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
Paddle
提交
fe177b62
P
Paddle
项目概览
PaddlePaddle
/
Paddle
1 年多 前同步成功
通知
2302
Star
20931
Fork
5422
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1423
列表
看板
标记
里程碑
合并请求
543
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
1,423
Issue
1,423
列表
看板
标记
里程碑
合并请求
543
合并请求
543
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
fe177b62
编写于
12月 09, 2017
作者:
S
sweetsky0901
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
test detection_output cpu and gpu ok, but doc will be modify
上级
9e72cc5c
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
145 addition
and
42 deletion
+145
-42
paddle/operators/detection_output_op.cc
paddle/operators/detection_output_op.cc
+8
-7
paddle/operators/detection_output_op.h
paddle/operators/detection_output_op.h
+73
-22
paddle/operators/math/detection_util.h
paddle/operators/math/detection_util.h
+9
-13
python/paddle/v2/fluid/tests/test_detection_output_op.py
python/paddle/v2/fluid/tests/test_detection_output_op.py
+55
-0
未找到文件。
paddle/operators/detection_output_op.cc
浏览文件 @
fe177b62
...
@@ -65,17 +65,18 @@ class Detection_output_Op : public framework::OperatorWithKernel {
...
@@ -65,17 +65,18 @@ class Detection_output_Op : public framework::OperatorWithKernel {
public:
public:
using
framework
::
OperatorWithKernel
::
OperatorWithKernel
;
using
framework
::
OperatorWithKernel
::
OperatorWithKernel
;
void
InferShape
(
framework
::
InferShapeContext
*
ctx
)
const
override
{
void
InferShape
(
framework
::
InferShapeContext
*
ctx
)
const
override
{
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"X"
),
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"Loc"
),
"Input(X) of Detection_output_Op"
"should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"Conf"
),
"Input(X) of Detection_output_Op"
"should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasInput
(
"PriorBox"
),
"Input(X) of Detection_output_Op"
"Input(X) of Detection_output_Op"
"should not be null."
);
"should not be null."
);
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"Out"
),
PADDLE_ENFORCE
(
ctx
->
HasOutput
(
"Out"
),
"Output(Out) of Detection_output_Op should not be null."
);
"Output(Out) of Detection_output_Op should not be null."
);
auto
in_x_dims
=
ctx
->
GetInputDim
(
"X"
);
std
::
vector
<
int64_t
>
output_shape
({
1
,
7
});
int
pyramid_height
=
ctx
->
Attrs
().
Get
<
int
>
(
"pyramid_height"
);
PADDLE_ENFORCE
(
in_x_dims
.
size
()
==
4
,
"Detection_output_ing intput must be of 4-dimensional."
);
int
outlen
=
((
std
::
pow
(
4
,
pyramid_height
)
-
1
)
/
(
4
-
1
))
*
in_x_dims
[
1
];
std
::
vector
<
int64_t
>
output_shape
({
in_x_dims
[
0
],
outlen
});
ctx
->
SetOutputDim
(
"Out"
,
framework
::
make_ddim
(
output_shape
));
ctx
->
SetOutputDim
(
"Out"
,
framework
::
make_ddim
(
output_shape
));
}
}
};
};
...
...
paddle/operators/detection_output_op.h
浏览文件 @
fe177b62
...
@@ -40,6 +40,9 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
...
@@ -40,6 +40,9 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
int
input_num
=
in_loc
->
dims
()[
0
];
int
input_num
=
in_loc
->
dims
()[
0
];
int
batch_size
=
in_loc
->
dims
()[
1
];
int
batch_size
=
in_loc
->
dims
()[
1
];
int
channels
=
in_loc
->
dims
()[
2
];
int
height
=
in_loc
->
dims
()[
3
];
int
weight
=
in_loc
->
dims
()[
4
];
int
loc_sum_size
=
in_loc
->
numel
();
int
loc_sum_size
=
in_loc
->
numel
();
int
conf_sum_size
=
in_conf
->
numel
();
int
conf_sum_size
=
in_conf
->
numel
();
std
::
vector
<
int64_t
>
loc_shape_vec
({
1
,
loc_sum_size
});
std
::
vector
<
int64_t
>
loc_shape_vec
({
1
,
loc_sum_size
});
...
@@ -49,17 +52,62 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
...
