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
cf8a5573
P
Paddle
项目概览
PaddlePaddle
/
Paddle
接近 2 年 前同步成功
通知
2323
Star
20933
Fork
5424
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
未验证
提交
cf8a5573
编写于
2月 15, 2022
作者:
F
feng_shuai
提交者:
GitHub
2月 15, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
pool2d_coonvert_ut (#39545)
上级
a558d386
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
203 addition
and
143 deletion
+203
-143
paddle/fluid/inference/tensorrt/convert/pool2d_op.cc
paddle/fluid/inference/tensorrt/convert/pool2d_op.cc
+92
-54
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.cu
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.cu
+53
-8
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.h
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.h
+38
-46
python/paddle/fluid/tests/unittests/ir/inference/test_trt_convert_pool2d.py
...d/tests/unittests/ir/inference/test_trt_convert_pool2d.py
+9
-35
python/paddle/fluid/tests/unittests/ir/inference/test_trt_pool_op.py
...le/fluid/tests/unittests/ir/inference/test_trt_pool_op.py
+11
-0
未找到文件。
paddle/fluid/inference/tensorrt/convert/pool2d_op.cc
浏览文件 @
cf8a5573
...
...
@@ -106,6 +106,9 @@ class Pool2dOpConverter : public OpConverter {
reduce_operation
=
nvinfer1
::
ReduceOperation
::
kAVG
;
plugin_pool_type
=
plugin
::
PoolPlugin
::
PoolType
::
avg
;
}
if
(
global_pooling
||
adaptive
)
{
std
::
fill
(
paddings
.
begin
(),
paddings
.
end
(),
0
);
}
if
(
padding_algorithm
==
"VALID"
)
{
std
::
fill
(
paddings
.
begin
(),
paddings
.
end
(),
0
);
...
...
@@ -136,6 +139,46 @@ class Pool2dOpConverter : public OpConverter {
#endif
}
std
::
vector
<
int
>
real_paddings
=
paddings
;
for
(
int
i
=
0
;
i
<
2
;
++
i
)
{
int
copy_pad
=
*
(
paddings
.
begin
()
+
i
);
real_paddings
.
insert
(
real_paddings
.
begin
()
+
2
*
i
+
1
,
copy_pad
);
}
// SAME
if
(
padding_algorithm
==
"SAME"
)
{
// expand
for
(
int
i
=
0
;
i
<
2
;
++
i
)
{
int
copy_pad
=
*
(
paddings
.
begin
()
+
2
*
i
);
paddings
.
insert
(
paddings
.
begin
()
+
2
*
i
+
1
,
copy_pad
);
}
// compute
for
(
int
i
=
0
;
i
<
2
;
++
i
)
{
int
out_size
=
(
input_shape
.
d
[
2
+
i
]
+
strides
[
i
]
-
1
)
/
strides
[
i
];
int
pad_sum
=
std
::
max
(
(
out_size
-
1
)
*
strides
[
i
]
+
ksize
[
i
]
-
input_shape
.
d
[
2
+
i
],
0
);
int
pad_0
=
pad_sum
/
2
;
int
pad_1
=
pad_sum
-
pad_0
;
paddings
[
i
*
2
]
=
pad_0
;
paddings
[
i
*
2
+
1
]
=
pad_1
;
}
real_paddings
=
paddings
;
// slice
for
(
int
i
=
0
;
i
<
2
;
++
i
)
{
paddings
.
erase
(
paddings
.
begin
()
+
i
+
1
);
}
}
// VALID
if
(
padding_algorithm
==
"VALID"
)
{
std
::
fill
(
real_paddings
.
begin
(),
real_paddings
.
end
(),
0
);
}
if
(
global_pooling
==
true
&&
!
engine_
->
with_dynamic_shape
())
{
nv_ksize
.
d
[
0
]
=
input_shape
.
d
[
input_dims
-
2
];
nv_ksize
.
d
[
1
]
=
input_shape
.
d
[
input_dims
-
1
];
ksize
[
0
]
=
input_shape
.
d
[
input_dims
-
2
];
ksize
[
1
]
=
input_shape
.
d
[
input_dims
-
1
];
}
if
(
engine_
->
with_dynamic_shape
())
{
if
(
!
adaptive
&&
!
global_pooling
&&
!
ceil_mode
)
{
// input_shape.d < 0 means we can't get shape info here.
...
...
