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
92a2817a
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
92a2817a
编写于
10月 23, 2018
作者:
S
sneaxiy
浏览文件
操作
浏览文件
下载
差异文件
test=develop
上级
a9d7a9d7
6b4056bb
变更
34
展开全部
隐藏空白更改
内联
并排
Showing
34 changed file
with
389 addition
and
344 deletion
+389
-344
paddle/fluid/framework/ir/CMakeLists.txt
paddle/fluid/framework/ir/CMakeLists.txt
+1
-3
paddle/fluid/framework/ir/graph_helper_test.cc
paddle/fluid/framework/ir/graph_helper_test.cc
+3
-3
paddle/fluid/framework/ir/graph_test.cc
paddle/fluid/framework/ir/graph_test.cc
+1
-1
paddle/fluid/framework/op_desc.cc
paddle/fluid/framework/op_desc.cc
+5
-11
paddle/fluid/framework/program_desc_test.cc
paddle/fluid/framework/program_desc_test.cc
+1
-1
paddle/fluid/framework/reader_test.cc
paddle/fluid/framework/reader_test.cc
+1
-1
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
+1
-1
paddle/fluid/inference/tests/api/tester_helper.h
paddle/fluid/inference/tests/api/tester_helper.h
+1
-1
paddle/fluid/operators/CMakeLists.txt
paddle/fluid/operators/CMakeLists.txt
+6
-6
paddle/fluid/operators/array_to_lod_tensor_op.cc
paddle/fluid/operators/array_to_lod_tensor_op.cc
+1
-1
paddle/fluid/operators/concat_op.h
paddle/fluid/operators/concat_op.h
+8
-20
paddle/fluid/operators/detection/generate_proposal_labels_op.cc
.../fluid/operators/detection/generate_proposal_labels_op.cc
+1
-1
paddle/fluid/operators/lod_tensor_to_array_op.cc
paddle/fluid/operators/lod_tensor_to_array_op.cc
+2
-2
paddle/fluid/operators/math/CMakeLists.txt
paddle/fluid/operators/math/CMakeLists.txt
+6
-6
paddle/fluid/operators/math/concat_and_split.cc
paddle/fluid/operators/math/concat_and_split.cc
+3
-3
paddle/fluid/operators/math/concat_and_split.cu
paddle/fluid/operators/math/concat_and_split.cu
+15
-15
paddle/fluid/operators/math/concat_and_split.h
paddle/fluid/operators/math/concat_and_split.h
+1
-1
paddle/fluid/operators/math/concat_test.cc
paddle/fluid/operators/math/concat_test.cc
+1
-1
paddle/fluid/operators/reader/reader_blocking_queue_test.cc
paddle/fluid/operators/reader/reader_blocking_queue_test.cc
+1
-1
paddle/fluid/operators/sequence_concat_op.h
paddle/fluid/operators/sequence_concat_op.h
+2
-2
paddle/fluid/operators/split_op.cc
paddle/fluid/operators/split_op.cc
+5
-6
paddle/fluid/operators/split_op.h
paddle/fluid/operators/split_op.h
+15
-10
paddle/fluid/operators/strided_memcpy.h
paddle/fluid/operators/strided_memcpy.h
+23
-1
python/paddle/fluid/layer_helper.py
python/paddle/fluid/layer_helper.py
+12
-3
python/paddle/fluid/layers/control_flow.py
python/paddle/fluid/layers/control_flow.py
+17
-16
python/paddle/fluid/layers/detection.py
python/paddle/fluid/layers/detection.py
+38
-27
python/paddle/fluid/layers/io.py
python/paddle/fluid/layers/io.py
+1
-1
python/paddle/fluid/layers/layer_function_generator.py
python/paddle/fluid/layers/layer_function_generator.py
+5
-3
python/paddle/fluid/layers/metric_op.py
python/paddle/fluid/layers/metric_op.py
+5
-5
python/paddle/fluid/layers/nn.py
python/paddle/fluid/layers/nn.py
+187
-169
python/paddle/fluid/layers/tensor.py
python/paddle/fluid/layers/tensor.py
+17
-14
python/paddle/fluid/regularizer.py
python/paddle/fluid/regularizer.py
+2
-2
python/paddle/fluid/tests/CMakeLists.txt
python/paddle/fluid/tests/CMakeLists.txt
+1
-5
python/paddle/fluid/tests/unittests/test_slice_var.py
python/paddle/fluid/tests/unittests/test_slice_var.py
+0
-1
未找到文件。
paddle/fluid/framework/ir/CMakeLists.txt
浏览文件 @
92a2817a
...
...
@@ -42,12 +42,10 @@ if(WITH_MKLDNN)
pass_library
(
mkldnn_placement_pass base
)
pass_library
(
conv_bias_mkldnn_fuse_pass inference
)
pass_library
(
conv_relu_mkldnn_fuse_pass inference
)
pass_library
(
conv_elementwise_add_mkldnn_fuse_pass inference
)
endif
()
cc_library
(
fuse_elewise_add_act_pass SRCS fuse_elewise_add_act_pass.cc DEPS pass graph_pattern_detector
)
if
(
WITH_MKLDNN
)
pass_library
(
conv_elementwise_add_mkldnn_fuse_pass inference
)
endif
()
set
(
GLOB_PASS_LIB
${
PASS_LIBRARY
}
CACHE INTERNAL
"Global PASS library"
)
...
...
paddle/fluid/framework/ir/graph_helper_test.cc
浏览文件 @
92a2817a
...
...
@@ -200,15 +200,15 @@ TEST(GraphHelperTest, GraphNum) {
Graph
g
(
prog
);
BuildZeroGraph
(
&
g
);
ASSERT_EQ
(
GraphNum
(
g
),
0
);
ASSERT_EQ
(
GraphNum
(
g
),
0
UL
);
Graph
g2
(
prog
);
BuildOneGraph
(
&
g2
);
ASSERT_EQ
(
GraphNum
(
g2
),
1
);
ASSERT_EQ
(
GraphNum
(
g2
),
1
UL
);
Graph
g3
(
prog
);
BuildTwoGraphs
(
&
g3
);
ASSERT_EQ
(
GraphNum
(
g3
),
2
);
ASSERT_EQ
(
GraphNum
(
g3
),
2
UL
);
}
}
// namespace ir
...
...
paddle/fluid/framework/ir/graph_test.cc
浏览文件 @
92a2817a
...
...
@@ -124,7 +124,7 @@ TEST(GraphTest, Basic) {
ASSERT_EQ
(
n
->
outputs
.
size
(),
0UL
);
}
}
ASSERT_EQ
(
nodes
.
size
(),
5
);
ASSERT_EQ
(
nodes
.
size
(),
5
UL
);
}
TEST
(
GraphTest
,
WriteAfterRead
)
{
...
...
paddle/fluid/framework/op_desc.cc
浏览文件 @
92a2817a
...
...
@@ -515,20 +515,14 @@ void OpDesc::InferShape(const BlockDesc &block) const {
}
void
OpDesc
::
InferVarType
(
BlockDesc
*
block
)
const
{
// There are a few places that var type can be set.
// When VarDesc is created, default set to LOD_TENSOR.
// When output variable is created, default is defaut set to LOD_TENSOR.
// We limit here to be the only place that operator defines its customized
// var type inference. Hence, we don't do any "default" setting here.
auto
&
info
=
OpInfoMap
::
Instance
().
Get
(
this
->
Type
());
if
(
info
.
infer_var_type_
)
{
info
.
infer_var_type_
(
*
this
,
block
);
}
else
{
// all output type is LoDTensor by default
VLOG
(
10
)
<<
this
->
Type
()
<<
" has not registered InferVarType. Set output variables to "
"LOD_TENSOR"
;
for
(
auto
&
out_pair
:
this
->
outputs_
)
{
for
(
auto
&
out_var_name
:
out_pair
.
second
)
{
block
->
FindRecursiveOrCreateVar
(
out_var_name
)
.
