>
);
paddle/operators/elementwise_max_op.cu
0 → 100644
浏览文件 @
acf37ad6
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. */
#define EIGEN_USE_GPU
#include "paddle/operators/elementwise_max_op.h"
namespace
ops
=
paddle
::
operators
;
REGISTER_OP_CUDA_KERNEL
(
elementwise_max
,
ops
::
ElementwiseMaxKernel
<
paddle
::
platform
::
CUDADeviceContext
,
float
>
,
ops
::
ElementwiseMaxKernel
<
paddle
::
platform
::
CUDADeviceContext
,
double
>
,
ops
::
ElementwiseMaxKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
,
ops
::
ElementwiseMaxKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int64_t
>
);
REGISTER_OP_CUDA_KERNEL
(
elementwise_max_grad
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
float
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
double
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int
>
,
ops
::
ElementwiseMaxGradKernel
<
paddle
::
platform
::
CUDADeviceContext
,
int64_t
>
);
paddle/operators/elementwise_max_op.h
浏览文件 @
acf37ad6
...
...
@@ -65,43 +65,88 @@ class ElementwiseMaxKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
Elementwise
Sub
GradFunctor
{
struct
Elementwise
Max
GradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
typename
dY
,
typename
dZ
>
void
operator
()(
Device
d
,
X
x
,
Y
y
,
Z
z
,
dX
dx
,
dY
dy
,
dZ
dz
)
{
auto
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
auto
x_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
x
);
auto
y_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
y
);
auto
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
(
x_e
>
y_e
)
*
dz_e
;
dx_e
.
device
(
d
)
=
(
x_e
>
y_e
)
.
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
y_e
>=
x_e
)
*
dz_e
;
dy_e
.
device
(
d
)
=
(
y_e
>=
x_e
)
.
template
cast
<
T
>()
*
dz_e
;
}
}
};
template
<
typename
T
>
struct
Elementwise
SubOne
GradFunctor
{
struct
Elementwise
MaxBroadCast
GradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
typename
dY
,
typename
dZ
>
void
operator
()(
Device
d
,
X
x
,
Y
y
,
Z
z
,
dX
dx
,
dY
dy
,
dZ
dz
)
{
typename
dY
,
typename
dZ
,
typename
Pre
,
typename
N
>
void
operator
()(
Device
d
,
X
x
,
Y
y
,
Z
z
,
dX
dx
,
dY
dy
,
dZ
dz
,
Pre
pre
,
N
n
)
{
auto
x_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
x
);
auto
y_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
y
);
auto
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
auto
y_e_bcast
=
y_e
.
reshape
(
Eigen
::
DSizes
<
int
,
2
>
(
1
,
n
))
.
broadcast
(
Eigen
::
DSizes
<
int
,
2
>
(
pre
,
1
))
.
reshape
(
Eigen
::
DSizes
<
int
,
1
>
(
x_e
.
size
()));
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
(
x_e
>
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
((
y_e_bcast
>=
x_e
).
template
cast
<
T
>()
*
dz_e
)
.
reshape
(
Eigen
::
DSizes
<
int
,
2
>
(
pre
,
n
))
.
sum
(
Eigen
::
array
<
int
,
1
>
{{
0
}});
}
}
};
template
<
typename
T
>
struct
ElementwiseMaxBroadCast2GradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
typename
dY
,
typename
dZ
,
typename
Pre
,
typename
N
,
typename
Post
>
void
operator
()(
Device
d
,
X
x
,
Y
y
,
Z
z
,
dX
dx
,
dY
dy
,
dZ
dz
,
Pre
pre
,
N
n
,
Post
post
)
{
auto
x_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
x
);
auto
y_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
y
);
auto
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
auto
y_e_bcast
=
y_e
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
1
,
n
,
1
))
.
broadcast
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
1
,
post
))
.
reshape
(
Eigen
::
DSizes
<
int
,
1
>
(
x_e
.
size
()));
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
dz_e
;
dx_e
.
device
(
d
)
=
(
x_e
>
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
)
*
dz_e
.
sum
();
dy_e
.
device
(
d
)
=
((
y_e_bcast
>=
x_e
).
template
cast
<
T
>()
*
dz_e
)
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
n
,
post
))
.
sum
(
Eigen
::
array
<
int
,
2
>
{{
0
,
2
}});
}
}
};
template
<
typename
DeviceContext
,
typename
T
>
class
ElementwiseMaxGradKernel
:
public
framework
::
OpKernel
<
T
>
{
public:
void
Compute
(
const
framework
::
ExecutionContext
&
ctx
)
const
override
{
ElementwiseGradCompute
<
DeviceContext
,
T
,
ElementwiseMaxGradFunctor
<
T
>
,
ElementwiseMaxBroadCastGradFunctor
<
T
>
,
ElementwiseMaxBroadCast2GradFunctor
<
T
>>
(
ctx
);
}
};
}
// namespace operators
}
// namespace paddle
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