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
PaddlePaddle
PaddleDetection
提交
4849fba7
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
12 个月 前同步成功
通知
692
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
4849fba7
编写于
10月 11, 2017
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
follow comments
上级
c22e7ff7
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
72 addition
and
25 deletion
+72
-25
paddle/operators/math/CMakeLists.txt
paddle/operators/math/CMakeLists.txt
+2
-2
paddle/operators/pool_op.cc
paddle/operators/pool_op.cc
+32
-9
paddle/operators/pool_with_index_op.cc
paddle/operators/pool_with_index_op.cc
+38
-14
未找到文件。
paddle/operators/math/CMakeLists.txt
浏览文件 @
4849fba7
...
...
@@ -3,14 +3,14 @@ if(WITH_GPU)
nv_test
(
math_function_test SRCS math_function_test.cc DEPS math_function tensor
)
nv_library
(
softmax SRCS softmax.cc softmax.cu DEPS operator
)
nv_library
(
cross_entropy SRCS cross_entropy.cc cross_entropy.cu DEPS operator
)
nv_library
(
pooling SRCS pooling.cc pooling.cu DEPS
operator
)
nv_library
(
pooling SRCS pooling.cc pooling.cu DEPS
device_context
)
nv_library
(
vol2col SRCS vol2col.cc vol2col.cu DEPS device_context
)
else
()
cc_library
(
math_function SRCS math_function.cc im2col.cc DEPS cblas device_context operator
)
cc_test
(
math_function_test SRCS math_function_test.cc DEPS math_function tensor
)
cc_library
(
softmax SRCS softmax.cc DEPS operator
)
cc_library
(
cross_entropy SRCS cross_entropy.cc DEPS operator
)
cc_library
(
pooling SRCS pooling.cc DEPS
operator
)
cc_library
(
pooling SRCS pooling.cc DEPS
device_context
)
cc_library
(
vol2col SRCS vol2col.cc DEPS device_context
)
endif
()
...
...
paddle/operators/pool_op.cc
浏览文件 @
4849fba7
...
...
@@ -35,7 +35,7 @@ void PoolOp::InferShape(framework::InferShapeContext *ctx) const {
std
::
vector
<
int
>
paddings
=
ctx
->
Attrs
().
Get
<
std
::
vector
<
int
>>
(
"paddings"
);
PADDLE_ENFORCE
(
in_x_dims
.
size
()
==
4
||
in_x_dims
.
size
()
==
5
,
"Pooling intput should be 4-D or 5-D"
);
"Pooling intput should be 4-D or 5-D
tensor.
"
);
if
(
ctx
->
Attrs
().
Get
<
bool
>
(
"globalPooling"
))
{
ksize
.
resize
(
static_cast
<
size_t
>
(
in_x_dims
.
size
())
-
2
);
...
...
@@ -70,11 +70,11 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddInput
(
"X"
,
"The input tensor of pooling operator. "
"
(Tensor)
The input tensor of pooling operator. "
"The format of input tensor is NCHW. Where N is batch size, C is the "
"number of channels, H and W is the height and width of feature."
);
AddOutput
(
"Out"
,
"The output tensor of pooling operator."
"
(Tensor)
The output tensor of pooling operator."
"The format of output tensor is also NCHW."
"Where N is batch size, C is "
"the number of channels, H and W is the height and "
...
...
@@ -87,7 +87,7 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
AddAttr
<
std
::
vector
<
int
>>
(
"ksize"
,
"The pooling size(height, width) of pooling operator."
"The pooling
window
size(height, width) of pooling operator."
"If globalPooling = true, ksize is ignored and need not be "
"specified."
);
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -99,12 +99,12 @@ Pool2dOpMaker::Pool2dOpMaker(framework::OpProto *proto,
"If globalPooling = true, ksize is ignored and need not be specified."
)
.
SetDefault
(
false
);
AddAttr
<
std
::
vector
<
int
>>
(
"strides"
,
"
Strides(height, width) of pooling operator
."
"
The strides(height, width) of pooling window
."
"Default {1,1}."
)
.
SetDefault
({
1
,
1
});
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
AddAttr
<
std
::
vector
<
int
>>
(
"paddings"
,
"
Paddings(height, width) of pooling operator.
"
"
The zero padding(height, width) size on both sides
"
"Default {0,0}."
)
.