SetType
(
proto
::
VarType
::
LOD_TENSOR
);
}
}
}
}
...
...
paddle/fluid/framework/program_desc_test.cc
浏览文件 @
92a2817a
...
...
@@ -103,7 +103,7 @@ TEST(ProgramDesc, copy_ctor) {
ASSERT_EQ
(
1
,
op
->
GetBlockAttrId
(
"sub_block"
));
found_sub_block
=
true
;
ASSERT_EQ
(
2
,
op
->
GetBlocksAttrIds
(
"sub_blocks"
).
size
());
ASSERT_EQ
(
2
UL
,
op
->
GetBlocksAttrIds
(
"sub_blocks"
).
size
());
found_sub_blocks
=
true
;
}
}
...
...
paddle/fluid/framework/reader_test.cc
浏览文件 @
92a2817a
...
...
@@ -40,7 +40,7 @@ TEST(READER, decorate_chain) {
auto
endpoints
=
root
->
GetEndPoints
();
ASSERT_EQ
(
endpoints
.
size
(),
2U
);
ASSERT_NE
(
endpoints
.
count
(
end_point1
.
get
()),
0UL
);
ASSERT_NE
(
endpoints
.
count
(
end_point2
.
get
()),
0
);
ASSERT_NE
(
endpoints
.
count
(
end_point2
.
get
()),
0
UL
);
}
{
...
...
paddle/fluid/inference/tests/api/analyzer_resnet50_tester.cc
浏览文件 @
92a2817a
...
...
@@ -71,7 +71,7 @@ void profile(bool use_mkldnn = false) {
}
TEST
(
Analyzer_resnet50
,
profile
)
{
profile
();
}
#if
n
def PADDLE_WITH_MKLDNN
#ifdef PADDLE_WITH_MKLDNN
TEST
(
Analyzer_resnet50
,
profile_mkldnn
)
{
profile
(
true
/* use_mkldnn */
);
}
#endif
...
...
paddle/fluid/inference/tests/api/tester_helper.h
浏览文件 @
92a2817a
...
...
@@ -50,7 +50,7 @@ void CompareResult(const std::vector<PaddleTensor> &outputs,
auto
&
ref_out
=
ref_outputs
[
i
];
size_t
size
=
VecReduceToInt
(
out
.
shape
);
size_t
ref_size
=
VecReduceToInt
(
ref_out
.
shape
);
EXPECT_GT
(
size
,
0
);
EXPECT_GT
(
size
,
0
UL
);
EXPECT_EQ
(
size
,
ref_size
);
EXPECT_EQ
(
out
.
dtype
,
ref_out
.
dtype
);
switch
(
out
.
dtype
)
{
...
...
paddle/fluid/operators/CMakeLists.txt
浏览文件 @
92a2817a
...
...
@@ -284,10 +284,10 @@ op_library(max_sequence_len_op DEPS lod_rank_table)
op_library
(
sequence_conv_op DEPS context_project
)
op_library
(
sequence_pool_op DEPS sequence_pooling
)
if
(
NOT WIN32
)
op_library
(
lstm_op DEPS sequence2batch lstm_compute
)
op_library
(
hierarchical_sigmoid_op DEPS matrix_bit_code
)
op_library
(
lstmp_op DEPS sequence2batch lstm_compute
)
op_library
(
gru_op DEPS sequence2batch gru_compute
)
op_library
(
lstm_op DEPS sequence2batch lstm_compute
)
op_library
(
hierarchical_sigmoid_op DEPS matrix_bit_code
)
op_library
(
lstmp_op DEPS sequence2batch lstm_compute
)
op_library
(
gru_op DEPS sequence2batch gru_compute
)
endif
(
NOT WIN32
)
op_library
(
recurrent_op DEPS executor
)
op_library
(
warpctc_op DEPS dynload_warpctc sequence_padding sequence_scale
)
...
...
@@ -316,7 +316,7 @@ op_library(save_op DEPS lod_tensor)
op_library
(
load_op DEPS lod_tensor
)
op_library
(
save_combine_op DEPS lod_tensor
)
op_library
(
load_combine_op DEPS lod_tensor
)
op_library
(
concat_op DEPS concat
)
op_library
(
concat_op DEPS concat
_and_split
)
list
(
REMOVE_ITEM GENERAL_OPS
${
DEPS_OPS
}
)
...
...
@@ -348,6 +348,6 @@ cc_test(strided_memcpy_test SRCS strided_memcpy_test.cc DEPS tensor memory)
cc_test
(
save_load_op_test SRCS save_load_op_test.cc DEPS save_op load_op
)
cc_test
(
save_load_combine_op_test SRCS save_load_combine_op_test.cc DEPS save_combine_op load_combine_op
)
if
(
NOT WIN32
)
nv_test
(
nccl_op_test SRCS nccl_op_test.cu.cc DEPS nccl_op gpu_info device_context
)
nv_test
(
nccl_op_test SRCS nccl_op_test.cu.cc DEPS nccl_op gpu_info device_context
)
endif
()
nv_test
(
dropout_op_test SRCS dropout_op_test.cc DEPS dropout_op tensor
)
paddle/fluid/operators/array_to_lod_tensor_op.cc
浏览文件 @
92a2817a
...
...
@@ -11,7 +11,7 @@ distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. */
#include <paddle/fluid/operators/math/concat.h>
#include <paddle/fluid/operators/math/concat
_and_split
.h>
#include <numeric>
#include "paddle/fluid/framework/lod_rank_table.h"
...
...
paddle/fluid/operators/concat_op.h
浏览文件 @
92a2817a
...
...
@@ -17,7 +17,7 @@ limitations under the License. */
#include <utility>
#include <vector>
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
#include "paddle/fluid/operators/strided_memcpy.h"
namespace
paddle
{
...
...
@@ -89,29 +89,17 @@ class ConcatGradKernel : public framework::OpKernel<T> {
outputs
.
push_back
(
nullptr
);
}
}
auto
&
dev_ctx
=
ctx
.
template
device_context
<
DeviceContext
>();
// Sometimes direct copies will be faster, this maybe need deeply analysis.
if
(
axis
==
0
&&
outs
.
size
()
<
10
)
{
size_t
input_offset
=
0
;
const
auto
in_stride
=
framework
::
stride_numel
(
out_grad
->
dims
());
for
(
size_t
i
=
0
;
i
<
outs
.
size
();
++
i
)
{
auto
out_stride
=
framework
::
stride_numel
(
ins
[
i
]
->
dims
());
auto
*
out
=
outputs
[
i
];
if
(
out
!=
nullptr
)
{
StridedNumelCopyWithAxis
<
T
>
(
ctx
.
device_context
(),
axis
,
out
->
data
<
T
>
(),
out_stride
,
out_grad
->
data
<
T
>
()
+
input_offset
,
in_stride
,
out_stride
[
axis
]);
}
input_offset
+=
out_stride
[
axis
];
}
std
::
vector
<
const
framework
::
Tensor
*>
ref_shape
;
ref_shape
.
insert
(
ref_shape
.
begin
(),
ins
.
begin
(),
ins
.
end
());
StridedMemcpyWithAxis0
<
T
>
(
dev_ctx
,
*
out_grad
,
ref_shape
,
&
outputs
);
}
else
{
auto
&
dev_ctx
=
ctx
.
template
device_context
<
DeviceContext
>();
paddle
::
operators
::
math
::
ConcatGradFunctor
<
DeviceContext
,
T
>
concat_grad_functor
;
concat_grad_functor
(
dev_ctx
,
*
out_grad
,
ctx
.
MultiInput
<
framework
::
Tensor
>
(
"X"
),
static_cast
<
int
>
(
axis
),
&
outputs
);
math
::
SplitFunctor
<
DeviceContext
,
T
>
split_functor
;
split_functor
(
dev_ctx
,
*
out_grad
,
ctx
.
