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
a6e6bc45
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
a6e6bc45
编写于
10月 24, 2018
作者:
P
phlrain
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
modify dropout att; test=develop
上级
049c9c7d
变更
5
显示空白变更内容
内联
并排
Showing
5 changed file
with
55 addition
and
29 deletion
+55
-29
paddle/fluid/operators/dropout_op.cc
paddle/fluid/operators/dropout_op.cc
+24
-9
paddle/fluid/operators/dropout_op.cu
paddle/fluid/operators/dropout_op.cu
+7
-5
paddle/fluid/operators/dropout_op.h
paddle/fluid/operators/dropout_op.h
+5
-3
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+15
-8
python/paddle/fluid/tests/unittests/test_dropout_op.py
python/paddle/fluid/tests/unittests/test_dropout_op.py
+4
-4
未找到文件。
paddle/fluid/operators/dropout_op.cc
浏览文件 @
a6e6bc45
...
...
@@ -13,6 +13,7 @@ See the License for the specific language governing permissions and
limitations under the License. */
#include "paddle/fluid/operators/dropout_op.h"
#include <string>
namespace
paddle
{
namespace
operators
{
...
...
@@ -57,15 +58,29 @@ class DropoutOpMaker : public framework::OpProtoAndCheckerMaker {
"will be dropped."
)
.
SetDefault
(
false
);
AddAttr
<
int
>
(
"seed"
,
"Dropout random seed."
).
SetDefault
(
0
);
AddAttr
<
bool
>
(
"dropout_implementation"
,
"When it's True, In the training, after set some value"
"to 0 (probability is dropout_prob),"
"all the value will divide (1-dropout_prob)"
"By using this way, will do nothing in the inference program"
"The dropout op can be removed in the inference program."
"The inference program will be more efficient"
"When it's False, same as original"
)
.
SetDefault
(
false
);
AddAttr
<
std
::
string
>
(
"dropout_implementation"
,
"[
\"
downgrade_in_infer
\"
|
\"
upscale_in_train
\"
]"
"There are two kinds of ways to implement dropout"
"(the mask below is a tensor have the same shape with input"
"the value of mask is 0 or 1, the ratio of 0 is dropout_prob)"
"1. downgrade_in_infer(default), downgrade the outcome at inference "
"time"
" train: out = input * mask"
" inference: out = input * dropout_prob"
"2. upscale_in_train, upscale the outcome at training time, do nothing "
"in inference"
" train: out = input * mask / ( 1.0 - dropout_prob )"
" inference: out = input"
" dropout op can be removed from the program. the program will be "
"efficient"
)
.
SetDefault
(
"downgrade_in_infer"
)
.
AddCustomChecker
([](
const
std
::
string
&
type
)
{
PADDLE_ENFORCE
(
type
==
"downgrade_in_infer"
||
type
==
"upscale_in_train"
,
"dropout_implementation can only be downgrade_in_infer or "
"upscale_in_train"
);
});
AddComment
(
R"DOC(
Dropout Operator.
...
...
paddle/fluid/operators/dropout_op.cu
浏览文件 @
a6e6bc45
...
...
@@ -17,6 +17,7 @@ limitations under the License. */
#include <thrust/iterator/counting_iterator.h>
#include <thrust/random.h>
#include <thrust/transform.h>
#include <string>
#include "paddle/fluid/operators/dropout_op.h"
#include "paddle/fluid/platform/float16.h"
...
...
@@ -27,7 +28,7 @@ template <typename T>
__global__
void
RandomGenerator
(
const
size_t
n
,
const
int
seed
,
const
float
dropout_prob
,
const
T
*
src
,
T
*
mask_data
,
T
*
dst
,
bool
dropout_implementatio
n
)
{
bool
is_upscale_in_trai
n
)
{
thrust
::
minstd_rand
rng
;
rng
.
seed
(
seed
);
thrust
::
uniform_real_distribution
<
float
>
dist
(
0
,
1
);
...
