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
s920243400
PaddleDetection
提交
3c40cb76
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
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
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
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
提交
3c40cb76
编写于
3月 01, 2019
作者:
N
nhzlx
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
7 refine zero copy
update trt in docker file test=develop
上级
2eff3e26
变更
6
显示空白变更内容
内联
并排
Showing
6 changed file
with
120 addition
and
5 deletion
+120
-5
Dockerfile
Dockerfile
+2
-1
paddle/fluid/inference/api/analysis_predictor.cc
paddle/fluid/inference/api/analysis_predictor.cc
+31
-0
paddle/fluid/inference/api/analysis_predictor.h
paddle/fluid/inference/api/analysis_predictor.h
+7
-0
paddle/fluid/inference/api/details/zero_copy_tensor.cc
paddle/fluid/inference/api/details/zero_copy_tensor.cc
+58
-2
paddle/fluid/inference/api/details/zero_copy_tensor_dummy.cc
paddle/fluid/inference/api/details/zero_copy_tensor_dummy.cc
+1
-1
paddle/fluid/inference/api/paddle_api.h
paddle/fluid/inference/api/paddle_api.h
+21
-1
未找到文件。
Dockerfile
浏览文件 @
3c40cb76
...
...
@@ -75,7 +75,8 @@ RUN curl -s -q https://glide.sh/get | sh
# and its size is only one-third of the official one.
# 2. Manually add ~IPluginFactory() in IPluginFactory class of NvInfer.h, otherwise, it couldn't work in paddle.
# See https://github.com/PaddlePaddle/Paddle/issues/10129 for details.
RUN
wget
-qO-
http://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.0.3.Ubuntu-16.04.4.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz |
\
RUN
wget
-qO-
https://paddlepaddledeps.cdn.bcebos.com/TensorRT-4.0.1.6-ubuntu14.04.x86_64-gnu.cuda-8.0.cudnn7.0.tar.gz |
\
tar
-xz
-C
/usr/local
&&
\
cp
-rf
/usr/local/TensorRT/include /usr
&&
\
cp
-rf
/usr/local/TensorRT/lib /usr
...
...
paddle/fluid/inference/api/analysis_predictor.cc
浏览文件 @
3c40cb76
...
...
@@ -435,12 +435,14 @@ void AnalysisPredictor::PrepareFeedFetch() {
}
feeds_
[
idx
]
=
op
;
feed_names_
[
op
->
Output
(
"Out"
)[
0
]]
=
idx
;
idx2feeds_
[
idx
]
=
op
->
Output
(
"Out"
)[
0
];
}
else
if
(
op
->
Type
()
==
"fetch"
)
{
int
idx
=
boost
::
get
<
int
>
(
op
->
GetAttr
(
"col"
));
if
(
fetches_
.
size
()
<=
static_cast
<
size_t
>
(
idx
))
{
fetches_
.
resize
(
idx
+
1
);
}
fetches_
[
idx
]
=
op
;
idx2fetches_
[
idx
]
=
op
->
Input
(
"X"
)[
0
];
}
}
}
...
...
@@ -453,6 +455,22 @@ void AnalysisPredictor::CreateFeedFetchVar(framework::Scope *scope) {
var
->
GetMutable
<
framework
::
FeedFetchList
>
();
}
std
::
vector
<
std
::
string
>
AnalysisPredictor
::
GetInputNames
()
{
std
::
vector
<
std
::
string
>
input_names
;
for
(
auto
&
item
:
idx2feeds_
)
{
input_names
.
push_back
(
item
.
second
);
}
return
input_names
;
}
std
::
vector
<
std
::
string
>
AnalysisPredictor
::
GetOutputNames
()
{
std
::
vector
<
std
::
string
>
output_names
;
for
(
auto
&
item
:
idx2fetches_
)
{
output_names
.
push_back
(
item
.
second
);
}
return
output_names
;
}
std
::
unique_ptr
<
ZeroCopyTensor
>
AnalysisPredictor
::
GetInputTensor
(
const
std
::
string
&
name
)
{
PADDLE_ENFORCE
(
executor_
->
scope
()
->
FindVar
(
name
),
"no name called %s"
,
name
);
...
...
@@ -460,6 +478,13 @@ std::unique_ptr<ZeroCopyTensor> AnalysisPredictor::GetInputTensor(
new
ZeroCopyTensor
(
static_cast
<
void
*>
(
executor_
->
scope
())));
res
->
input_or_output_
=
true
;
res
->
SetName
(
name
);
if
(
platform
::
is_cpu_place
(
place_
))
{
res
->
SetPlace
(
PaddlePlace
::
kCPU
);
}
else
{
auto
gpu_place
=
boost
::
get
<
platform
::
CUDAPlace
>
(
place_
);
res
->
SetPlace
(
PaddlePlace
::
kGPU
,
gpu_place
.
GetDeviceId
());
}
return
res
;
}
...
...