MultiInput
<
framework
::
Tensor
>
(
"X"
),
static_cast
<
int
>
(
axis
),
&
outputs
);
}
}
};
...
...
paddle/fluid/operators/detection/generate_proposal_labels_op.cc
浏览文件 @
92a2817a
...
...
@@ -16,7 +16,7 @@ limitations under the License. */
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/operators/detection/bbox_util.h"
#include "paddle/fluid/operators/gather.h"
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
#include "paddle/fluid/operators/math/math_function.h"
namespace
paddle
{
...
...
paddle/fluid/operators/lod_tensor_to_array_op.cc
浏览文件 @
92a2817a
...
...
@@ -17,7 +17,7 @@ limitations under the License. */
#include "paddle/fluid/framework/lod_tensor_array.h"
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/operators/detail/safe_ref.h"
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
#include "paddle/fluid/platform/device_context.h"
#include "paddle/fluid/platform/port.h"
...
...
@@ -79,7 +79,7 @@ struct LoDTensorToArrayFunctor : public boost::static_visitor<void> {
template
<
typename
DeviceContext
>
template
<
typename
T
>
void
LoDTensorToArrayFunctorImpl
<
DeviceContext
>::
apply
()
{
math
::
ConcatGrad
Functor
<
DeviceContext
,
T
>
func
;
math
::
Split
Functor
<
DeviceContext
,
T
>
func
;
func
(
*
dev_ctx_
,
prev_functor_
->
input_
,
prev_functor_
->
ref_inputs_
,
0
,
&
prev_functor_
->
outputs_
);
}
...
...
paddle/fluid/operators/math/CMakeLists.txt
浏览文件 @
92a2817a
if
(
NOT WIN32
)
add_subdirectory
(
detail
)
add_subdirectory
(
detail
)
endif
(
NOT WIN32
)
function
(
math_library TARGET
)
...
...
@@ -35,7 +35,7 @@ function(math_library TARGET)
endfunction
()
# please add new math_library in alphabetical order
math_library
(
concat
)
math_library
(
concat
_and_split
)
math_library
(
context_project DEPS im2col math_function
)
math_library
(
cross_entropy
)
math_library
(
cos_sim_functor
)
...
...
@@ -43,8 +43,8 @@ math_library(depthwise_conv)
math_library
(
im2col
)
if
(
NOT WIN32
)
# windows do not support avx functions yet.
math_library
(
gru_compute DEPS activation_functions math_function
)
math_library
(
lstm_compute DEPS activation_functions
)
math_library
(
gru_compute DEPS activation_functions math_function
)
math_library
(
lstm_compute DEPS activation_functions
)
endif
(
NOT WIN32
)
cc_library
(
blas SRCS blas.cc DEPS cblas framework_proto device_context
)
...
...
@@ -58,7 +58,7 @@ math_library(sequence_pooling DEPS math_function)
math_library
(
sequence_scale
)
math_library
(
softmax DEPS math_function
)
if
(
NOT WIN32
)
math_library
(
matrix_bit_code
)
math_library
(
matrix_bit_code
)
endif
(
NOT WIN32
)
math_library
(
unpooling
)
math_library
(
vol2col
)
...
...
@@ -72,7 +72,7 @@ if(WITH_GPU)
nv_test
(
math_function_gpu_test SRCS math_function_test.cu DEPS math_function
)
nv_test
(
selected_rows_functor_gpu_test SRCS selected_rows_functor_test.cu DEPS selected_rows_functor math_function
)
endif
()
cc_test
(
concat_test SRCS concat_test.cc DEPS concat
)
cc_test
(
concat_test SRCS concat_test.cc DEPS concat
_and_split
)
cc_test
(
cpu_vec_test SRCS cpu_vec_test.cc DEPS blas cpu_info
)
cc_library
(
jit_kernel
SRCS jit_kernel.cc jit_kernel_blas.cc jit_kernel_exp.cc jit_kernel_lstm.cc
...
...
paddle/fluid/operators/math/concat.cc
→
paddle/fluid/operators/math/concat
_and_split
.cc
浏览文件 @
92a2817a
...
...
@@ -12,7 +12,7 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. */
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
#include <vector>
namespace
paddle
{
...
...
@@ -67,7 +67,7 @@ class ConcatFunctor<platform::CPUDeviceContext, T> {
* each dimension must be the same, except the axis dimension.
*/
template
<
typename
T
>
class
ConcatGrad
Functor
<
platform
::
CPUDeviceContext
,
T
>
{
class
Split
Functor
<
platform
::
CPUDeviceContext
,
T
>
{
public:
void
operator
()(
const
platform
::
CPUDeviceContext
&
context
,
const
framework
::
Tensor
&
input
,
...
...
@@ -111,7 +111,7 @@ class ConcatGradFunctor<platform::CPUDeviceContext, T> {
};
#define DEFINE_FUNCTOR(type) \
template class ConcatFunctor<platform::CPUDeviceContext, type>; \
template class
ConcatGrad
Functor<platform::CPUDeviceContext, type>;
template class
Split
Functor<platform::CPUDeviceContext, type>;
FOR_ALL_TYPES
(
DEFINE_FUNCTOR
);
...
...
paddle/fluid/operators/math/concat.cu
→
paddle/fluid/operators/math/concat
_and_split
.cu
浏览文件 @
92a2817a
...
...
@@ -15,7 +15,7 @@ limitations under the License. */
#include <algorithm>
#include <vector>
#include "paddle/fluid/framework/mixed_vector.h"
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
#include "paddle/fluid/platform/cuda_primitives.h"
#include "paddle/fluid/platform/float16.h"
...
...
@@ -24,7 +24,7 @@ namespace operators {
namespace
math
{
template
<
typename
T
>
__global__
void
KernelConcat
(
T
**
inputs
,
const
int
*
input_cols
,
int
col_size
,
__global__
void
ConcatKernel
(
T
**
inputs
,
const
int
*
input_cols
,
int
col_size
,
const
int
output_rows
,
const
int
output_cols
,
T
*
output
)
{
int
tid_x
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
...
...
@@ -50,7 +50,7 @@ __global__ void KernelConcat(T** inputs, const int* input_cols, int col_size,
}
template
<
typename
T
>
__global__
void
KernelConcat
(
T
**
inputs_data
,
const
int
fixed_in_col
,
__global__
void
ConcatKernel
(
T
**
inputs_data
,
const
int
fixed_in_col
,
const
int
out_rows
,
const
int
out_cols
,
T
*
output_data
)
{
int
tid_x
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
...
...
@@ -67,9 +67,9 @@ __global__ void KernelConcat(T** inputs_data, const int fixed_in_col,
}
template
<
typename
T
>
__global__
void
KernelConcatGrad
(
const
T
*
input_data
,
const
int
in_row
,
const
int
in_col
,
const
int
*
out_cols
,
int
out_cols_size
,
T
**
outputs_data
)
{
__global__
void
SplitKernel
(
const
T
*
input_data
,
const
int
in_row
,
const
int
in_col
,
const
int
*
out_cols
,
int
out_cols_size
,
T
**
outputs_data
)
{
int
tid_x
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
int
curr_segment
=
0
;
int
curr_offset
=
out_cols
[
0
];
...
...
@@ -94,9 +94,9 @@ __global__ void KernelConcatGrad(const T* input_data, const int in_row,
}
template
<
typename
T
>
__global__
void
KernelConcatGrad
(
const
T
*
input_data
,
const
int
in_row
,
const
int
in_col
,
const
int
fixed_out_col
,
T
**
outputs_data
)
{
__global__
void
SplitKernel
(
const
T
*
input_data
,
const
int
in_row
,
const
int
in_col
,
const
int
fixed_out_col
,
T
**
outputs_data
)
{
int
tid_x
=
blockIdx
.
x
*
blockDim
.
x
+
threadIdx
.
x
;
for
(;
tid_x
<
in_col
;
tid_x
+=
blockDim
.
x
*
gridDim
.
x
)
{
int
split
=
tid_x
/
fixed_out_col
;
...
