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
8b30fada
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
8b30fada
编写于
3月 07, 2018
作者:
C
chengduoZH
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
refine elementwise sub,div,min,max
上级
c43995ed
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
34 addition
and
277 deletion
+34
-277
paddle/fluid/operators/elementwise_div_op.h
paddle/fluid/operators/elementwise_div_op.h
+7
-72
paddle/fluid/operators/elementwise_max_op.h
paddle/fluid/operators/elementwise_max_op.h
+8
-71
paddle/fluid/operators/elementwise_min_op.h
paddle/fluid/operators/elementwise_min_op.h
+8
-71
paddle/fluid/operators/elementwise_mul_op.h
paddle/fluid/operators/elementwise_mul_op.h
+5
-6
paddle/fluid/operators/elementwise_sub_op.h
paddle/fluid/operators/elementwise_sub_op.h
+6
-57
未找到文件。
paddle/fluid/operators/elementwise_div_op.h
浏览文件 @
8b30fada
...
...
@@ -41,77 +41,14 @@ class ElementwiseDivKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
ElementwiseDivGradFunctor
{
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
y_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
y
);
auto
z_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
z
);
auto
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
dz_e
/
y_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
-
1.0
*
dz_e
*
z_e
/
y_e
;
}
}
};
template
<
typename
T
>
struct
ElementwiseDivBroadCastGradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
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
)
=
dz_e
/
y_e_bcast
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
*
(
x_e
*
dz_e
)
/
(
y_e_bcast
*
y_e_bcast
))
.
reshape
(
Eigen
::
DSizes
<
int
,
2
>
(
pre
,
n
))
.
sum
(
Eigen
::
array
<
int
,
1
>
{{
0
}});
}
}
struct
DivGradDX
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
/
y
;
}
};
template
<
typename
T
>
struct
ElementwiseDivBroadCast2GradFunctor
{
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
/
y_e_bcast
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
*
(
x_e
*
dz_e
)
/
(
y_e_bcast
*
y_e_bcast
))
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
n
,
post
))
.
sum
(
Eigen
::
array
<
int
,
2
>
{{
0
,
2
}});
}
struct
DivGradDY
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
-
dout
*
x
/
(
y
*
y
);
}
};
...
...
@@ -128,10 +65,8 @@ class ElementwiseDivGradKernel : public framework::OpKernel<T> {
auto
*
dx
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"X"
));
auto
*
dy
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"Y"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
ElementwiseGradCompute
<
DeviceContext
,
T
,
ElementwiseDivGradFunctor
<
T
>
,
ElementwiseDivBroadCastGradFunctor
<
T
>
,
ElementwiseDivBroadCast2GradFunctor
<
T
>>
(
ctx
,
x
,
y
,
out
,
dout
,
axis
,
dx
,
dy
);
ElemwiseGradCompute
<
DeviceContext
,
T
,
DivGradDX
<
T
>
,
DivGradDY
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
DivGradDX
<
T
>
(),
DivGradDY
<
T
>
());
}
};
...
...
paddle/fluid/operators/elementwise_max_op.h
浏览文件 @
8b30fada
...
...
@@ -41,76 +41,16 @@ class ElementwiseMaxKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
ElementwiseMaxGradFunctor
{
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
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
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
x_e
<=
y_e
).
template
cast
<
T
>()
*
dz_e
;
}
struct
MaxGradDx
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
(
x
>
y
);
}
};
template
<
typename
T
>
struct
ElementwiseMaxBroadCastGradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
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
)
=
((
x_e
<=
y_e_bcast
).
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
)
=
(
x_e
>
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
((
x_e
<=
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
)
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
n
,
post
))
.
sum
(
Eigen
::
array
<
int
,
2
>
{{
0
,
2
}});
}
struct
MaxGradDy
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
(
x
<=
y
);
}
};
...
...
@@ -127,12 +67,9 @@ class ElementwiseMaxGradKernel : public framework::OpKernel<T> {
auto
*
dx
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"X"
));
auto
*
dy
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"Y"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
ElementwiseGradCompute
<
DeviceContext
,
T
,
ElementwiseMaxGradFunctor
<
T
>
,
ElementwiseMaxBroadCastGradFunctor
<
T
>
,
ElementwiseMaxBroadCast2GradFunctor
<
T
>>
(
ctx
,
x
,
y
,
out
,
dout
,
axis
,
dx
,
dy
);
ElemwiseGradCompute
<
DeviceContext
,
T
,
MaxGradDx
<
T
>
,
MaxGradDy
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
MaxGradDx
<
T
>
(),
MaxGradDy
<
T
>
());
}
};
}
// namespace operators
}
// namespace paddle
paddle/fluid/operators/elementwise_min_op.h
浏览文件 @
8b30fada
...
...
@@ -41,76 +41,16 @@ class ElementwiseMinKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
ElementwiseMinGradFunctor
{
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
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
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
x_e
>=
y_e
).
template
cast
<
T
>()
*
dz_e
;
}
struct
MinGradDx
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
(
x
<
y
);
}
};
template
<
typename
T
>
struct
ElementwiseMinBroadCastGradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
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
)
=
((
x_e
>=
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
)
.
reshape
(
Eigen
::
DSizes
<
int
,
2
>
(
pre
,
n
))
.
sum
(
Eigen
::
array
<
int
,
1
>
{{
0
}});
}
}
};
template
<
typename
T
>
struct
ElementwiseMinBroadCast2GradFunctor
{
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
)
=
(
x_e
<
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
((
x_e
>=
y_e_bcast
).
template
cast
<
T
>()
*
dz_e
)
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
n
,
post
))
.
sum
(
Eigen
::
array
<
int
,
2
>
{{
0
,
2
}});
}
struct
MinGradDy
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
(
x
>=
y
);
}
};
...