@@ -173,15 +216,15 @@ class Pool2dOpConverter : public OpConverter {
pool_layer
->
setPaddingMode
(
nvinfer1
::
PaddingMode
::
kEXPLICIT_ROUND_UP
);
}
layer
=
pool_layer
;
}
else
if
(
global_pooling
)
{
}
else
if
(
global_pooling
&&
!
adaptive
)
{
auto
*
reduce_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Reduce
,
*
input1
,
reduce_operation
,
12
,
true
);
layer
=
reduce_layer
;
}
else
{
#if IS_TRT_VERSION_GE(6000)
plugin
::
PoolPluginDynamic
*
plugin
=
new
plugin
::
PoolPluginDynamic
(
ceil_mode
,
pool_type
,
adaptive
,
ksize
,
strides
,
paddings
,
global_pooling
);
plugin
::
PoolPluginDynamic
*
plugin
=
new
plugin
::
PoolPluginDynamic
(
ceil_mode
,
pool_type
,
adaptive
,
exclusive
,
ksize
,
strides
,
paddings
,
global_pooling
);
layer
=
engine_
->
AddDynamicPlugin
(
&
input1
,
1
,
plugin
);
#endif
}
...
...
@@ -195,21 +238,13 @@ class Pool2dOpConverter : public OpConverter {
return
;
}
if
(
global_pooling
==
true
)
{
nv_ksize
.
d
[
0
]
=
input_shape
.
d
[
input_dims
-
2
];
nv_ksize
.
d
[
1
]
=
input_shape
.
d
[
input_dims
-
1
];
if
(
global_pooling
==
true
&&
adaptive
==
false
)
{
auto
*
pool_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Pooling
,
*
input1
,
nv_pool_type
,
nv_ksize
);
PADDLE_ENFORCE_NOT_NULL
(
pool_layer
,
platform
::
errors
::
Fatal
(
"trt pool layer in converter could not be created."
));
auto
output_name
=
op_desc
.
Output
(
"Out"
)[
0
];
pool_layer
->
setStride
(
nv_strides
);
pool_layer
->
setPadding
(
nv_paddings
);
if
(
padding_algorithm
==
"SAME"
)
{
pool_layer
->
setPaddingMode
(
nvinfer1
::
PaddingMode
::
kSAME_UPPER
);
}
pool_layer
->
setAverageCountExcludesPadding
(
exclusive
);
pool_layer
->
setName
((
"pool2d (Output: "
+
output_name
+
")"
).
c_str
());
pool_layer
->
getOutput
(
0
)
->
setName
(
output_name
.
c_str
());
engine_
->
SetITensor
(
output_name
,
pool_layer
->
getOutput
(
0
));
...
...
@@ -222,58 +257,61 @@ class Pool2dOpConverter : public OpConverter {
if
(
!
adaptive
)
{
if
(
ceil_mode
)
{
nvinfer1
::
DimsHW
pre_pad
(
0
,
0
)
;
nvinfer1
::
DimsHW
post_pad
(
0
,
0
);
// If ceil mode is true, we will pad the appropriate size to the input.
DealCeilMode
(
input_shape
,
ksize
,
strides
,
paddings
,
&
pre_pad
,
&
post_pad
,
input_dims
);
auto
*
pad_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Padding
,
*
input1
,
pre_pad
,
post_pad
);
std
::
vector
<
int
>
input_shape_v
;
for
(
int
i
=
0
;
i
<
input_dims
;
i
++
)
{
input_shape_v
.
push_back
(
input_shape
.
d
[
i
]);
}
plugin
::
PoolPlugin
*
plugin
=
new
plugin
::
PoolPlugin
(
ceil_mode
,
plugin_pool_type
,
adaptive
,
exclusive
,
ksize
,
strides
,
paddings
,
input_shape_v
,
real_paddings
);
auto
*
pool_layer
=
engine_
->
AddPlugin
(
&
input1
,
1
,
plugin
);
PADDLE_ENFORCE_NOT_NULL
(
p
ad_layer
,
platform
::
errors
::
Fatal
(
"Pad layer in poolOp converter could not be "
"created. The pointer to pad layer is `NULL`
."
));
input1
=
pad_layer
->
getOutput
(
0
)
;
}
p
ool_layer
,
platform
::
errors
::
Fatal
(
"trt pool plugin layer in converter could not be created
."
