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
8e86721f
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
未验证
提交
8e86721f
编写于
7月 06, 2018
作者:
Y
yuyang18
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix data balance on single GPU
上级
d3a48484
变更
5
隐藏空白更改
内联
并排
Showing
5 changed file
with
26 addition
and
10 deletion
+26
-10
paddle/fluid/framework/details/build_strategy.h
paddle/fluid/framework/details/build_strategy.h
+1
-1
paddle/fluid/framework/details/data_balance_op_handle.cc
paddle/fluid/framework/details/data_balance_op_handle.cc
+3
-3
paddle/fluid/framework/details/multi_devices_graph_builder.cc
...le/fluid/framework/details/multi_devices_graph_builder.cc
+5
-0
paddle/fluid/operators/read_op.cc
paddle/fluid/operators/read_op.cc
+7
-3
python/paddle/fluid/tests/unittests/test_data_balance.py
python/paddle/fluid/tests/unittests/test_data_balance.py
+10
-3
未找到文件。
paddle/fluid/framework/details/build_strategy.h
浏览文件 @
8e86721f
...
@@ -34,7 +34,7 @@ struct BuildStrategy {
...
@@ -34,7 +34,7 @@ struct BuildStrategy {
std
::
string
debug_graphviz_path_
{
""
};
std
::
string
debug_graphviz_path_
{
""
};
bool
enable_data_balance_
{
tru
e
};
bool
enable_data_balance_
{
fals
e
};
};
};
}
// namespace details
}
// namespace details
...
...
paddle/fluid/framework/details/data_balance_op_handle.cc
浏览文件 @
8e86721f
...
@@ -86,9 +86,9 @@ std::vector<std::array<int, 3>> DataBalanceOpHandle::GetBalancePlan(
...
@@ -86,9 +86,9 @@ std::vector<std::array<int, 3>> DataBalanceOpHandle::GetBalancePlan(
}
}
void
DataBalanceOpHandle
::
RunImpl
()
{
void
DataBalanceOpHandle
::
RunImpl
()
{
if
(
places_
.
size
()
==
1
)
{
PADDLE_ENFORCE_GT
(
places_
.
size
(),
1
,
return
;
"Data balance can only be enabled when the number of "
}
"places to run larger than 1."
);
auto
in_var_handles
=
DynamicCast
<
VarHandle
>
(
inputs_
);
auto
in_var_handles
=
DynamicCast
<
VarHandle
>
(
inputs_
);
auto
out_var_handles
=
DynamicCast
<
VarHandle
>
(
outputs_
);
auto
out_var_handles
=
DynamicCast
<
VarHandle
>
(
outputs_
);
PADDLE_ENFORCE
(
in_var_handles
.
size
()
%
places_
.
size
()
==
0
);
PADDLE_ENFORCE
(
in_var_handles
.
size
()
%
places_
.
size
()
==
0
);
...
...
paddle/fluid/framework/details/multi_devices_graph_builder.cc
浏览文件 @
8e86721f
...
@@ -59,6 +59,11 @@ MultiDevSSAGraphBuilder::MultiDevSSAGraphBuilder(
...
@@ -59,6 +59,11 @@ MultiDevSSAGraphBuilder::MultiDevSSAGraphBuilder(
grad_names_
.
insert
(
GradVarName
(
p
));
grad_names_
.
insert
(
GradVarName
(
p
));
}
}
balance_vars_
.
resize
(
places_
.
size
(),
0
);
balance_vars_
.
resize
(
places_
.
size
(),
0
);
if
(
strategy_
.
enable_data_balance_
&&
places_
.
size
()
==
1
)
{
LOG
(
WARNING
)
<<
"It is no need to enable data balance when there is only "
"one place. enable_data_balance is set to False."
;
strategy_
.
enable_data_balance_
=
false
;
}
}
}
void
MultiDevSSAGraphBuilder
::
CreateOpHandleIOs
(
SSAGraph
*
result
,
void
MultiDevSSAGraphBuilder
::
CreateOpHandleIOs
(
SSAGraph
*
result
,
...