...
@@ -127,12 +67,9 @@ class ElementwiseMinGradKernel : public framework::OpKernel<T> {
auto
*
dx
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"X"
));
auto
*
dy
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"Y"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
ElementwiseGradCompute
<
DeviceContext
,
T
,
ElementwiseMinGradFunctor
<
T
>
,
ElementwiseMinBroadCastGradFunctor
<
T
>
,
ElementwiseMinBroadCast2GradFunctor
<
T
>>
(
ctx
,
x
,
y
,
out
,
dout
,
axis
,
dx
,
dy
);
ElemwiseGradCompute
<
DeviceContext
,
T
,
MinGradDx
<
T
>
,
MinGradDy
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
MinGradDx
<
T
>
(),
MinGradDy
<
T
>
());
}
};
}
// namespace operators
}
// namespace paddle
paddle/fluid/operators/elementwise_mul_op.h
浏览文件 @
8b30fada
...
...
@@ -40,14 +40,15 @@ class ElementwiseMulKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
IdentityGrad_
DX
{
struct
MulGrad
DX
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
y
;
}
};
template
<
typename
T
>
struct
IdentityGrad_
DY
{
struct
MulGrad
DY
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
*
x
;
}
};
template
<
typename
DeviceContext
,
typename
T
>
class
ElementwiseMulGradKernel
:
public
framework
::
OpKernel
<
T
>
{
public:
...
...
@@ -61,10 +62,8 @@ class ElementwiseMulGradKernel : public framework::OpKernel<T> {
auto
*
dx
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"X"
));
auto
*
dy
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"Y"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
ElemwiseGradCompute
<
DeviceContext
,
T
,
IdentityGrad_DX
<
T
>
,
IdentityGrad_DY
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
IdentityGrad_DX
<
T
>
(),
IdentityGrad_DY
<
T
>
());
ElemwiseGradCompute
<
DeviceContext
,
T
,
MulGradDX
<
T
>
,
MulGradDY
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
MulGradDX
<
T
>
(),
MulGradDY
<
T
>
());
}
};
}
// namespace operators
...
...
paddle/fluid/operators/elementwise_sub_op.h
浏览文件 @
8b30fada
...
...
@@ -40,61 +40,13 @@ class ElementwiseSubKernel : public framework::OpKernel<T> {
};
template
<
typename
T
>
struct
ElementwiseSubGradFunctor
{
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
);
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
)
*
dz_e
;
}
}
struct
SubGradDX
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
dout
;
}
};
template
<
typename
T
>
struct
ElementwiseSubBroadCastGradFunctor
{
template
<
typename
Device
,
typename
X
,
typename
Y
,
typename
Z
,
typename
dX
,
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
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
)
*
dz_e
.
reshape
(
Eigen
::
DSizes
<
int
,
2
>
(
pre
,
n
))
.
sum
(
Eigen
::
array
<
int
,
1
>
{{
0
}});
}
}
};
template
<
typename
T
>
struct
ElementwiseSubBroadCast2GradFunctor
{
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
dz_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dz
);
if
(
dx
)
{
auto
dx_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dx
);
dx_e
.
device
(
d
)
=
dz_e
;
}
if
(
dy
)
{
auto
dy_e
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
dy
);
dy_e
.
device
(
d
)
=
(
-
1.0
)
*
dz_e
.
reshape
(
Eigen
::
DSizes
<
int
,
3
>
(
pre
,
n
,
post
))
.
sum
(
Eigen
::
array
<
int
,
2
>
{{
0
,
2
}});
}
}
struct
SubGradDY
{
HOSTDEVICE
T
operator
()(
T
x
,
T
y
,
T
out
,
T
dout
)
const
{
return
-
dout
;
}
};
template
<
typename
DeviceContext
,
typename
T
>
...
...
@@ -110,12 +62,9 @@ class ElementwiseSubGradKernel : public framework::OpKernel<T> {
auto
*
dx
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"X"
));
auto
*
dy
=
ctx
.
Output
<
Tensor
>
(
framework
::
GradVarName
(
"Y"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
ElementwiseGradCompute
<
DeviceContext
,
T
,
ElementwiseSubGradFunctor
<
T
>
,
ElementwiseSubBroadCastGradFunctor
<
T
>
,
ElementwiseSubBroadCast2GradFunctor
<
T
>>
(
ctx
,
x
,
y
,
out
,
dout
,
axis
,
dx
,
dy
);
ElemwiseGradCompute
<
DeviceContext
,
T
,
SubGradDX
<
T
>
,
SubGradDY
<
T
>>
(
ctx
,
*
x
,
*
y
,
*
out
,
*
dout
,
axis
,
dx
,
dy
,
SubGradDX
<
T
>
(),
SubGradDY
<
T
>
());
}
};
}
// 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