));
layer
=
pool_layer
;
}
else
{
#if IS_TRT_VERSION_GE(8000)
// Exclude padding pixels from the average mean is not supported well by
// TRT
// so enable padding for trt8.0 above.
if
((
g_post_pad
.
w
()
>
0
||
g_post_pad
.
h
()
>
0
)
&&
(
padding_algorithm
!=
"SAME"
)
&&
!
ceil_mode
)
{
auto
*
pad_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Padding
,
*
input1
,
g_pre_pad
,
g_post_pad
);
PADDLE_ENFORCE_NOT_NULL
(
pad_layer
,
platform
::
errors
::
Fatal
(
"Pad layer in poolOp converter could not be "
"created. The pointer to pad layer is `NULL`."
));
input1
=
pad_layer
->
getOutput
(
0
);
}
// Exclude padding pixels from the average mean is not supported well by
// TRT
// so enable padding for trt8.0 above.
if
((
g_post_pad
.
w
()
>
0
||
g_post_pad
.
h
()
>
0
)
&&
(
padding_algorithm
!=
"SAME"
)
&&
!
ceil_mode
)
{
auto
*
pad_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Padding
,
*
input1
,
g_pre_pad
,
g_post_pad
);
PADDLE_ENFORCE_NOT_NULL
(
pad_layer
,
platform
::
errors
::
Fatal
(
"Pad layer in poolOp converter could not be "
"created. The pointer to pad layer is `NULL`."
));
input1
=
pad_layer
->
getOutput
(
0
);
}
#endif
auto
*
pool_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Pooling
,
*
input1
,
nv_pool_type
,
nv_ksize
);
PADDLE_ENFORCE_NOT_NULL
(
pool_layer
,
platform
::
errors
::
Fatal
(
"trt pool layer in converter could not be created."
));
pool_layer
->
setStride
(
nv_strides
);
pool_layer
->
setPadding
(
nv_paddings
);
if
(
padding_algorithm
==
"SAME"
)
{
pool_layer
->
setPaddingMode
(
nvinfer1
::
PaddingMode
::
kSAME_UPPER
);
auto
*
pool_layer
=
TRT_ENGINE_ADD_LAYER
(
engine_
,
Pooling
,
*
input1
,
nv_pool_type
,
nv_ksize
);
PADDLE_ENFORCE_NOT_NULL
(
pool_layer
,
platform
::
errors
::
Fatal
(
"trt pool layer in converter could not be created."
));
pool_layer
->
setStride
(
nv_strides
);
pool_layer
->
setPadding
(
nv_paddings
);
if
(
padding_algorithm
==
"SAME"
)
{
pool_layer
->
setPaddingMode
(
nvinfer1
::
PaddingMode
::
kSAME_UPPER
);
}
pool_layer
->
setAverageCountExcludesPadding
(
exclusive
);
layer
=
pool_layer
;
}
pool_layer
->
setAverageCountExcludesPadding
(
exclusive
);
layer
=
pool_layer
;
}
else
{
// Average pooling needs to exclude the padding pixels from the average
// mean.
// It is not supported well by TRT, we use a plugin here
.
// It is not supported well by TRT, we use a plugin here
std
::
vector
<
int
>
input_shape_v
;
for
(
int
i
=
0
;
i
<
input_dims
;
i
++
)
{
input_shape_v
.
push_back
(
input_shape
.
d
[
i
]);
}
plugin
::
PoolPlugin
*
plugin
=
new
plugin
::
PoolPlugin
(
ceil_mode
,
plugin_pool_type
,
adaptive
,
ksize
,
strides
,
paddings
,
input_shape_v
);
plugin
::
PoolPlugin
*
plugin
=
new
plugin
::
PoolPlugin
(
ceil_mode
,
plugin_pool_type
,
adaptive
,
exclusive
,
ksize
,
strides
,
paddings
,
input_shape_v
,
real_paddings
);
auto
*
pool_layer
=
engine_
->
AddPlugin
(
&
input1
,
1
,
plugin
);
PADDLE_ENFORCE_NOT_NULL
(
pool_layer
,
...
...
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.cu
浏览文件 @
cf8a5573
...
...