...
@@ -170,11 +170,11 @@ class ConcatFunctor<platform::CUDADeviceContext, T> {
dim3
grid_size
=
dim3
(
grid_cols
,
grid_rows
,
1
);
if
(
sameShape
)
{
KernelConcat
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
ConcatKernel
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
dev_ins_data
,
in_col
,
out_row
,
out_col
,
output
->
data
<
T
>
());
}
else
{
const
int
*
dev_ins_col_data
=
inputs_col
.
CUDAData
(
context
.
GetPlace
());
KernelConcat
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
ConcatKernel
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
dev_ins_data
,
dev_ins_col_data
,
static_cast
<
int
>
(
inputs_col
.
size
()),
out_row
,
out_col
,
output
->
data
<
T
>
());
}
...
...
@@ -189,7 +189,7 @@ class ConcatFunctor<platform::CUDADeviceContext, T> {
* each dimension must be the same, except the axis dimension.
*/
template
<
typename
T
>
class
ConcatGrad
Functor
<
platform
::
CUDADeviceContext
,
T
>
{
class
Split
Functor
<
platform
::
CUDADeviceContext
,
T
>
{
public:
void
operator
()(
const
platform
::
CUDADeviceContext
&
context
,
const
framework
::
Tensor
&
input
,
...
...
@@ -248,11 +248,11 @@ class ConcatGradFunctor<platform::CUDADeviceContext, T> {
dim3
grid_size
=
dim3
(
grid_cols
,
grid_rows
,
1
);
if
(
sameShape
)
{
KernelConcatGrad
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
SplitKernel
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
input
.
data
<
T
>
(),
in_row
,
in_col
,
out0_col
,
dev_out_gpu_data
);
}
else
{
const
int
*
dev_outs_col_data
=
outputs_cols
.
CUDAData
(
context
.
GetPlace
());
KernelConcatGrad
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
SplitKernel
<<<
grid_size
,
block_size
,
0
,
context
.
stream
()
>>>
(
input
.
data
<
T
>
(),
in_row
,
in_col
,
dev_outs_col_data
,
static_cast
<
int
>
(
outputs_cols
.
size
()),
dev_out_gpu_data
);
}
...
...
@@ -264,7 +264,7 @@ class ConcatGradFunctor<platform::CUDADeviceContext, T> {
#define DEFINE_FUNCTOR(type) \
template class ConcatFunctor<platform::CUDADeviceContext, type>; \
template class
ConcatGrad
Functor<platform::CUDADeviceContext, type>
template class
Split
Functor<platform::CUDADeviceContext, type>
FOR_ALL_TYPES
(
DEFINE_FUNCTOR
);
...
...
paddle/fluid/operators/math/concat.h
→
paddle/fluid/operators/math/concat
_and_split
.h
浏览文件 @
92a2817a
...
...
@@ -54,7 +54,7 @@ class ConcatFunctor {
* Output[1] = [[5,6]]
*/
template
<
typename
DeviceContext
,
typename
T
>
class
ConcatGrad
Functor
{
class
Split
Functor
{
public:
void
operator
()(
const
DeviceContext
&
context
,
const
framework
::
Tensor
&
input
,
const
std
::
vector
<
const
framework
::
Tensor
*>&
ref_inputs
,
...
...
paddle/fluid/operators/math/concat_test.cc
浏览文件 @
92a2817a
...
...
@@ -12,10 +12,10 @@ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. */
#include "paddle/fluid/operators/math/concat.h"
#include <gtest/gtest.h>
#include <vector>
#include "paddle/fluid/framework/tensor_util.h"
#include "paddle/fluid/operators/math/concat_and_split.h"
template
<
typename
DeviceContext
,
typename
Place
>
void
testConcat
()
{
...
...
paddle/fluid/operators/reader/reader_blocking_queue_test.cc
浏览文件 @
92a2817a
...
...
@@ -237,7 +237,7 @@ TEST(BlockingQueue, speed_test_mode) {
}
for
(
size_t
i
=
0
;
i
<
queue_size
;
++
i
)
{
q2
.
Receive
(
&
b
);
EXPECT_EQ
(
b
,
0
);
EXPECT_EQ
(
b
,
0
UL
);
}
EXPECT_EQ
(
q2
.
Size
(),
queue_size
);
}
paddle/fluid/operators/sequence_concat_op.h
浏览文件 @
92a2817a
...
...
@@ -17,7 +17,7 @@
#include <vector>
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/operators/detail/safe_ref.h"
#include "paddle/fluid/operators/math/concat.h"
#include "paddle/fluid/operators/math/concat
_and_split
.h"
namespace
paddle
{
namespace
operators
{
...
...
@@ -106,7 +106,7 @@ class SeqConcatGradKernel : public framework::OpKernel<T> {
}
}
math
::
ConcatGrad
Functor
<
DeviceContext
,
T
>
functor
;
math
::
Split
Functor
<
DeviceContext
,
T
>
functor
;
std
::
vector
<
const
framework
::
Tensor
*>
sliced_x_ptr
;
std
::
vector
<
framework
::
Tensor
*>
sliced_dx_ptr
;
for
(
auto
&
x
:
sliced_x
)
{
...
...
paddle/fluid/operators/split_op.cc
浏览文件 @
92a2817a
...
...
@@ -111,11 +111,10 @@ Example:
}
// namespace paddle
namespace
ops
=
paddle
::
operators
;
USE_CPU_ONLY_OP
(
concat
);
REGISTER_OPERATOR
(
split
,
ops
::
SplitOp
,
ops
::
SplitOpMaker
,
ops
::
SplitGradMaker
);
REGISTER_OP_CPU_KERNEL
(
split
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUPlace
,
double
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUPlace
,
float
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUPlace
,
int64_t
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUPlace
,
int
>
);
REGISTER_OP_CPU_KERNEL
(
split
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUDeviceContext
,
double
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUDeviceContext
,
float
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int64_t
>
,
ops
::
SplitOpKernel
<
paddle
::
platform
::
CPUDeviceContext
,
int
>
);
paddle/fluid/operators/split_op.h
浏览文件 @
92a2817a
...
...
@@ -17,6 +17,7 @@ limitations under the License. */
#include <chrono> // NOLINT
#include <vector>
#include "paddle/fluid/framework/op_registry.h"
#include "paddle/fluid/operators/math/concat_and_split.h"
#include "paddle/fluid/operators/strided_memcpy.h"
namespace
paddle
{
...
...
@@ -28,18 +29,22 @@ class SplitOpKernel : public framework::OpKernel<T> {
void
Compute
(
const
framework
::
ExecutionContext
&
ctx
)
const
override
{
auto
*
in
=
ctx
.
Input
<
framework
::
Tensor
>
(
"X"
);
auto
outs
=
ctx
.
MultiOutput
<
framework
::
Tensor
>
(
"Out"
);
auto
in_stride
=
framework
::
stride_numel
(
in
->
dims
());
int64_t
axis
=
static_cast
<
int64_t
>
(
ctx
.
Attr
<
int
>
(
"axis"
));
int
axis
=
ctx
.
Attr
<
int
>
(
"axis"
);
auto
place
=
ctx
.
GetPlace
();
size_t
input_offset
=
0
;
for
(
auto
&
out
:
outs
)
{
out
->
mutable_data
<
T
>
(
ctx
.
GetPlace
());
auto
out_stride
=
framework
::
stride_numel
(
out
->
dims
());
StridedNumelCopyWithAxis
<
T
>
(
ctx
.
device_context
(),
axis
,
out
->
data
<
T
>
(),
out_stride
,
in
->
data
<
T
>
()
+
input_offset
,
in_stride
,
out_stride
[
axis
]);
input_offset
+=
out_stride
[
axis
];
std
::
vector
<
const
framework
::
Tensor
*>
shape_refer
;
for
(
size_t
j
=
0
;
j
<
outs
.
size
();
++
j
)
{
outs
[
j
]
->
mutable_data
<
T
>
(
ctx
.