@@ -470,6 +495,12 @@ std::unique_ptr<ZeroCopyTensor> AnalysisPredictor::GetOutputTensor(
new
ZeroCopyTensor
(
static_cast
<
void
*>
(
executor_
->
scope
())));
res
->
input_or_output_
=
false
;
res
->
SetName
(
name
);
if
(
platform
::
is_cpu_place
(
place_
))
{
res
->
SetPlace
(
PaddlePlace
::
kCPU
);
}
else
{
auto
gpu_place
=
boost
::
get
<
platform
::
CUDAPlace
>
(
place_
);
res
->
SetPlace
(
PaddlePlace
::
kGPU
,
gpu_place
.
GetDeviceId
());
}
return
res
;
}
...
...
paddle/fluid/inference/api/analysis_predictor.h
浏览文件 @
3c40cb76
...
...
@@ -55,6 +55,9 @@ class AnalysisPredictor : public PaddlePredictor {
std
::
vector
<
PaddleTensor
>
*
output_data
,
int
batch_size
=
-
1
)
override
;
std
::
vector
<
std
::
string
>
GetInputNames
();
std
::
vector
<
std
::
string
>
GetOutputNames
();
std
::
unique_ptr
<
ZeroCopyTensor
>
GetInputTensor
(
const
std
::
string
&
name
)
override
;
std
::
unique_ptr
<
ZeroCopyTensor
>
GetOutputTensor
(
...
...
@@ -133,7 +136,11 @@ class AnalysisPredictor : public PaddlePredictor {
std
::
shared_ptr
<
framework
::
ProgramDesc
>
inference_program_
;
std
::
vector
<
framework
::
OpDesc
*>
feeds_
;
std
::
map
<
std
::
string
,
size_t
>
feed_names_
;
// Sorted according to the idx.
std
::
map
<
size_t
,
std
::
string
>
idx2feeds_
;
std
::
vector
<
framework
::
OpDesc
*>
fetches_
;
std
::
map
<
size_t
,
std
::
string
>
idx2fetches_
;
// Memory buffer for feed inputs. The temporary LoDTensor will cause serious
// concurrency problems, wrong results and memory leak, so cache them.
std
::
vector
<
framework
::
LoDTensor
>
feed_tensors_
;
...
...
paddle/fluid/inference/api/details/zero_copy_tensor.cc
浏览文件 @
3c40cb76
...
...
@@ -15,6 +15,7 @@
#include "paddle/fluid/framework/lod_tensor.h"
#include "paddle/fluid/framework/scope.h"
#include "paddle/fluid/inference/api/paddle_inference_api.h"
#include "paddle/fluid/memory/memcpy.h"
#include "paddle/fluid/platform/enforce.h"
namespace
paddle
{
...
...
@@ -73,6 +74,61 @@ T *ZeroCopyTensor::data(PaddlePlace *place, int *size) const {
return
res
;
}
template
<
typename
T
>
void
ZeroCopyTensor
::
copy_from_cpu
(
const
T
*
data
)
{
EAGER_GET_TENSOR
;
PADDLE_ENFORCE_GE
(
tensor
->
numel
(),
0
,
"You should call ZeroCopyTensor::Reshape(const std::vector<int> &shape)"
"function before copy data from cpu."
);
size_t
ele_size
=
tensor
->
numel
()
*
sizeof
(
T
);
if
(
place_
==
PaddlePlace
::
kCPU
)
{
auto
*
t_data
=
tensor
->
mutable_data
<
T
>
(
platform
::
CPUPlace
());
std
::
memcpy
(
static_cast
<
void
*>
(
t_data
),
data
,
ele_size
);
}
else
{
#ifdef PADDLE_WITH_CUDA
platform
::
DeviceContextPool
&
pool
=
platform
::
DeviceContextPool
::
Instance
();
platform
::
CUDAPlace
gpu_place
(
device_
);
auto
*
t_data
=
tensor
->
mutable_data
<
T
>
(
gpu_place
);
auto
*
dev_ctx
=
static_cast
<
const
platform
::
CUDADeviceContext
*>
(
pool
.
Get
(
gpu_place
));
memory
::
Copy
(
gpu_place
,
static_cast
<
void
*>
(
t_data
),
platform
::
CPUPlace
(),
data
,
ele_size
,
dev_ctx
->
stream
());
#else
PADDLE_THROW
(
"Not compile with CUDA, should not reach here."
);
#endif
}
}
template
<
typename
T
>
void
ZeroCopyTensor
::
copy_to_cpu
(
T
*
data
)
{
EAGER_GET_TENSOR
;
auto
ele_num
=
tensor
->
numel
();
auto
*
t_data
=
tensor
->
data
<
T
>
();
auto
t_place
=
tensor
->
place
();
if
(
platform
::
is_cpu_place
(
t_place
))
{
std
::
memcpy
(
static_cast
<
void
*>
(
data
),
t_data
,
ele_num
*
sizeof
(
T
));
}
else
{
#ifdef PADDLE_WITH_CUDA
platform
::
DeviceContextPool
&
pool
=
platform
::
DeviceContextPool
::
Instance
();
auto
gpu_place
=
boost
::
get
<
platform
::
CUDAPlace
>
(
t_place
);
auto
*
dev_ctx
=
static_cast
<
const
platform
::
CUDADeviceContext
*>
(
pool
.