@@ -35,6 +35,36 @@ nvinfer1::Dims PoolPlugin::getOutputDimensions(int index,
return
output_dims
;
}
size_t
PoolPlugin
::
getSerializationSize
()
const
TRT_NOEXCEPT
{
return
getBaseSerializationSize
()
+
SerializedSize
(
ceil_mode_
)
+
SerializedSize
(
pool_type_
)
+
SerializedSize
(
adaptive_
)
+
SerializedSize
(
exclusive_
)
+
SerializedSize
(
ksize_
)
+
SerializedSize
(
strides_
)
+
SerializedSize
(
paddings_
)
+
SerializedSize
(
real_paddings_
)
+
SerializedSize
(
input_shape_
)
+
SerializedSize
(
output_shape_
);
}
// TRT will call this func when we need to serialize the configuration of
// tensorrt.
void
PoolPlugin
::
serialize
(
void
*
buffer
)
const
TRT_NOEXCEPT
{
serializeBase
(
buffer
);
SerializeValue
(
&
buffer
,
ceil_mode_
);
SerializeValue
(
&
buffer
,
pool_type_
);
SerializeValue
(
&
buffer
,
adaptive_
);
SerializeValue
(
&
buffer
,
exclusive_
);
SerializeValue
(
&
buffer
,
ksize_
);
SerializeValue
(
&
buffer
,
strides_
);
SerializeValue
(
&
buffer
,
paddings_
);
SerializeValue
(
&
buffer
,
real_paddings_
);
SerializeValue
(
&
buffer
,
input_shape_
);
SerializeValue
(
&
buffer
,
output_shape_
);
}
PoolPlugin
*
PoolPlugin
::
clone
()
const
TRT_NOEXCEPT
{
return
new
PoolPlugin
(
ceil_mode_
,
pool_type_
,
adaptive_
,
exclusive_
,
ksize_
,
strides_
,
paddings_
,
input_shape_
,
real_paddings_
);
}
int
PoolPlugin
::
enqueue
(
int
batchSize
,
const
void
*
const
*
inputs
,
#if IS_TRT_VERSION_LT(8000)
void
**
outputs
,
void
*
workspace
,
...
...
@@ -59,14 +89,15 @@ int PoolPlugin::enqueue(int batchSize, const void *const *inputs,
paddle
::
operators
::
math
::
MaxPool
<
float
>
,
float
>
pool2d_forward
;
pool2d_forward
(
idata
,
input_shape
,
output_shape
,
ksize_
,
strides_
,
paddings_
,
true
,
adaptive_
,
odatas
[
0
],
stream
,
pool_process
);
paddings_
,
true
,
false
,
odatas
[
0
],
stream
,
pool_process
);
}
else
if
(
pool_type_
==
PoolType
::
avg
)
{
paddle
::
operators
::
math
::
AvgPool
<
float
>
pool_process
;
paddle
::
operators
::
math
::
Pool2dDirectCUDAFunctor
<
paddle
::
operators
::
math
::
AvgPool
<
float
>
,
float
>
pool2d_forward
;
pool2d_forward
(
idata
,
input_shape
,
output_shape
,
ksize_
,
strides_
,
paddings_
,
true
,
adaptive_
,
odatas
[
0
],
stream
,
pool_process
);
paddings_
,
exclusive_
,
adaptive_
,
odatas
[
0
],
stream
,
pool_process
);
}
return
cudaGetLastError
()
!=
cudaSuccess
;
...
...
@@ -82,6 +113,7 @@ PoolPluginDynamic::PoolPluginDynamic(void const *serialData,
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
pool_type
);
pool_type_
=
std
::
string
(
pool_type
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
adaptive_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
exclusive_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
ksize_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
strides_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
paddings_
);
...
...
@@ -90,21 +122,27 @@ PoolPluginDynamic::PoolPluginDynamic(void const *serialData,
size_t
PoolPluginDynamic
::
getSerializationSize
()
const
TRT_NOEXCEPT
{
return
SerializedSize
(
ceil_mode_
)
+
SerializedSize
(
pool_type_
.
c_str
())
+
SerializedSize
(
adaptive_
)
+
SerializedSize
(
ksiz
e_
)
+
SerializedSize
(
strides_
)
+
SerializedSize
(
padding
s_
)
+
SerializedSize
(
is_global_
);
SerializedSize
(
adaptive_
)
+
SerializedSize
(
exclusiv
e_
)
+
SerializedSize
(
ksize_
)
+
SerializedSize
(
stride
s_
)
+
SerializedSize
(
paddings_
)
+
SerializedSize
(
is_global_
);
}
void
PoolPluginDynamic
::
serialize
(
void
*
buffer
)
const
TRT_NOEXCEPT
{
SerializeValue
(
&
buffer
,
ceil_mode_
);
SerializeValue
(
&
buffer
,
pool_type_
.