GetPlace
());
shape_refer
.
emplace_back
(
outs
[
j
]);
}
auto
&
dev_ctx
=
ctx
.
template
device_context
<
DeviceContext
>();
// Sometimes direct copies will be faster, this maybe need deeply analysis.
if
(
axis
==
0
&&
outs
.
size
()
<
10
)
{
StridedMemcpyWithAxis0
<
T
>
(
dev_ctx
,
*
in
,
shape_refer
,
&
outs
);
}
else
{
math
::
SplitFunctor
<
DeviceContext
,
T
>
functor
;
functor
(
dev_ctx
,
*
in
,
shape_refer
,
axis
,
&
outs
);
}
}
};
...
...
paddle/fluid/operators/strided_memcpy.h
浏览文件 @
92a2817a
...
...
@@ -13,8 +13,9 @@ See the License for the specific language governing permissions and
limitations under the License. */
#pragma once
#include <vector>
#include "paddle/fluid/framework/tensor.h"
#include "paddle/fluid/operators/detail/strided_memcpy.h"
namespace
paddle
{
namespace
operators
{
...
...
@@ -98,5 +99,26 @@ inline void StridedNumelCopyWithAxis(const platform::DeviceContext& ctx,
}
}
template
<
typename
T
>
inline
void
StridedMemcpyWithAxis0
(
const
platform
::
DeviceContext
&
dev_ctx
,
const
framework
::
Tensor
&
input
,
const
std
::
vector
<
const
framework
::
Tensor
*>&
shape_refer
,
std
::
vector
<
framework
::
Tensor
*>*
outputs
)
{
const
framework
::
DDim
in_stride
=
stride_numel
(
input
.
dims
());
const
int
axis
=
0
;
size_t
input_offset
=
0
;
for
(
size_t
i
=
0
;
i
<
outputs
->
size
();
++
i
)
{
auto
out_stride
=
stride_numel
(
shape_refer
[
i
]
->
dims
());
auto
out
=
outputs
->
at
(
i
);
if
(
out
!=
nullptr
)
{
StridedNumelCopyWithAxis
<
T
>
(
dev_ctx
,
axis
,
out
->
data
<
T
>
(),
out_stride
,
input
.
data
<
T
>
()
+
input_offset
,
in_stride
,
out_stride
[
axis
]);
}
input_offset
+=
out_stride
[
axis
];
}
}
}
// namespace operators
}
// namespace paddle
python/paddle/fluid/layer_helper.py
浏览文件 @
92a2817a
...
...
@@ -324,10 +324,19 @@ class LayerHelper(object):
raise
ValueError
(
"no Parameter name %s found"
%
name
)
return
param
def
create_tmp_variable
(
self
,
dtype
,
stop_gradient
=
False
):
def
create_variable_for_type_inference
(
self
,
dtype
,
stop_gradient
=
False
):
"""Create a temporary variable that should be type inferred layer.
Note:
The default type will be set to LOD_TENSOR. However, when
the var is used as operator output, its type will be updated
based on operator's `VarTypeInference` implementation in
infer_var_type.
"""
return
self
.
main_program
.
current_block
().
create_var
(
name
=
unique_name
.
generate
(
"."
.
join
([
self
.
name
,
'tmp'
])),
dtype
=
dtype
,
type
=
core
.
VarDesc
.
VarType
.
LOD_TENSOR
,
persistable
=
False
,
stop_gradient
=
stop_gradient
)
...
...
@@ -388,7 +397,7 @@ class LayerHelper(object):
b
=
self
.
create_parameter
(
attr
=
bias_attr
,
shape
=
size
,
dtype
=
input_var
.
dtype
,
is_bias
=
True
)
tmp
=
self
.
create_
tmp_variabl
e
(
dtype
=
input_var
.
dtype
)
tmp
=
self
.
create_
variable_for_type_inferenc
e
(
dtype
=
input_var
.
dtype
)
self
.
append_op
(
type
=
'elementwise_add'
,
inputs
=
{
'X'
:
[
input_var
],
...
...
@@ -414,7 +423,7 @@ class LayerHelper(object):
tmp
=
input_var
# NOTE(dzhwinter): some activation support inplace compution.
if
not
core
.
IsInplace
(
act_type
):
tmp
=
self
.
create_
tmp_variabl
e
(
dtype
=
input_var
.
dtype
)
tmp
=
self
.
create_
variable_for_type_inferenc
e
(
dtype
=
input_var
.
dtype
)
self
.
append_op
(
type
=
act_type
,
inputs
=
{
"X"
:
[
input_var
]},
...
...
python/paddle/fluid/layers/control_flow.py
浏览文件 @
92a2817a
...
...
@@ -80,8 +80,8 @@ def split_lod_tensor(input, mask, level=0):
"""
helper
=
LayerHelper
(
'split_lod_tensor'
,
**
locals
())
out_true
=
helper
.
create_
tmp_variabl
e
(
dtype
=
input
.
dtype
)
out_false
=
helper
.
create_
tmp_variabl
e
(
dtype
=
input
.
dtype
)
out_true
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
input
.
dtype
)
out_false
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
input
.
dtype
)
helper
.
append_op
(
type
=
'split_lod_tensor'
,
inputs
=
{
...
...
@@ -131,7 +131,7 @@ def merge_lod_tensor(in_true, in_false, x, mask, level=0):
in_true=out_true, in_false=out_false, mask=y, x=x, level=level)
"""
helper
=
LayerHelper
(
'merge_lod_tensor'
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
in_true
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
in_true
.
dtype
)
helper
.
append_op
(
type
=
'merge_lod_tensor'
,
inputs
=
{
'X'
:
x
,
...
...
@@ -524,7 +524,7 @@ class StaticRNN(object):
if
not
isinstance
(
o
,
Variable
):
raise
TypeError
(
"step output takes a Variable"
)
tmp_o
=
self
.
helper
.
create_
tmp_variabl
e
(
dtype
=
o
.
dtype
)
tmp_o
=
self
.
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
o
.
dtype
)
self
.
helper
.
append_op
(
type
=
'rnn_memory_helper'
,
inputs
=
{
'X'
:
[
o
]},
...
...
@@ -606,7 +606,8 @@ class StaticRNN(object):
pre_memories
.
append
(
mem
.
pre_mem
.
name
)
mem_var
=
rnn_block
.
var
(
mem
.
mem
.
name
)
assert
isinstance
(
mem_var
,
Variable
)
new_mem
=
self
.
helper
.
create_tmp_variable
(
dtype
=
mem_var
.
dtype
)
new_mem
=
self
.
helper
.
create_variable_for_type_inference
(
dtype
=
mem_var
.
dtype
)
rnn_block
.
append_op
(
type
=
'rnn_memory_helper'
,
...
...
@@ -813,7 +814,7 @@ def max_sequence_len(rank_table):
${out_comment}.
"""
helper
=
LayerHelper
(
"max_seqence_len"
,
**
locals
())
res
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"int64"
)
res
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"int64"
)
helper
.
append_op
(
type
=
"max_sequence_len"
,
inputs
=
{
"RankTable"
:
rank_table
},
...
...
@@ -884,7 +885,7 @@ def array_to_lod_tensor(x, table):
lod_tensor = fluid.layers.array_to_lod_tensor(array, table)
"""
helper
=
LayerHelper
(
"array_to_lod_tensor"
,
**
locals
())
tmp
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
tmp
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
"array_to_lod_tensor"
,
inputs
=
{
'X'
:
x
,
...
...
@@ -915,7 +916,7 @@ def increment(x, value=1.0, in_place=True):
"""
helper
=
LayerHelper
(
"increment"
,
**
locals
())
if
not
in_place
:
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
else
:
out
=
x
helper
.
append_op
(
...