@@ -49,17 +52,62 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
framework
::
DDim
conf_shape
(
framework
::
make_ddim
(
conf_shape_vec
));
framework
::
DDim
conf_shape
(
framework
::
make_ddim
(
conf_shape_vec
));
framework
::
Tensor
loc_tensor
;
framework
::
Tensor
loc_tensor
;
framework
::
Tensor
conf_tensor
;
framework
::
Tensor
conf_tensor
;
loc_tensor
.
Resize
(
loc_shape
);
conf_tensor
.
Resize
(
conf_shape
);
loc_tensor
.
mutable_data
<
T
>
(
loc_shape
,
context
.
GetPlace
());
loc_tensor
.
mutable_data
<
T
>
(
loc_shape
,
context
.
GetPlace
());
conf_tensor
.
mutable_data
<
T
>
(
conf_shape
,
context
.
GetPlace
());
conf_tensor
.
mutable_data
<
T
>
(
conf_shape
,
context
.
GetPlace
());
framework
::
Tensor
loc_cpu
;
framework
::
Tensor
conf_cpu
;
framework
::
Tensor
priorbox_cpu
;
const
T
*
in_loc_data
=
in_loc
->
data
<
T
>
();
const
T
*
in_conf_data
=
in_conf
->
data
<
T
>
();
T
*
loc_data
;
T
*
conf_data
;
const
T
*
priorbox_data
=
in_priorbox
->
data
<
T
>
();
// KNCHW ==> NHWC
if
(
platform
::
is_gpu_place
(
context
.
GetPlace
()))
{
loc_cpu
.
mutable_data
<
T
>
(
in_loc
->
dims
(),
platform
::
CPUPlace
());
framework
::
CopyFrom
(
*
in_loc
,
platform
::
CPUPlace
(),
context
.
device_context
(),
&
loc_cpu
);
in_loc_data
=
loc_cpu
.
data
<
T
>
();
conf_cpu
.
mutable_data
<
T
>
(
in_conf
->
dims
(),
platform
::
CPUPlace
());
framework
::
CopyFrom
(
*
in_conf
,
platform
::
CPUPlace
(),
context
.
device_context
(),
&
conf_cpu
);
in_conf_data
=
conf_cpu
.
data
<
T
>
();
priorbox_cpu
.
mutable_data
<
T
>
(
in_priorbox
->
dims
(),
platform
::
CPUPlace
());
framework
::
CopyFrom
(
*
in_priorbox
,
platform
::
CPUPlace
(),
context
.
device_context
(),
&
priorbox_cpu
);
priorbox_data
=
priorbox_cpu
.
data
<
T
>
();
loc_tensor
.
mutable_data
<
T
>
(
loc_shape
,
platform
::
CPUPlace
());
conf_tensor
.
mutable_data
<
T
>
(
conf_shape
,
platform
::
CPUPlace
());
}
T
*
loc_tensor_data
=
loc_tensor
.
data
<
T
>
();
T
*
conf_tensor_data
=
conf_tensor
.
data
<
T
>
();
for
(
int
i
=
0
;
i
<
input_num
;
++
i
)
{
for
(
int
i
=
0
;
i
<
input_num
;
++
i
)
{
math
::
appendWithPermute
<
T
>
(
*
in_loc
,
&
loc_tensor
);
math
::
appendWithPermute
<
T
>
(
in_loc_data
,
input_num
,
batch_size
,
channels
,
math
::
appendWithPermute
<
T
>
(
*
in_conf
,
&
conf_tensor
);
height
,
weight
,
loc_tensor_data
);
math
::
appendWithPermute
<
T
>
(
in_conf_data
,
input_num
,
batch_size
,
channels
,
height
,
weight
,
conf_tensor_data
);
}
loc_data
=
loc_tensor
.
data
<
T
>
();
if
(
platform
::
is_gpu_place
(
context
.
GetPlace
()))
{
framework
::
Tensor
conf_gpu
;
conf_gpu
.
Resize
(
conf_shape
);
conf_gpu
.
mutable_data
<
T
>
(
conf_shape
,
context
.