c_str
());
SerializeValue
(
&
buffer
,
adaptive_
);
SerializeValue
(
&
buffer
,
exclusive_
);
SerializeValue
(
&
buffer
,
ksize_
);
SerializeValue
(
&
buffer
,
strides_
);
SerializeValue
(
&
buffer
,
paddings_
);
SerializeValue
(
&
buffer
,
is_global_
);
}
nvinfer1
::
IPluginV2DynamicExt
*
PoolPluginDynamic
::
clone
()
const
TRT_NOEXCEPT
{
return
new
PoolPluginDynamic
(
ceil_mode_
,
pool_type_
,
adaptive_
,
exclusive_
,
ksize_
,
strides_
,
paddings_
,
is_global_
);
}
nvinfer1
::
DimsExprs
PoolPluginDynamic
::
getOutputDimensions
(
int
output_index
,
const
nvinfer1
::
DimsExprs
*
inputs
,
int
nb_inputs
,
nvinfer1
::
IExprBuilder
&
expr_builder
)
TRT_NOEXCEPT
{
...
...
@@ -117,11 +155,14 @@ nvinfer1::DimsExprs PoolPluginDynamic::getOutputDimensions(
platform
::
errors
::
InvalidArgument
(
"The channel dimension should be "
"static, but we found it's dynamic."
));
nvinfer1
::
DimsExprs
output
(
inputs
[
0
]);
if
(
is_global_
)
{
if
(
is_global_
&&
!
adaptive_
)
{
output
.
d
[
2
]
=
expr_builder
.
constant
(
1
);
output
.
d
[
3
]
=
expr_builder
.
constant
(
1
);
return
output
;
}
if
(
is_global_
&&
adaptive_
)
{
return
inputs
[
0
];
}
if
(
adaptive_
)
{
output
.
d
[
2
]
=
expr_builder
.
constant
(
ksize_
[
0
]);
output
.
d
[
3
]
=
expr_builder
.
constant
(
ksize_
[
1
]);
...
...
@@ -245,6 +286,10 @@ int PoolPluginDynamic::enqueue(const nvinfer1::PluginTensorDesc *input_desc,
output_shape
[
2
]
=
data_dim
[
0
];
output_shape
[
3
]
=
data_dim
[
1
];
}
if
(
adaptive_
)
{
output_shape
[
2
]
=
h
;
output_shape
[
3
]
=
w
;
}
if
(
pool_type_
==
"max"
)
{
paddle
::
operators
::
math
::
MaxPool
<
float
>
pool_process
;
...
...
@@ -252,14 +297,14 @@ int PoolPluginDynamic::enqueue(const nvinfer1::PluginTensorDesc *input_desc,
paddle
::
operators
::
math
::
MaxPool
<
float
>
,
float
>
pool2d_forward
;
pool2d_forward
(
input
,
input_shape
,
output_shape
,
ksize
,
strides_
,
paddings
,
true
,
adaptive_
,
output
,
stream
,
pool_process
);
true
,
false
,
output
,
stream
,
pool_process
);
}
else
if
(
pool_type_
==
"avg"
)
{
paddle
::
operators
::
math
::
AvgPool
<
float
>
pool_process
;
paddle
::
operators
::
math
::
Pool2dDirectCUDAFunctor
<
paddle
::
operators
::
math
::
AvgPool
<
float
>
,
float
>
pool2d_forward
;
pool2d_forward
(
input
,
input_shape
,
output_shape
,
ksize
,
strides_
,
paddings
,
true
,
adaptive_
,
output
,
stream
,
pool_process
);
exclusive_
,
adaptive_
,
output
,
stream
,
pool_process
);
}
return
cudaGetLastError
()
!=
cudaSuccess
;
...
...
paddle/fluid/inference/tensorrt/plugin/pool_op_plugin.h
浏览文件 @
cf8a5573
...
...