Get
(
gpu_place
));
memory
::
Copy
(
platform
::
CPUPlace
(),
static_cast
<
void
*>
(
data
),
gpu_place
,
t_data
,
ele_num
*
sizeof
(
T
),
dev_ctx
->
stream
());
#else
PADDLE_THROW
(
"Not compile with CUDA, should not reach here."
);
#endif
}
}
template
void
ZeroCopyTensor
::
copy_from_cpu
<
float
>(
const
float
*
data
);
template
void
ZeroCopyTensor
::
copy_from_cpu
<
int64_t
>(
const
int64_t
*
data
);
template
void
ZeroCopyTensor
::
copy_to_cpu
<
float
>(
float
*
data
);
template
void
ZeroCopyTensor
::
copy_to_cpu
<
int64_t
>(
int64_t
*
data
);
template
float
*
ZeroCopyTensor
::
data
<
float
>(
PaddlePlace
*
place
,
int
*
size
)
const
;
template
int64_t
*
ZeroCopyTensor
::
data
<
int64_t
>(
PaddlePlace
*
place
,
...
...
@@ -92,10 +148,10 @@ void *ZeroCopyTensor::FindTensor() const {
return
tensor
;
}
std
::
vector
<
int
64_t
>
ZeroCopyTensor
::
shape
()
const
{
std
::
vector
<
int
>
ZeroCopyTensor
::
shape
()
const
{
EAGER_GET_TENSOR
;
PADDLE_ENFORCE
(
tensor_
,
"not found tensor called %s in the scope"
,
name_
);
return
framework
::
vectorize
(
tensor
->
dims
());
return
framework
::
vectorize
2int
(
tensor
->
dims
());
}
void
ZeroCopyTensor
::
SetLoD
(
const
std
::
vector
<
std
::
vector
<
size_t
>>
&
x
)
{
...
...
paddle/fluid/inference/api/details/zero_copy_tensor_dummy.cc
浏览文件 @
3c40cb76
...
...
@@ -37,7 +37,7 @@ template int64_t *ZeroCopyTensor::mutable_data(PaddlePlace place);
void
*
ZeroCopyTensor
::
FindTensor
()
const
{
return
nullptr
;
}
std
::
vector
<
int
64_t
>
ZeroCopyTensor
::
shape
()
const
{
return
{};
}
std
::
vector
<
int
>
ZeroCopyTensor
::
shape
()
const
{
return
{};
}
void
ZeroCopyTensor
::
SetLoD
(
const
std
::
vector
<
std
::
vector
<
size_t
>>
&
x
)
{}
...
...
paddle/fluid/inference/api/paddle_api.h
浏览文件 @
3c40cb76
...
...
@@ -160,11 +160,21 @@ class ZeroCopyTensor {
template
<
typename
T
>
T
*
data
(
PaddlePlace
*
place
,
int
*
size
)
const
;
std
::
vector
<
int64_t
>
shape
()
const
;
template
<
typename
T
>
void
copy_from_cpu
(
const
T
*
data
);
template
<
typename
T
>
void
copy_to_cpu
(
T
*
data
);
std
::
vector
<
int
>
shape
()
const
;
void
SetLoD
(
const
std
::
vector
<
std
::
vector
<
size_t
>>&
x
);
std
::
vector
<
std
::
vector
<
size_t
>>
lod
()
const
;
const
std
::
string
&
name
()
const
{
return
name_
;
}
void
SetPlace
(
PaddlePlace
place
,
int
device
=
-
1
)
{
place_
=
place
;
device_
=
device
;
}
protected:
explicit
ZeroCopyTensor
(
void
*
scope
)
:
scope_
{
scope
}
{}
...
...
@@ -179,6 +189,8 @@ class ZeroCopyTensor {
// The corresponding tensor pointer inside Paddle workspace is cached for
// performance.
mutable
void
*
tensor_
{
nullptr
};
PaddlePlace
place_
;
int
device_
;
};
/** A simple Inference API for Paddle.
...
...
@@ -200,6 +212,14 @@ class PaddlePredictor {
std
::
vector
<
PaddleTensor
>*
output_data
,
int
batch_size
=
-
1
)
=
0
;
/** \brief Get input names of the model
*/
virtual
std
::
vector
<
std
::
string
>
GetInputNames
()
{
return
{};
}
/** \brief Get output names of the model
*/
virtual
std
::
vector
<
std
::
string
>
GetOutputNames
()
{
return
{};
}
/** \brief Get a mutable tensor directly.
*
* NOTE Only works in AnalysisPredictor.
...
...
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