...
@@ -1012,7 +1013,7 @@ def less_than(x, y, force_cpu=None, cond=None, **ignored):
"""
helper
=
LayerHelper
(
"less_than"
,
**
locals
())
if
cond
is
None
:
cond
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'bool'
)
cond
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'bool'
)
cond
.
stop_gradient
=
True
attrs
=
dict
()
...
...
@@ -1051,7 +1052,7 @@ def equal(x, y, cond=None, **ignored):
"""
helper
=
LayerHelper
(
"equal"
,
**
locals
())
if
cond
is
None
:
cond
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'bool'
)
cond
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'bool'
)
cond
.
stop_gradient
=
True
helper
.
append_op
(
...
...
@@ -1098,7 +1099,7 @@ def array_read(array, i):
array
,
Variable
)
or
array
.
type
!=
core
.
VarDesc
.
VarType
.
LOD_TENSOR_ARRAY
:
raise
TypeError
(
"array should be tensor array vairable"
)
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
array
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
array
.
dtype
)
helper
.
append_op
(
type
=
'read_from_array'
,
inputs
=
{
'X'
:
[
array
],
...
...
@@ -1133,7 +1134,7 @@ def shrink_memory(x, i, table):
usage.
"""
helper
=
LayerHelper
(
'shrink_memory'
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
'shrink_rnn_memory'
,
inputs
=
{
'X'
:
[
x
],
...
...
@@ -1170,7 +1171,7 @@ def array_length(array):
"""
helper
=
LayerHelper
(
'array_length'
,
**
locals
())
tmp
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'int64'
)
tmp
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'int64'
)
tmp
.
stop_gradient
=
True
helper
.
append_op
(
type
=
'lod_array_length'
,
inputs
=
{
'X'
:
[
array
]},
outputs
=
{
'Out'
:
[
tmp
]})
...
...
@@ -1590,7 +1591,7 @@ class DynamicRNN(object):
self
.
mem_dict
=
dict
()
self
.
output_array
=
[]
self
.
outputs
=
[]
self
.
cond
=
self
.
helper
.
create_
tmp_variabl
e
(
dtype
=
'bool'
)
self
.
cond
=
self
.
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'bool'
)
self
.
cond
.
stop_gradient
=
False
self
.
while_op
=
While
(
self
.
cond
)
self
.
input_array
=
[]
...
...
@@ -1924,7 +1925,7 @@ def reorder_lod_tensor_by_rank(x, rank_table):
helper
.
is_instance
(
'x'
,
Variable
)
helper
.
is_instance
(
'rank_table'
,
Variable
)
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
'reorder_lod_tensor_by_rank'
,
inputs
=
{
'X'
:
[
x
],
...
...
@@ -1958,7 +1959,7 @@ def is_empty(x, cond=None, **ignored):
"""
helper
=
LayerHelper
(
"is_empty"
,
**
locals
())
if
cond
is
None
:
cond
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'bool'
)
cond
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'bool'
)
cond
.
stop_gradient
=
True
elif
not
isinstance
(
cond
,
Variable
):
raise
TypeError
(
"cond takes a variable"
)
...
...
python/paddle/fluid/layers/detection.py
浏览文件 @
92a2817a
...
...
@@ -147,10 +147,11 @@ def rpn_target_assign(bbox_pred,
helper
=
LayerHelper
(
'rpn_target_assign'
,
**
locals
())
# Assign target label to anchors
loc_index
=
helper
.
create_tmp_variable
(
dtype
=
'int32'
)
score_index
=
helper
.
create_tmp_variable
(
dtype
=
'int32'
)
target_label
=
helper
.
create_tmp_variable
(
dtype
=
'int32'
)
target_bbox
=
helper
.
create_tmp_variable
(
dtype
=
anchor_box
.
dtype
)
loc_index
=
helper
.
create_variable_for_type_inference
(
dtype
=
'int32'
)
score_index
=
helper
.
create_variable_for_type_inference
(
dtype
=
'int32'
)
target_label
=
helper
.
create_variable_for_type_inference
(
dtype
=
'int32'
)
target_bbox
=
helper
.
create_variable_for_type_inference
(
dtype
=
anchor_box
.
dtype
)
helper
.
append_op
(
type
=
"rpn_target_assign"
,
inputs
=
{
...
...
@@ -282,7 +283,8 @@ def detection_output(loc,
scores
=
nn
.
reshape
(
x
=
scores
,
shape
=
compile_shape
,
actual_shape
=
run_shape
)
scores
=
nn
.
transpose
(
scores
,
perm
=
[
0
,
2
,
1
])
scores
.
stop_gradient
=
True
nmsed_outs
=
helper
.
create_tmp_variable
(
dtype
=
decoded_box
.
dtype
)
nmsed_outs
=
helper
.
create_variable_for_type_inference
(
dtype
=
decoded_box
.
dtype
)
helper
.
append_op
(
type
=
"multiclass_nms"
,
inputs
=
{
'Scores'
:
scores
,
...
...
@@ -314,7 +316,7 @@ def iou_similarity(x, y, name=None):
"""
helper
=
LayerHelper
(
"iou_similarity"
,
**
locals
())
if
name
is
None
:
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
else
:
out
=
helper
.
create_variable
(
name
=
name
,
dtype
=
x
.
dtype
,
persistable
=
False
)
...
...
@@ -351,7 +353,8 @@ def box_coder(prior_box,
helper
=
LayerHelper
(
"box_coder"
,
**
locals
())
if
name
is
None
:
output_box
=
helper
.
create_tmp_variable
(
dtype
=
prior_box
.
dtype
)
output_box
=
helper
.
create_variable_for_type_inference
(
dtype
=
prior_box
.
dtype
)
else
:
output_box
=
helper
.
create_variable
(
name
=
name
,
dtype
=
prior_box
.
dtype
,
persistable
=
False
)
...
...
@@ -382,7 +385,7 @@ def polygon_box_transform(input, name=None):
"""
helper
=
LayerHelper
(
"polygon_box_transform"
,
**
locals
())
if
name
is
None
:
output
=
helper
.
create_
tmp_variabl
e
(
dtype
=
input
.
dtype
)
output
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
input
.
dtype
)
else
:
output
=
helper
.
create_variable
(
name
=
name
,
dtype
=
prior_box
.
input
,
persistable
=
False
)
...
...
@@ -450,7 +453,7 @@ def detection_map(detect_res,
helper
=
LayerHelper
(
"detection_map"
,
**
locals
())
def
__create_var
(
type
):
return
helper
.
create_
tmp_variabl
e
(
dtype
=
type
)
return
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
type
)
map_out
=
__create_var
(
'float32'
)
accum_pos_count_out
=
out_states
[
0
]
if
out_states
else
__create_var
(
'int32'
)
...
...
@@ -557,8 +560,9 @@ def bipartite_match(dist_matrix,
>>> matched_indices, matched_dist = fluid.layers.bipartite_match(iou)
"""
helper
=
LayerHelper
(
'bipartite_match'
,
**
locals
())
match_indices
=
helper
.
create_tmp_variable
(
dtype
=
'int32'
)
match_distance
=
helper
.
create_tmp_variable
(
dtype
=
dist_matrix
.
dtype
)
match_indices
=
helper
.
create_variable_for_type_inference
(
dtype
=
'int32'
)
match_distance
=
helper
.
create_variable_for_type_inference
(
dtype
=
dist_matrix
.
dtype
)
helper
.
append_op
(
type
=
'bipartite_match'
,
inputs
=
{
'DistMat'
:
dist_matrix
},
...
...
@@ -644,8 +648,8 @@ def target_assign(input,
gt, matched_indices, mismatch_value=0)
"""
helper
=
LayerHelper
(
'target_assign'
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
input
.
dtype
)
out_weight
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'float32'
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
input
.
dtype
)
out_weight
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'float32'
)
helper
.
append_op
(
type
=
'target_assign'
,
inputs
=
{
...