@@ -29,26 +29,32 @@ static std::vector<int> CalcOutputSize(const std::vector<int>& input_shape,
const
bool
&
adaptive
,
const
std
::
vector
<
int
>&
ksize
,
const
std
::
vector
<
int
>&
strides
,
const
std
::
vector
<
int
>&
paddings
)
{
const
std
::
vector
<
int
>&
real_
paddings
)
{
std
::
vector
<
int
>
output_shape
=
input_shape
;
if
(
adaptive
)
{
output_shape
[
0
]
=
ksize
[
0
];
output_shape
[
1
]
=
ksize
[
1
];
}
else
{
int
output_h
,
output_w
;
if
(
!
ceil_mode
)
{
output_h
=
(
input_shape
[
0
]
-
ksize
[
0
]
+
2
*
paddings
[
0
])
/
strides
[
0
]
+
1
;
output_w
=
(
input_shape
[
1
]
-
ksize
[
1
]
+
2
*
paddings
[
1
])
/
strides
[
1
]
+
1
;
}
else
{
output_h
=
(
input_shape
[
0
]
-
ksize
[
0
]
+
2
*
paddings
[
0
]
+
strides
[
0
]
-
1
)
/
strides
[
0
]
+
1
;
output_w
=
(
input_shape
[
1
]
-
ksize
[
1
]
+
2
*
paddings
[
1
]
+
strides
[
1
]
-
1
)
/
strides
[
1
]
+
1
;
int
output_h
=
0
,
output_w
=
0
;
if
(
ceil_mode
)
{
output_h
=
(
input_shape
[
0
]
-
ksize
[
0
]
+
real_paddings
[
0
]
+
real_paddings
[
1
]
+
strides
[
0
]
-
1
)
/
strides
[
0
]
+
1
;
output_w
=
(
input_shape
[
1
]
-
ksize
[
1
]
+
real_paddings
[
2
]
+
real_paddings
[
3
]
+
strides
[
1
]
-
1
)
/
strides
[
1
]
+
1
;
}
// TRT will use native layer when ceil_model=false
/*
else{
output_h = (input_shape[0] - ksize[0] + real_paddings[0] +
real_paddings[1]) / strides[0] + 1;
output_w = (input_shape[1] - ksize[1] + real_paddings[2] +
real_paddings[3]) / strides[1] + 1;
}
*/
output_shape
[
0
]
=
output_h
;
output_shape
[
1
]
=
output_w
;
}
...
...
@@ -57,47 +63,32 @@ static std::vector<int> CalcOutputSize(const std::vector<int>& input_shape,
class
PoolPlugin
:
public
PluginTensorRT
{
public:
size_t
getSerializationSize
()
const
TRT_NOEXCEPT
override
{
return
getBaseSerializationSize
()
+
SerializedSize
(
ceil_mode_
)
+
SerializedSize
(
pool_type_
)
+
SerializedSize
(
adaptive_
)
+
SerializedSize
(
ksize_
)
+
SerializedSize
(
strides_
)
+
SerializedSize
(
paddings_
)
+
SerializedSize
(
input_shape_
)
+
SerializedSize
(
output_shape_
);
}
size_t
getSerializationSize
()
const
TRT_NOEXCEPT
override
;
// TRT will call this func when we need to serialize the configuration of
// tensorrt.
void
serialize
(
void
*
buffer
)
const
TRT_NOEXCEPT
override
{
serializeBase
(
buffer
);
SerializeValue
(
&
buffer
,
ceil_mode_
);
SerializeValue
(
&
buffer
,
pool_type_
);
SerializeValue
(
&
buffer
,
adaptive_
);
SerializeValue
(
&
buffer
,
ksize_
);
SerializeValue
(
&
buffer
,
strides_
);
SerializeValue
(
&
buffer
,
paddings_
);
SerializeValue
(
&
buffer
,
input_shape_
);
SerializeValue
(
&
buffer
,
output_shape_
);
}
void
serialize
(
void
*
buffer
)
const
TRT_NOEXCEPT
override
;
enum
class
PoolType
{
max
=
0
,
avg
,
};
PoolPlugin
()
{}
PoolPlugin
(
bool
ceil_mode
,
PoolType
pool_type
,
bool
adaptive
,
PoolPlugin
(
bool
ceil_mode
,
PoolType
pool_type
,
bool
adaptive
,
bool
exclusive
,
std
::
vector
<
int
>
ksize
,
std
::
vector
<
int
>
strides
,
std
::
vector
<
int
>
paddings
,
std
::
vector
<
int
>
input_shape
)
std
::
vector
<
int
>
paddings
,
std
::
vector
<
int
>
input_shape
,
std
::
vector
<
int
>
real_paddings
)
:
ceil_mode_
(
ceil_mode
),
pool_type_
(
pool_type
),
adaptive_
(
adaptive
),
exclusive_
(
exclusive
),
ksize_
(
ksize
),
strides_
(
strides
),
paddings_
(
paddings
),
real_paddings_
(
real_paddings
),
input_shape_
(
input_shape
)
{
output_shape_
=
input_shape_
;
std
::
vector
<
int
>
output_shape
=
CalcOutputSize
({
input_shape_
[
1
],
input_shape_
[
2
]},
ceil_mode_
,
adaptive_
,
ksize_
,
strides_
,
paddings_
);
adaptive_
,
ksize_
,
strides_
,
real_
paddings_
);
output_shape_
[
1
]
=
output_shape
[
0
];
output_shape_
[
2
]
=
output_shape
[
1
];
}
...