...
@@ -48,7 +49,7 @@ __global__ void RandomGenerator(const size_t n, const int seed,
if
(
dist
(
rng
)
<
dropout_prob
)
{
mask
=
static_cast
<
T
>
(
0
);
}
else
{
if
(
dropout_implementatio
n
)
{
if
(
is_upscale_in_trai
n
)
{
mask
=
static_cast
<
T
>
(
1.0
f
/
(
1.0
f
-
dropout_prob
));
}
else
{
mask
=
static_cast
<
T
>
(
1
);
...
...
@@ -72,7 +73,8 @@ class GPUDropoutKernel : public framework::OpKernel<T> {
y
->
mutable_data
<
T
>
(
context
.
GetPlace
());
float
dropout_prob
=
context
.
Attr
<
float
>
(
"dropout_prob"
);
auto
dropout_implementation
=
context
.
Attr
<
bool
>
(
"dropout_implementation"
);
auto
dropout_implementation
=
context
.
Attr
<
std
::
string
>
(
"dropout_implementation"
);
auto
&
place
=
*
context
.
template
device_context
<
Place
>().
eigen_device
();
if
(
!
context
.
Attr
<
bool
>
(
"is_test"
))
{
auto
*
mask
=
context
.
Output
<
Tensor
>
(
"Mask"
);
...
...
@@ -90,11 +92,11 @@ class GPUDropoutKernel : public framework::OpKernel<T> {
RandomGenerator
<
T
><<<
grid
,
threads
,
0
,
context
.
cuda_device_context
().
stream
()
>>>
(
size
,
seed
,
dropout_prob
,
x_data
,
mask_data
,
y_data
,
dropout_implementation
);
(
dropout_implementation
==
"upscale_in_train"
)
);
}
else
{
auto
X
=
EigenMatrix
<
T
>::
Reshape
(
*
x
,
1
);
auto
Y
=
EigenMatrix
<
T
>::
Reshape
(
*
y
,
1
);
if
(
dropout_implementation
)
{
if
(
dropout_implementation
==
"upscale_in_train"
)
{
Y
.
device
(
place
)
=
X
;
}
else
{
Y
.
device
(
place
)
=
X
*
static_cast
<
T
>
(
1.0
f
-
dropout_prob
);
...
...
paddle/fluid/operators/dropout_op.h
浏览文件 @
a6e6bc45
...
...
@@ -14,6 +14,7 @@ limitations under the License. */
#pragma once
#include <random>
#include <string>
#include "paddle/fluid/framework/eigen.h"
#include "paddle/fluid/framework/op_registry.h"
...
...
@@ -36,7 +37,8 @@ class CPUDropoutKernel : public framework::OpKernel<T> {
auto
*
y_data
=
y
->
mutable_data
<
T
>
(
context
.
GetPlace
());
float
dropout_prob
=
context
.
Attr
<
float
>
(
"dropout_prob"
);
auto
dropout_implementation
=
context
.
Attr
<
bool
>
(
"dropout_implementation"
);
auto
dropout_implementation
=
context
.
Attr
<
std
::
string
>
(
"dropout_implementation"
);
if
(
!
context
.
Attr
<
bool
>
(
"is_test"
))
{
auto
*
mask
=
context
.
Output
<
Tensor
>
(
"Mask"
);
auto
*
mask_data
=
mask
->
mutable_data
<
T
>
(
context
.
GetPlace
());
...
...
@@ -57,7 +59,7 @@ class CPUDropoutKernel : public framework::OpKernel<T> {
mask_data
[
i
]
=
0
;
y_data
[
i
]
=
0
;
}
else
{
if
(
dropout_implementation
)
{
if
(
dropout_implementation
==
"upscale_in_train"
)
{
mask_data
[
i
]
=
1.0
f
/
static_cast
<
T
>
(
1.0
f
-
dropout_prob
);
y_data
[
i
]
=
x_data
[
i
]
/
static_cast
<
T
>
(
1.0
f
-
dropout_prob
);
}
else
{
...