...
@@ -816,9 +820,10 @@ def ssd_loss(location,
conf_loss
=
nn
.
reshape
(
x
=
conf_loss
,
shape
=
(
num
,
num_prior
),
actual_shape
=
actual_shape
)
conf_loss
.
stop_gradient
=
True
neg_indices
=
helper
.
create_
tmp_variabl
e
(
dtype
=
'int32'
)
neg_indices
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
'int32'
)
dtype
=
matched_indices
.
dtype
updated_matched_indices
=
helper
.
create_tmp_variable
(
dtype
=
dtype
)
updated_matched_indices
=
helper
.
create_variable_for_type_inference
(
dtype
=
dtype
)
helper
.
append_op
(
type
=
'mine_hard_examples'
,
inputs
=
{
...
...
@@ -998,8 +1003,8 @@ def prior_box(input,
max_sizes
=
[
max_sizes
]
attrs
[
'max_sizes'
]
=
max_sizes
box
=
helper
.
create_
tmp_variabl
e
(
dtype
)
var
=
helper
.
create_
tmp_variabl
e
(
dtype
)
box
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
)
var
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
)
helper
.
append_op
(
type
=
"prior_box"
,
inputs
=
{
"Input"
:
input
,
...
...
@@ -1337,8 +1342,8 @@ def anchor_generator(input,
'offset'
:
offset
}
anchor
=
helper
.
create_
tmp_variabl
e
(
dtype
)
var
=
helper
.
create_
tmp_variabl
e
(
dtype
)
anchor
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
)
var
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
)
helper
.
append_op
(
type
=
"anchor_generator"
,
inputs
=
{
"Input"
:
input
},
...
...
@@ -1384,7 +1389,7 @@ def roi_perspective_transform(input,
"""
helper
=
LayerHelper
(
'roi_perspective_transform'
,
**
locals
())
dtype
=
helper
.
input_dtype
()
out
=
helper
.
create_
tmp_variabl
e
(
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
)
helper
.
append_op
(
type
=
"roi_perspective_transform"
,
inputs
=
{
"X"
:
input
,
...
...
@@ -1418,11 +1423,15 @@ def generate_proposal_labels(rpn_rois,
helper
=
LayerHelper
(
'generate_proposal_labels'
,
**
locals
())
rois
=
helper
.
create_tmp_variable
(
dtype
=
rpn_rois
.
dtype
)
labels_int32
=
helper
.
create_tmp_variable
(
dtype
=
gt_classes
.
dtype
)
bbox_targets
=
helper
.
create_tmp_variable
(
dtype
=
rpn_rois
.
dtype
)
bbox_inside_weights
=
helper
.
create_tmp_variable
(
dtype
=
rpn_rois
.
dtype
)
bbox_outside_weights
=
helper
.
create_tmp_variable
(
dtype
=
rpn_rois
.
dtype
)
rois
=
helper
.
create_variable_for_type_inference
(
dtype
=
rpn_rois
.
dtype
)
labels_int32
=
helper
.
create_variable_for_type_inference
(
dtype
=
gt_classes
.
dtype
)
bbox_targets
=
helper
.
create_variable_for_type_inference
(
dtype
=
rpn_rois
.
dtype
)
bbox_inside_weights
=
helper
.
create_variable_for_type_inference
(
dtype
=
rpn_rois
.
dtype
)
bbox_outside_weights
=
helper
.
create_variable_for_type_inference
(
dtype
=
rpn_rois
.
dtype
)
helper
.
append_op
(
type
=
"generate_proposal_labels"
,
...
...
@@ -1504,8 +1513,10 @@ def generate_proposals(scores,
"""
helper
=
LayerHelper
(
'generate_proposals'
,
**
locals
())
rpn_rois
=
helper
.
create_tmp_variable
(
dtype
=
bbox_deltas
.
dtype
)
rpn_roi_probs
=
helper
.
create_tmp_variable
(
dtype
=
scores
.
dtype
)
rpn_rois
=
helper
.
create_variable_for_type_inference
(
dtype
=
bbox_deltas
.
dtype
)
rpn_roi_probs
=
helper
.
create_variable_for_type_inference
(
dtype
=
scores
.
dtype
)
helper
.
append_op
(
type
=
"generate_proposals"
,
inputs
=
{
...
...
python/paddle/fluid/layers/io.py
浏览文件 @
92a2817a
...
...
@@ -954,7 +954,7 @@ def read_file(reader):
"""
helper
=
LayerHelper
(
'read_file'
)
out
=
[
helper
.
create_
tmp_variabl
e
(
helper
.
create_
variable_for_type_inferenc
e
(
stop_gradient
=
True
,
dtype
=
'float32'
)
for
_
in
range
(
len
(
reader
.
desc
.
shapes
()))
]
...
...
python/paddle/fluid/layers/layer_function_generator.py
浏览文件 @
92a2817a
...
...
@@ -202,10 +202,12 @@ def generate_layer_fn(op_type):
out_var
=
out
[
0
]
if
(
isinstance
(
out
,
list
)
or
isinstance
(
out
,
tuple
))
else
out
else
:
out_var
=
helper
.
create_
tmp_variabl
e
(
dtype
=
dtype
)
out_var
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
dtype
)
outputs
[
o_name
]
=
[
out_var
]
for
name
in
intermediate_output_names
:
outputs
[
name
]
=
[
helper
.
create_tmp_variable
(
dtype
=
dtype
)]
outputs
[
name
]
=
[
helper
.
create_variable_for_type_inference
(
dtype
=
dtype
)
]
helper
.
append_op
(
type
=
op_type
,
inputs
=
inputs
,
outputs
=
outputs
,
attrs
=
kwargs
)
return
helper
.
append_activation
(
out_var
)
...
...
@@ -229,7 +231,7 @@ def generate_layer_fn_noattr(op_type):
def
func
(
x
,
name
=
None
):
helper
=
LayerHelper
(
op_type
,
**
locals
())
output
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
output
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
op_type
,
inputs
=
{
"X"
:
x
},
outputs
=
{
"Out"
:
output
})
return
output
...
...
python/paddle/fluid/layers/metric_op.py
浏览文件 @
92a2817a
...
...
@@ -58,11 +58,11 @@ def accuracy(input, label, k=1, correct=None, total=None):
"""
helper
=
LayerHelper
(
"accuracy"
,
**
locals
())
topk_out
,
topk_indices
=
nn
.
topk
(
input
,
k
=
k
)
acc_out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"float32"
)
acc_out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"float32"
)
if
correct
is
None
:
correct
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"int64"
)
correct
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"int64"
)
if
total
is
None
:
total
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"int64"
)
total
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"int64"
)
helper
.
append_op
(
type
=
"accuracy"
,
inputs
=
{
...
...
@@ -124,8 +124,8 @@ def auc(input,
auc_out=fluid.layers.auc(input=prediction, label=label)
"""
helper
=
LayerHelper
(
"auc"
,
**
locals
())
auc_out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"float64"
)
batch_auc_out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
"float64"
)
auc_out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"float64"
)
batch_auc_out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
"float64"
)
# make tp, tn, fp, fn persistable, so that can accumulate all batches.
# for batch auc
...
...
python/paddle/fluid/layers/nn.py
浏览文件 @
92a2817a
此差异已折叠。
点击以展开。
python/paddle/fluid/layers/tensor.py
浏览文件 @
92a2817a
...
...
@@ -152,7 +152,7 @@ def cast(x, dtype):
result = fluid.layers.cast(x=data, dtype='float64')
"""
helper
=
LayerHelper
(
'cast'
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
dtype
)
helper
.
append_op
(
type
=
'cast'
,
inputs
=
{
'X'
:
[
x
]},
...
...