GetPlace
());
framework
::
CopyFrom
(
conf_tensor
,
platform
::
GPUPlace
(),
context
.
device_context
(),
&
conf_gpu
);
// softmax
math
::
SoftmaxFunctor
<
Place
,
T
>
()(
context
.
device_context
(),
&
conf_gpu
,
&
conf_gpu
);
conf_tensor
.
mutable_data
<
T
>
(
conf_gpu
.
dims
(),
platform
::
CPUPlace
());
framework
::
CopyFrom
(
conf_gpu
,
platform
::
CPUPlace
(),
context
.
device_context
(),
&
conf_tensor
);
}
else
{
// softmax
math
::
SoftmaxFunctor
<
Place
,
T
>
()(
context
.
device_context
(),
&
conf_tensor
,
&
conf_tensor
);
}
}
// softmax
conf_data
=
conf_tensor
.
data
<
T
>
();
math
::
SoftmaxFunctor
<
Place
,
T
>
()(
context
.
device_context
(),
&
conf_tensor
,
&
conf_tensor
);
// get decode bboxes
// get decode bboxes
size_t
num_priors
=
in_priorbox
->
numel
()
/
8
;
size_t
num_priors
=
in_priorbox
->
numel
()
/
8
;
std
::
vector
<
std
::
vector
<
operators
::
math
::
BBox
<
T
>>>
all_decoded_bboxes
;
std
::
vector
<
std
::
vector
<
operators
::
math
::
BBox
<
T
>>>
all_decoded_bboxes
;
...
@@ -69,29 +117,26 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
...
@@ -69,29 +117,26 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
size_t
prior_offset
=
i
*
8
;
size_t
prior_offset
=
i
*
8
;
size_t
loc_pred_offset
=
n
*
num_priors
*
4
+
i
*
4
;
size_t
loc_pred_offset
=
n
*
num_priors
*
4
+
i
*
4
;
std
::
vector
<
math
::
BBox
<
T
>>
prior_bbox_vec
;
std
::
vector
<
math
::
BBox
<
T
>>
prior_bbox_vec
;
math
::
getBBoxFromPriorData
<
T
>
(
in_priorbox
->
data
<
T
>
()
+
prior_offset
,
1
,
math
::
getBBoxFromPriorData
<
T
>
(
priorbox_data
+
prior_offset
,
1
,
prior_bbox_vec
);
prior_bbox_vec
);
std
::
vector
<
std
::
vector
<
T
>>
prior_bbox_var
;
std
::
vector
<
std
::
vector
<
T
>>
prior_bbox_var
;
math
::
getBBoxVarFromPriorData
<
T
>
(
in_priorbox
->
data
<
T
>
()
+
prior_offset
,
math
::
getBBoxVarFromPriorData
<
T
>
(
priorbox_data
+
prior_offset
,
1
,
1
,
prior_bbox_var
);
prior_bbox_var
);
std
::
vector
<
T
>
loc_pred_data
;
std
::
vector
<
T
>
loc_pred_data
;
for
(
size_t
j
=
0
;
j
<
4
;
++
j
)
for
(
size_t
j
=
0
;
j
<
4
;
++
j
)
loc_pred_data
.
push_back
(
loc_pred_data
.
push_back
(
*
(
loc_data
+
loc_pred_offset
+
j
));
*
(
loc_tensor
.
data
<
T
>
()
+
loc_pred_offset
+
j
));
math
::
BBox
<
T
>
bbox
=
math
::
decodeBBoxWithVar
<
T
>
(
math
::
BBox
<
T
>
bbox
=
math
::
decodeBBoxWithVar
<
T
>
(
prior_bbox_vec
[
0
],
prior_bbox_var
[
0
],
loc_pred_data
);
prior_bbox_vec
[
0
],
prior_bbox_var
[
0
],
loc_pred_data
);
decoded_bboxes
.
push_back
(
bbox
);
decoded_bboxes
.
push_back
(
bbox
);
}
}
all_decoded_bboxes
.
push_back
(
decoded_bboxes
);
all_decoded_bboxes
.
push_back
(
decoded_bboxes
);
}
}
std
::
vector
<
std
::
map
<
size_t
,
std
::
vector
<
size_t
>>>
all_indices
;
std
::
vector
<
std
::
map
<
size_t
,
std
::
vector
<
size_t
>>>
all_indices
;
int
num_kept
=
math
::
getDetectionIndices
<
T
>
(
int
num_kept
=
math
::
getDetectionIndices
<
T
>
(
conf_
tensor
.