...
@@ -71,7 +73,7 @@ class CPUDropoutKernel : public framework::OpKernel<T> {
auto
Y
=
EigenMatrix
<
T
>::
Reshape
(
*
y
,
1
);
auto
&
place
=
*
context
.
template
device_context
<
DeviceContext
>().
eigen_device
();
if
(
dropout_implementation
)
{
if
(
dropout_implementation
==
"upscale_in_train"
)
{
Y
.
device
(
place
)
=
X
;
}
else
{
Y
.
device
(
place
)
=
X
*
static_cast
<
T
>
(
1.0
f
-
dropout_prob
);
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
a6e6bc45
...
...
@@ -985,7 +985,7 @@ def dropout(x,
is_test
=
False
,
seed
=
None
,
name
=
None
,
dropout_implementation
=
False
):
dropout_implementation
=
"downgrade_in_infer"
):
"""
Computes dropout.
...
...
@@ -1005,13 +1005,20 @@ def dropout(x,
units will be dropped. DO NOT use a fixed seed in training.
name (str|None): A name for this layer(optional). If set None, the layer
will be named automatically.
dropout_implementation(bool): A Flag indicating whether divide (1-dropout_prob).
When it's True, all the units will divide (1-dropout_prob)
after set some units to zero in the train program.
And do nothing in the inference program.
The dropout op can be removed in the inference program.
The inference program will be more efficient
When it's False, same as original
dropout_implementation(string): ['downgrade_in_infer'(defauld)|'upscale_in_train']
1. downgrade_in_infer(default), downgrade the outcome at inference
train: out = input * mask
inference: out = input * dropout_prob
(make is a tensor same shape with input, value is 0 or 1
ratio of 0 is dropout_prob)
2. upscale_in_train, upscale the outcome at training time
train: out = input * mask / ( 1.0 - dropout_prob )
inference: out = input
(make is a tensor same shape with input, value is 0 or 1
ratio of 0 is dropout_prob)
dropout op can be removed from the program.
the program will be efficient
Returns:
...
...
python/paddle/fluid/tests/unittests/test_dropout_op.py
浏览文件 @
a6e6bc45
...
...
@@ -93,7 +93,7 @@ class TestDropoutOp6(TestDropoutOp):
'dropout_prob'
:
1.0
,
'fix_seed'
:
True
,
'is_test'
:
False
,
'd
iv_prob_in_train'
:
True
'd
ropout_implementation'
:
'upscale_in_train'
}
self
.
outputs
=
{
'Out'
:
np
.
zeros
((
32
,
64
)).
astype
(
'float32'
),
...
...
@@ -109,7 +109,7 @@ class TestDropoutOp7(TestDropoutOp):
'dropout_prob'
:
0.0
,
'fix_seed'
:
True
,
'is_test'
:
False
,
'd
iv_prob_in_train'
:
True
'd
ropout_implementation'
:
'upscale_in_train'
}
self
.
outputs
=
{
'Out'
:
self
.
inputs
[
'X'
],
...
...
@@ -125,7 +125,7 @@ class TestDropoutOp8(OpTest):
'dropout_prob'
:
0.35
,
'fix_seed'
:
True
,
'is_test'
:
True
,
'd
iv_prob_in_train'
:
True
'd
ropout_implementation'
:
'upscale_in_train'
}
self
.
outputs
=
{
'Out'
:
self
.
inputs
[
'X'
]}
...
...
@@ -140,7 +140,7 @@ class TestDropoutOp9(OpTest):
self
.
attrs
=
{
'dropout_prob'
:
0.75
,
'is_test'
:
True
,
'd
iv_prob_in_train'
:
True
'd
ropout_implementation'
:
'upscale_in_train'
}
self
.
outputs
=
{
'Out'
:
self
.
inputs
[
'X'
]}
...
...
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