...
@@ -109,17 +100,16 @@ class PoolPlugin : public PluginTensorRT {
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
ceil_mode_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
pool_type_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
adaptive_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
exclusive_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
ksize_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
strides_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
paddings_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
real_paddings_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
input_shape_
);
DeserializeValue
(
&
serialData
,
&
serialLength
,
&
output_shape_
);
}
PoolPlugin
*
clone
()
const
TRT_NOEXCEPT
override
{
return
new
PoolPlugin
(
ceil_mode_
,
pool_type_
,
adaptive_
,
ksize_
,
strides_
,
paddings_
,
input_shape_
);
}
PoolPlugin
*
clone
()
const
TRT_NOEXCEPT
override
;
const
char
*
getPluginType
()
const
TRT_NOEXCEPT
override
{
return
"pool_plugin"
;
...
...
@@ -139,9 +129,11 @@ class PoolPlugin : public PluginTensorRT {
bool
ceil_mode_
;
PoolType
pool_type_
;
bool
adaptive_
;
bool
exclusive_
;
std
::
vector
<
int
>
ksize_
;
std
::
vector
<
int
>
strides_
;
std
::
vector
<
int
>
paddings_
;
std
::
vector
<
int
>
real_paddings_
;
std
::
vector
<
int
>
input_shape_
;
std
::
vector
<
int
>
output_shape_
;
};
...
...
@@ -167,12 +159,14 @@ class PoolPluginDynamic : public DynamicPluginTensorRT {
public:
PoolPluginDynamic
()
{}
PoolPluginDynamic
(
const
bool
&
ceil_mode
,
const
std
::
string
&
pool_type
,
const
bool
&
adaptive
,
const
std
::
vector
<
int
>&
ksize
,
const
bool
&
adaptive
,
bool
exclusive
,
const
std
::
vector
<
int
>&
ksize
,
const
std
::
vector
<
int
>&
strides
,
const
std
::
vector
<
int
>&
paddings
,
const
bool
&
is_global
)
:
ceil_mode_
(
ceil_mode
),
pool_type_
(
pool_type
),
adaptive_
(
adaptive
),
exclusive_
(
exclusive
),
ksize_
(
ksize
),
strides_
(
strides
),
paddings_
(
paddings
),
...
...
@@ -180,10 +174,7 @@ class PoolPluginDynamic : public DynamicPluginTensorRT {
PoolPluginDynamic
(
void
const
*
serialData
,
size_t
serialLength
);
~
PoolPluginDynamic
()
{}
nvinfer1
::
IPluginV2DynamicExt
*
clone
()
const
TRT_NOEXCEPT
override
{
return
new
PoolPluginDynamic
(
ceil_mode_
,
pool_type_
,
adaptive_
,
ksize_
,
strides_
,
paddings_
,
is_global_
);
}
nvinfer1
::
IPluginV2DynamicExt
*
clone
()
const
TRT_NOEXCEPT
override
;
const
char
*
getPluginType
()
const
TRT_NOEXCEPT
override
{
return
"pool_plugin_dynamic"
;
...
...
@@ -229,6 +220,7 @@ class PoolPluginDynamic : public DynamicPluginTensorRT {
bool
ceil_mode_
;
std
::
string
pool_type_
;
bool
adaptive_
;
bool
exclusive_
;
std
::
vector
<
int
>
ksize_
;
std
::
vector
<
int
>
strides_
;
std
::
vector
<
int
>
paddings_
;
...