data
<
T
>
(),
num_priors
,
num_classes
,
background_label_id
,
conf_
data
,
num_priors
,
num_classes
,
background_label_id
,
batch_size
,
batch_size
,
confidence_threshold
,
nms_top_k
,
nms_threshold
,
top_k
,
confidence_threshold
,
nms_top_k
,
nms_threshold
,
top_k
,
all_decoded_bboxes
,
&
all_indices
);
all_decoded_bboxes
,
&
all_indices
);
framework
::
Tensor
out_tmp
;
if
(
num_kept
<=
0
)
{
if
(
num_kept
<=
0
)
{
std
::
vector
<
int64_t
>
out_shape_vec
({
0
,
0
});
std
::
vector
<
int64_t
>
out_shape_vec
({
0
,
0
});
framework
::
DDim
out_shape
(
framework
::
make_ddim
(
out_shape_vec
));
framework
::
DDim
out_shape
(
framework
::
make_ddim
(
out_shape_vec
));
...
@@ -100,14 +145,20 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
...
@@ -100,14 +145,20 @@ class Detection_output_Kernel : public framework::OpKernel<T> {
}
}
std
::
vector
<
int64_t
>
out_shape_vec
({
num_kept
,
7
});
std
::
vector
<
int64_t
>
out_shape_vec
({
num_kept
,
7
});
framework
::
DDim
out_shape
(
framework
::
make_ddim
(
out_shape_vec
));
framework
::
DDim
out_shape
(
framework
::
make_ddim
(
out_shape_vec
));
out_tmp
.
mutable_data
<
T
>
(
out_shape
,
context
.
GetPlace
());
T
*
out_data
=
out_tmp
.
data
<
T
>
();
math
::
getDetectionOutput
<
T
>
(
conf_tensor
.
data
<
T
>
(),
num_kept
,
num_priors
,
num_classes
,
batch_size
,
all_indices
,
all_decoded_bboxes
,
out_data
);
out
->
mutable_data
<
T
>
(
out_shape
,
context
.
GetPlace
());
out
->
mutable_data
<
T
>
(
out_shape
,
context
.
GetPlace
());
out
->
ShareDataWith
(
out_tmp
);
framework
::
Tensor
out_cpu
;
T
*
out_data
=
out
->
data
<
T
>
();
if
(
platform
::
is_gpu_place
(
context
.
GetPlace
()))
{
out_cpu
.
mutable_data
<
T
>
(
out
->
dims
(),
platform
::
CPUPlace
());
out_data
=
out_cpu
.
data
<
T
>
();
}
math
::
getDetectionOutput
<
T
>
(
conf_data
,
num_kept
,
num_priors
,
num_classes
,
batch_size
,
all_indices
,
all_decoded_bboxes
,
out_data
);
if
(
platform
::
is_gpu_place
(
context
.
GetPlace
()))
{
framework
::
CopyFrom
(
out_cpu
,
platform
::
GPUPlace
(),
context
.
device_context
(),
out
);
}
}
}
};
};
}
// namespace operators
}
// namespace operators
...
...
paddle/operators/math/detection_util.h
浏览文件 @
fe177b62
...
@@ -50,27 +50,23 @@ struct BBox {
...
@@ -50,27 +50,23 @@ struct BBox {
};
};
// KNCHW ==> NHWC
// KNCHW ==> NHWC
template
<
typename
T
>
template
<
typename
T
>
int
appendWithPermute
(
const
framework
::
Tensor
&
input
,
int
appendWithPermute
(
const
T
*
input_data
,
int
input_nums
,
int
batch_size
,
framework
::
Tensor
*
output
)
{
int
channels
,
int
height
,
int
weight
,
T
*
output_data
)
{
const
int
input_nums
=
input
.
dims
()[
0
];
const
int
batch_size
=
input
.
dims
()[
1
];
const
int
channels
=
input
.
dims
()[
2
];
const
int
height
=
input
.
dims
()[
3
];
const
int
weight
=
input
.
dims
()[
4
];
int
image_size
=
height
*
weight
;
int
image_size
=
height
*
weight
;
int
numel
=
input_nums
*
batch_size
*
channels
*
height
*
weight
;
int
offset
=
0
;
int
offset
=
0
;
for
(
int
p
=
0
;
p
<
input_nums
;
++
p
)
{
for
(
int
p
=
0
;
p
<
input_nums
;
++
p
)
{
int
in_p_offset
=
p
*
batch_size
*
channels
*
image_size
;
int
in_p_offset
=
p
*
batch_size
*
channels
*
image_size
;
for
(
int
n
=
0
;
n
<
batch_size
;
++
n
)
{
for
(
int
n
=
0
;
n
<
batch_size
;
++
n
)
{
int
in_n_offset
=
n
*
channels
*
image_size
;
int
in_n_offset
=
n
*
channels
*
image_size
;
int
out_n_offset
=
n
*
input
.