SetDefault
({
0
,
0
});
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -116,6 +116,17 @@ Input(X) and output(Out) are in NCHW format. Where N is batch size, C is the
number of channels, H and W is the height and width of feature.
Parameters(ksize, strides, paddings) are two elements.
These two elements represent height and width, respectively.
The input(X) size and output(Out) size may be different.
Example:
Input:
X shape: (N, C, H_in, W_in)
Output:
Out shape: (N, C, H_out, W_out)
Mask shape: (N, C, H_out, W_out)
where
H_out = (H_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
W_out = (W_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
)DOC"
);
}
...
...
@@ -124,12 +135,12 @@ Pool3dOpMaker::Pool3dOpMaker(framework::OpProto *proto,
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddInput
(
"X"
,
"The input tensor of pooling operator. "
"
(Tensor)
The input tensor of pooling operator. "
"The format of input tensor is NCDHW. Where N is batch size, C is "
"the number of channels, D, H and W is the depth, height and width of "
"feature."
);
AddOutput
(
"Out"
,
"The output tensor of pooling operator."
"
(Tensor)
The output tensor of pooling operator."
"The format of output tensor is also NCDHW."
"Where N is batch size, C is "
"the number of channels, D, H and W is the depth, height and "
...
...
@@ -142,7 +153,7 @@ Pool3dOpMaker::Pool3dOpMaker(framework::OpProto *proto,
AddAttr
<
std
::
vector
<
int
>>
(
"ksize"
,
"The pooling size(depth, height, width) of pooling operator."
"The pooling
window
size(depth, height, width) of pooling operator."
"If globalPooling = true, ksize is ignored and need not be "
"specified."
);
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -172,6 +183,18 @@ Input(X) and output(Out) are in NCDHW format. Where N is batch
size, C is the number of channels, D, H and W is the depth, height and
width of feature. Parameters(ksize, strides, paddings) are three elements.
These three elements represent depth, height and width, respectively.
The input(X) size and output(Out) size may be different.
Example:
Input:
X shape: (N, C, D_in, H_in, W_in)
Output:
Out shape: (N, C, D_out, H_out, W_out)
Mask shape: (N, C, D_out, H_out, W_out)
where
D_out = (D_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
H_out = (H_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
W_out = (W_in - ksize[2] + 2 * paddings[2]) / strides[2] + 1;
)DOC"
);
}
}
// namespace operators
...
...
paddle/operators/pool_with_index_op.cc
浏览文件 @
4849fba7
...
...
@@ -43,7 +43,7 @@ class MaxPoolWithIndexOp : public framework::OperatorWithKernel {
std
::
vector
<
int
>
paddings
=
ctx
->
Attrs
().
Get
<
std
::
vector
<
int
>>
(
"paddings"
);
PADDLE_ENFORCE
(
in_x_dims
.
size
()
==
4
||
in_x_dims
.
size
()
==
5
,
"Pooling intput should be 4-D or 5-D"
);
"Pooling intput should be 4-D or 5-D
tensor.
"
);
if
(
ctx
->
Attrs
().
Get
<
bool
>
(
"globalPooling"
))
{
ksize
.
resize
(
static_cast
<
size_t
>
(
in_x_dims
.
size
())
-
2
);
...
...
@@ -74,8 +74,8 @@ class MaxPoolWithIndexOpGrad : public framework::OperatorWithKernel {
protected:
void
InferShape
(
framework
::
InferShapeContext
*
ctx
)
const
override
{
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"X"
),
"Input(X) must not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"Mask"
),
"Input(Mask) must not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"X"
),
"Input(X) must not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
framework
::
GradVarName
(
"X"
)),
"Input(X@GRAD) should not be null."
);
ctx
->
SetOutputDim
(
framework
::
GradVarName
(
"X"
),
ctx
->
GetInputDim
(
"X"
));
...
...
@@ -89,17 +89,17 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddInput
(
"X"
,
"The input tensor of pooling operator. "
"
(Tensor)
The input tensor of pooling operator. "
"The format of input tensor is NCHW. Where N is batch size, C is the "
"number of channels, H and W is the height and width of image."
);
AddOutput
(
"Out"
,
"The output tensor of pooling operator."
"
(Tensor)
The output tensor of pooling operator."
"The format of output tensor is also NCHW."