...
paddle/fluid/operators/read_op.cc
浏览文件 @
8e86721f
...
@@ -92,9 +92,13 @@ class ReadOpMaker : public framework::OpProtoAndCheckerMaker {
...
@@ -92,9 +92,13 @@ class ReadOpMaker : public framework::OpProtoAndCheckerMaker {
void
Make
()
override
{
void
Make
()
override
{
AddInput
(
"Reader"
,
"(ReaderHolder) The executed reader."
);
AddInput
(
"Reader"
,
"(ReaderHolder) The executed reader."
);
AddOutput
(
"Out"
,
"(LoDTensor) The output data."
).
AsDuplicable
();
AddOutput
(
"Out"
,
"(LoDTensor) The output data."
).
AsDuplicable
();
AddAttr
<
bool
>
(
"throw_eof_exp"
,
AddAttr
<
bool
>
(
"If set true, an exception will be thrown when the Reader "
"throw_eof_exp"
,
"yields empty (which means there is no next data)."
)
"If set true, an exception will be thrown when the Reader "
"yields empty (which means there is no next data).
\n
"
"NOTES: This flag must be true always. It will be set to false"
" only when the data-balance is enabled in ParallelExecutor"
" and it is set by ParallelExecutor instance, not users."
)
.
SetDefault
(
true
);
.
SetDefault
(
true
);
AddComment
(
R"DOC(
AddComment
(
R"DOC(
Read Operator
Read Operator
...
...
python/paddle/fluid/tests/unittests/test_data_balance.py
浏览文件 @
8e86721f
...
@@ -103,8 +103,12 @@ class TestDataBalance(unittest.TestCase):
...
@@ -103,8 +103,12 @@ class TestDataBalance(unittest.TestCase):
exe
=
fluid
.
Executor
(
place
)
exe
=
fluid
.
Executor
(
place
)
exe
.
run
(
startup_prog
)
exe
.
run
(
startup_prog
)
build_strategy
=
fluid
.
BuildStrategy
()
build_strategy
.
enable_data_balance
=
True
parallel_exe
=
fluid
.
ParallelExecutor
(
parallel_exe
=
fluid
.
ParallelExecutor
(
use_cuda
=
self
.
use_cuda
,
main_program
=
main_prog
)
use_cuda
=
self
.
use_cuda
,
main_program
=
main_prog
,
build_strategy
=
build_strategy
)
if
(
parallel_exe
.
device_count
>
self
.
batch_size
):
if
(
parallel_exe
.
device_count
>
self
.
batch_size
):
print
(
"WARNING: Unittest TestDataBalance skipped.
\
print
(
"WARNING: Unittest TestDataBalance skipped.
\
...
@@ -145,9 +149,12 @@ class TestDataBalance(unittest.TestCase):
...
@@ -145,9 +149,12 @@ class TestDataBalance(unittest.TestCase):
place
=
fluid
.
CUDAPlace
(
0
)
if
self
.
use_cuda
else
fluid
.
CPUPlace
()
place
=
fluid
.
CUDAPlace
(
0
)
if
self
.
use_cuda
else
fluid
.
CPUPlace
()
exe
=
fluid
.
Executor
(
place
)
exe
=
fluid
.
Executor
(
place
)
exe
.
run
(
startup_prog
)
exe
.
run
(
startup_prog
)
build_strategy
=
fluid
.
BuildStrategy
()
build_strategy
.
enable_data_balance
=
True
parallel_exe
=
fluid
.
ParallelExecutor
(
parallel_exe
=
fluid
.
ParallelExecutor
(
use_cuda
=
self
.
use_cuda
,
main_program
=
main_prog
)
use_cuda
=
self
.
use_cuda
,
main_program
=
main_prog
,
build_strategy
=
build_strategy
)
if
(
parallel_exe
.
device_count
>
self
.
batch_size
):
if
(
parallel_exe
.
device_count
>
self
.
batch_size
):
print
(
"WARNING: Unittest TestDataBalance skipped.
\
print
(
"WARNING: Unittest TestDataBalance skipped.
\
...
...
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