numel
()
/
batch_size
+
offset
;
int
out_n_offset
=
n
*
numel
/
batch_size
+
offset
;
int
in_stride
=
image_size
;
int
in_stride
=
image_size
;
int
out_stride
=
channels
;
int
out_stride
=
channels
;
const
T
*
in_data
=
input
.
data
<
T
>
()
+
in_p_offset
+
in_n_offset
;
const
T
*
in_data
=
input
_data
+
in_p_offset
+
in_n_offset
;
T
*
out_data
=
output
->
data
<
T
>
()
+
out_n_offset
;
T
*
out_data
=
output
_data
+
out_n_offset
;
for
(
int
i
=
0
;
i
<
channels
;
++
i
)
{
for
(
int
c
=
0
;
c
<
channels
;
++
c
)
{
for
(
int
c
=
0
;
c
<
image_size
;
++
c
)
{
for
(
int
i
=
0
;
i
<
image_size
;
++
i
)
{
out_data
[
out_stride
*
c
+
i
]
=
in_data
[
i
*
in_stride
+
c
];
out_data
[
out_stride
*
i
+
c
]
=
in_data
[
c
*
in_stride
+
i
];
}
}
}
}
}
}
...
...
python/paddle/v2/fluid/tests/test_detection_output_op.py
0 → 100644
浏览文件 @
fe177b62
import
unittest
import
numpy
as
np
from
op_test
import
OpTest
class
TestUnpoolOp
(
OpTest
):
def
setUp
(
self
):
self
.
op_type
=
"detection_output"
self
.
init_test_case
()
#loc = np.zeros((1, 4, 4, 1, 1))
#conf = np.zero((1, 4, 2, 1, 1))
loc
=
np
.
array
([[[[[
0.1
]],
[[
0.1
]],
[[
0.1
]],
[[
0.1
]]],
[[[
0.1
]],
[[
0.1
]],
[[
0.1
]],
[[
0.1
]]],
[[[
0.1
]],
[[
0.1
]],
[[
0.1
]],
[[
0.1
]]],
[[[
0.1
]],
[[
0.1
]],
[[
0.1
]],
[[
0.1
]]]]])
conf
=
np
.
array
([[[[[
0.1
]],
[[
0.9
]]],
[[[
0.2
]],
[[
0.8
]]]],
[[[[
0.3
]],
[[
0.7
]]],
[[[
0.4
]],
[[
0.6
]]]]])
priorbox
=
np
.
array
([
0.1
,
0.1
,
0.5
,
0.5
,
0.1
,
0.1
,
0.2
,
0.2
,
\
0.2
,
0.2
,
0.6
,
0.6
,
0.1
,
0.1
,
0.2
,
0.2
,
\
0.3
,
0.3
,
0.7
,
0.7
,
0.1
,
0.1
,
0.2
,
0.2
,
\
0.4
,
0.4
,
0.8
,
0.8
,
0.1
,
0.1
,
0.2
,
0.2
])
output
=
np
.
array
([
0
,
1
,
0.68997443
,
0.099959746
,
0.099959746
,
\
0.50804031
,
0.50804031
])
self
.
inputs
=
{
'Loc'
:
loc
.
astype
(
'float32'
),
'Conf'
:
conf
.
astype
(
'float32'
),
'PriorBox'
:
priorbox
.
astype
(
'float32'
)
}
self
.
attrs
=
{
'num_classes'
:
self
.
num_classes
,
'top_k'
:
self
.
top_k
,
'nms_top_k'
:
self
.
nms_top_k
,
'background_label_id'
:
self
.
background_label_id
,
'nms_threshold'
:
self
.
nms_threshold
,
'confidence_threshold'
:
self
.
confidence_threshold
,
}
self
.
outputs
=
{
'Out'
:
output
.
astype
(
'float32'
)}
def
test_check_output
(
self
):
self
.
check_output
()
def
init_test_case
(
self
):
self
.
num_classes
=
2
self
.
top_k
=
10
self
.
nms_top_k
=
20
self
.
background_label_id
=
0
self
.
nms_threshold
=
0.01
self
.
confidence_threshold
=
0.01
if
__name__
==
'__main__'
:
unittest
.
main
()
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