...
python/paddle/fluid/tests/unittests/ir/inference/test_trt_convert_pool2d.py
浏览文件 @
cf8a5573
...
...
@@ -52,7 +52,7 @@ class TrtConvertPool2dTest(TrtLayerAutoScanTest):
return
np
.
random
.
random
([
24
,
3
,
3
,
3
]).
astype
(
np
.
float32
)
for
strides
in
[[
1
,
1
],
[
1
,
2
],
[
2
,
2
]]:
for
paddings
in
[[
0
,
2
],
[
0
,
3
]
,
[
0
,
1
,
2
,
3
]
]:
for
paddings
in
[[
0
,
2
],
[
0
,
3
]]:
for
pooling_type
in
[
'max'
,
'avg'
]:
for
padding_algotithm
in
[
'EXPLICIT'
,
'SAME'
,
'VAILD'
]:
for
ksize
in
[[
2
,
3
],
[
3
,
3
]]:
...
...
@@ -145,44 +145,18 @@ class TrtConvertPool2dTest(TrtLayerAutoScanTest):
True
),
1e-5
def
add_skip_trt_case
(
self
):
def
teller1
(
program_config
,
predictor_config
):
if
len
(
program_config
.
ops
[
0
].
attrs
[
'paddings'
])
==
4
:
return
True
return
False
self
.
add_skip_case
(
teller1
,
SkipReasons
.
TRT_NOT_IMPLEMENTED
,
"4-dims paddings are not support for trt now."
)
def
teller2
(
program_config
,
predictor_config
):
if
program_config
.
ops
[
0
].
attrs
[
'global_pooling'
]
==
True
:
return
True
return
False
self
.
add_skip_case
(
teller2
,
SkipReasons
.
TRT_NOT_IMPLEMENTED
,
"It is not support that global_pooling is true for trt now."
)
def
teller3
(
program_config
,
predictor_config
):
if
self
.
dynamic_shape
.
min_input_shape
==
{}
and
program_config
.
ops
[
0
].
attrs
[
'ceil_mode'
]
==
True
:
return
True
return
False
self
.
add_skip_case
(
teller3
,
SkipReasons
.
TRT_NOT_IMPLEMENTED
,
"It is not support that ceil_mode is true in static mode for trt now."
)
def
teller4
(
program_config
,
predictor_config
):
if
self
.
dynamic_shape
.
min_input_shape
!=
{}
and
(
program_config
.
ops
[
0
].
attrs
[
'strides'
]
==
[
1
,
2
]
or
program_config
.
ops
[
0
].
attrs
[
'strides'
]
==
[
2
,
2
]):
def
teller
(
program_config
,
predictor_config
):
if
program_config
.
ops
[
0
].
attrs
[
'pooling_type'
]
==
'avg'
and
\
program_config
.
ops
[
0
].
attrs
[
'global_pooling'
]
==
False
and
\
program_config
.
ops
[
0
].
attrs
[
'exclusive'
]
==
True
and
\
program_config
.
ops
[
0
].
attrs
[
'adaptive'
]
==
False
and
\
program_config
.
ops
[
0
].
attrs
[
'ceil_mode'
]
==
True
:
return
True
return
False
self
.
add_skip_case
(
teller
4
,
SkipReasons
.
TRT_NOT_IMPLEMENTED
,
"
It is not support that strides is not equal [1, 1] in dynamic mode for trt now
."
teller
,
SkipReasons
.
TRT_NOT_IMPLEMENTED
,
"
The results of some cases are Nan, but the results of TensorRT and GPU are the same
."
)
def
test
(
self
):
...
...
python/paddle/fluid/tests/unittests/ir/inference/test_trt_pool_op.py
浏览文件 @
cf8a5573
...
...
@@ -119,6 +119,17 @@ class TensorRTAvgPoolTest(TensorRTPoolTest):
self
.
exclusive
=
False
class
TensorRTAvgCeilPoolTest
(
TensorRTPoolTest
):
def
set_extra_config
(
self
):
self
.
pool_size
=
2
self
.
pool_type
=
'avg'
self
.
pool_stride
=
1
self
.
pool_padding
=
0
self
.
global_pooling
=
False
self
.
ceil_mode
=
True
self
.
exclusive
=
False
class
TensorRTGlobalPoolTest
(
TensorRTPoolTest
):
def
set_extra_config
(
self
):
self
.
pool_size
=
2
...
...
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