"Where N is batch size, C is "
"the number of channels, H and W is the height and "
"width of image."
);
AddOutput
(
"Mask"
,
"The Mask tensor of pooling operator."
"
(Tensor)
The Mask tensor of pooling operator."
"The format of output tensor is also NCHW."
"Where N is batch size, C is the number of channels, H and W "
"is the height and width of image."
...
...
@@ -107,7 +107,7 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
AddAttr
<
std
::
vector
<
int
>>
(
"ksize"
,
"The pooling size(height, width) of pooling operator."
"The pooling
window
size(height, width) of pooling operator."
"If globalPooling = true, ksize is ignored and need not be "
"specified."
);
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -119,13 +119,14 @@ class MaxPool2dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
"If globalPooling = true, ksize is ignored and need not be specified."
)
.
SetDefault
(
false
);
AddAttr
<
std
::
vector
<
int
>>
(
"strides"
,
"
Strides(height, width) of pooling operator
."
"
The strides(height, width) of pooling window
."
"Default {1,1}."
)
.
SetDefault
({
1
,
1
});
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
AddAttr
<
std
::
vector
<
int
>>
(
"paddings"
,
"Paddings(height, width) of pooling operator."
"Default {0,0}."
)
AddAttr
<
std
::
vector
<
int
>>
(
"paddings"
,
"The zero padding(height, width) size on both sides"
"Default {0,0}."
)
.
SetDefault
({
0
,
0
});
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -136,6 +137,17 @@ output(Out, Mask) are in NCHW format. Where N is batch size, C is the
number of channels, H and W is the height and width of feature.
Parameters(ksize, strides, paddings) are two elements.
These two elements represent height and width, respectively.
The input(X) size and output(Out, Mask) size may be different.
Example:
Input:
X shape: (N, C, H_in, W_in)
Output:
Out shape: (N, C, H_out, W_out)
Mask shape: (N, C, H_out, W_out)
where
H_out = (H_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
W_out = (W_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
)DOC"
);
}
};
...
...
@@ -147,18 +159,18 @@ class MaxPool3dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
:
OpProtoAndCheckerMaker
(
proto
,
op_checker
)
{
AddInput
(
"X"
,
"The input tensor of pooling operator. "
"
(Tensor)
The input tensor of pooling operator. "
"The format of input tensor is NCDHW. Where N is batch size, C is "
"the number of channels, D, H and W is the depth, height and width of "
"image."
);
AddOutput
(
"Out"
,
"The output tensor of pooling operator."
"
(Tensor)
The output tensor of pooling operator."
"The format of output tensor is also NCDHW."
"Where N is batch size, C is "
"the number of channels, D, H and W is the depth, height and "
"width of image."
);
AddOutput
(
"Mask"
,
"The Mask tensor of pooling operator."
"
(Tensor)
The Mask tensor of pooling operator."
"The format of output tensor is also NCDHW."
"Where N is batch size, C is the number of channels, D, H and W "
"is the depth, height and width of image."
...
...
@@ -166,7 +178,7 @@ class MaxPool3dWithIndexOpMaker : public framework::OpProtoAndCheckerMaker {
AddAttr
<
std
::
vector
<
int
>>
(
"ksize"
,
"The pooling size(depth, height, width) of pooling operator."
"The pooling
window
size(depth, height, width) of pooling operator."
"If globalPooling = true, ksize is ignored and need not be "
"specified."
);
// TODO(Chengduo): Add checker. (Currently,
// TypedAttrChecker don't support vector type.)
...
...
@@ -197,6 +209,18 @@ Input(X) and output(Out, Mask) are in NCDHW format. Where N is batch
size, C is the number of channels, D, H and W is the depth, height and
width of feature. Parameters(ksize, strides, paddings) are three elements.
These three elements represent depth, height and width, respectively.
The input(X) size and output(Out, Mask) size may be different.
Example:
Input:
X shape: (N, C, D_in, H_in, W_in)
Output:
Out shape: (N, C, D_out, H_out, W_out)
Mask shape: (N, C, D_out, H_out, W_out)
where
D_out = (D_in - ksize[0] + 2 * paddings[0]) / strides[0] + 1;
H_out = (H_in - ksize[1] + 2 * paddings[1]) / strides[1] + 1;
W_out = (W_in - ksize[2] + 2 * paddings[2]) / strides[2] + 1;
)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