@@ -184,7 +184,7 @@ def concat(input, axis=0, name=None):
out = fluid.layers.concat(input=[Efirst, Esecond, Ethird, Efourth])
"""
helper
=
LayerHelper
(
'concat'
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
helper
.
input_dtype
())
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
helper
.
input_dtype
())
helper
.
append_op
(
type
=
'concat'
,
inputs
=
{
'X'
:
input
},
...
...
@@ -221,7 +221,8 @@ def sums(input, out=None):
"""
helper
=
LayerHelper
(
'sum'
,
**
locals
())
if
out
is
None
:
out
=
helper
.
create_tmp_variable
(
dtype
=
helper
.
input_dtype
())
out
=
helper
.
create_variable_for_type_inference
(
dtype
=
helper
.
input_dtype
())
helper
.
append_op
(
type
=
'sum'
,
inputs
=
{
'X'
:
input
},
...
...
@@ -252,7 +253,7 @@ def assign(input, output=None):
"""
helper
=
LayerHelper
(
'assign'
,
**
locals
())
if
output
is
None
:
output
=
helper
.
create_
tmp_variabl
e
(
dtype
=
input
.
dtype
)
output
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
input
.
dtype
)
if
isinstance
(
input
,
Variable
):
helper
.
append_op
(
type
=
'assign'
,
inputs
=
{
'X'
:
[
input
]},
outputs
=
{
'Out'
:
[
output
]})
...
...
@@ -311,7 +312,7 @@ def fill_constant(shape, dtype, value, force_cpu=False, out=None):
helper
=
LayerHelper
(
"fill_constant"
,
**
locals
())
if
out
is
None
:
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
dtype
)
helper
.
append_op
(
type
=
'fill_constant'
,
inputs
=
{},
...
...
@@ -358,7 +359,7 @@ def fill_constant_batch_size_like(input,
${out_comment}.
"""
helper
=
LayerHelper
(
"fill_constant_batch_size_like"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
dtype
)
helper
.
append_op
(
type
=
'fill_constant_batch_size_like'
,
inputs
=
{
'Input'
:
input
},
...
...
@@ -396,7 +397,7 @@ def argmin(x, axis=0):
out = fluid.layers.argmin(x=in, axis=-1)
"""
helper
=
LayerHelper
(
"arg_min"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
VarDesc
.
VarType
.
INT64
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
VarDesc
.
VarType
.
INT64
)
helper
.
append_op
(
type
=
'arg_min'
,
inputs
=
{
'X'
:
x
},
...
...
@@ -427,7 +428,7 @@ def argmax(x, axis=0):
out = fluid.layers.argmax(x=in, axis=-1)
"""
helper
=
LayerHelper
(
"arg_max"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
VarDesc
.
VarType
.
INT64
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
VarDesc
.
VarType
.
INT64
)
helper
.
append_op
(
type
=
'arg_max'
,
inputs
=
{
'X'
:
x
},
...
...
@@ -477,8 +478,10 @@ def argsort(input, axis=-1, name=None):
out, indices = fluid.layers.argsort(input, axis=0)
"""
helper
=
LayerHelper
(
"argsort"
,
**
locals
())
out
=
helper
.
create_tmp_variable
(
dtype
=
input
.
dtype
,
stop_gradient
=
True
)
ids
=
helper
.
create_tmp_variable
(
VarDesc
.
VarType
.
INT64
,
stop_gradient
=
True
)
out
=
helper
.
create_variable_for_type_inference
(
dtype
=
input
.
dtype
,
stop_gradient
=
True
)
ids
=
helper
.
create_variable_for_type_inference
(
VarDesc
.
VarType
.
INT64
,
stop_gradient
=
True
)
helper
.
append_op
(
type
=
'argsort'
,
inputs
=
{
'X'
:
input
},
...
...
@@ -562,7 +565,7 @@ def reverse(x, axis):
if
isinstance
(
axis
,
int
):
axis
=
[
axis
]
helper
=
LayerHelper
(
"reverse"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
'reverse'
,
inputs
=
{
'Input'
:
x
},
...
...
@@ -654,7 +657,7 @@ def has_inf(x):
Variable: The tensor variable storing the output, only a bool value.
"""
helper
=
LayerHelper
(
"isinf"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
"isinf"
,
inputs
=
{
"X"
:
x
},
outputs
=
{
"Out"
:
out
})
return
out
...
...
@@ -670,7 +673,7 @@ def has_nan(x):
Variable: The tensor variable storing the output, only a bool value.
"""
helper
=
LayerHelper
(
"isnan"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
"isnan"
,
inputs
=
{
"X"
:
x
},
outputs
=
{
"Out"
:
out
})
return
out
...
...
@@ -687,6 +690,6 @@ def isfinite(x):
Variable: The tensor variable storing the output, contains a bool value.
"""
helper
=
LayerHelper
(
"isfinite"
,
**
locals
())
out
=
helper
.
create_
tmp_variabl
e
(
dtype
=
x
.
dtype
)
out
=
helper
.
create_
variable_for_type_inferenc
e
(
dtype
=
x
.
dtype
)
helper
.
append_op
(
type
=
"isfinite"
,
inputs
=
{
"X"
:
x
},
outputs
=
{
"Out"
:
out
})
return
out
python/paddle/fluid/regularizer.py
浏览文件 @
92a2817a
...
...
@@ -151,7 +151,7 @@ class L2DecayRegularizer(WeightDecayRegularizer):
decay
=
block
.
create_var
(
dtype
=
"float32"
,
shape
=
param
.
shape
,
type
=
core
.
VarDesc
.
VarType
.
SELECTED_ROWS
)
type
=
core
.
VarDesc
.
VarType
.
LOD_TENSOR
)
block
.
append_op
(
type
=
'extract_rows'
,
inputs
=
{
'X'
:
grad
},
outputs
=
{
'Out'
:
idx
})
block
.
append_op
(
...
...
@@ -228,7 +228,7 @@ class L1DecayRegularizer(WeightDecayRegularizer):
decay
=
block
.
create_var
(
dtype
=
"float32"
,
shape
=
param
.
shape
,
type
=
core
.
VarDesc
.
VarType
.
SELECTED_ROWS
)
type
=
core
.
VarDesc
.
VarType
.
LOD_TENSOR
)
block
.
append_op
(
type
=
'extract_rows'
,
inputs
=
{
'X'
:
grad
},
outputs
=
{
'Out'
:
idx
})
block
.
append_op
(
...
...
python/paddle/fluid/tests/CMakeLists.txt
浏览文件 @
92a2817a
if
(
NOT APPLE
)
set
(
PYTHON_TESTS_DIR
${
CMAKE_CURRENT_BINARY_DIR
}
CACHE PATH
"python tests directory"
)
else
()
set
(
PYTHON_TESTS_DIR
${
PADDLE_BINARY_DIR
}
/python/paddle/fluid/tests
)
endif
(
NOT APPLE
)
set
(
PYTHON_TESTS_DIR
${
PADDLE_BINARY_DIR
}
/python/paddle/fluid/tests CACHE INTERNAL
"python tests directory"
)
file
(
GLOB TEST_OPS RELATIVE
"
${
CMAKE_CURRENT_SOURCE_DIR
}
"
"test_*.py"
)
string
(
REPLACE
".py"
""
TEST_OPS
"
${
TEST_OPS
}
"
)
...
...
python/paddle/fluid/tests/unittests/test_slice_var.py
浏览文件 @
92a2817a
...
...
@@ -30,7 +30,6 @@ class TestSliceVar(unittest.TestCase):
var
=
program
.
global_block
().
create_var
(
name
=
str
(
random
.
randint
(
10000
,
99999
)),
persistable
=
True
,
# dtype=core.VarDesc.VarType.LOD_TENSOR,
shape
=
shape
)
var_list
.
append
(
var
)
blocks
=
slice_variable
(
var_list
,
10
,
min_size
)
...
...
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