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
df2d1769
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
df2d1769
编写于
10月 14, 2017
作者:
Q
qijun
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix code style
上级
7ef568e8
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
13 addition
and
9 deletion
+13
-9
paddle/framework/lod_tensor.h
paddle/framework/lod_tensor.h
+3
-0
paddle/framework/type_defs.h
paddle/framework/type_defs.h
+3
-0
paddle/operators/math/math_function.cu
paddle/operators/math/math_function.cu
+7
-9
未找到文件。
paddle/framework/lod_tensor.h
浏览文件 @
df2d1769
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
...
...
paddle/framework/type_defs.h
浏览文件 @
df2d1769
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
...
...
paddle/operators/math/math_function.cu
浏览文件 @
df2d1769
...
...
@@ -214,10 +214,8 @@ template struct SelectedRowsAdd<platform::GPUPlace, float>;
namespace
{
template
<
typename
T
>
__global__
void
SelectedRowsAddTensorKernel
(
const
T
*
selected_rows
,
const
int64_t
*
rows
,
T
*
tensor_out
,
int64_t
row_numel
,
int
block_size
)
{
const
int64_t
*
rows
,
T
*
tensor_out
,
int64_t
row_numel
,
int
block_size
)
{
const
int
ty
=
blockIdx
.
y
;
int
tid
=
threadIdx
.
x
;
...
...
@@ -261,11 +259,11 @@ struct SelectedRowsAddTensor<platform::GPUPlace, T> {
int
block_size
=
256
;
dim3
threads
(
block_size
,
1
);
dim3
grid
(
1
,
in1_height
);
SelectedRowsAddTensorKernel
<
T
><<<
grid
,
threads
,
0
,
reinterpret_cast
<
const
platform
::
CUDADeviceContext
&>
(
context
).
stream
(
)
>>>
(
in1_data
,
in1_rows
.
data
()
,
out_data
,
in1_row_numel
,
block_size
);
SelectedRowsAddTensorKernel
<
T
><<<
grid
,
threads
,
0
,
reinterpret_cast
<
const
platform
::
CUDADeviceContext
&>
(
context
)
.
stream
()
>>>
(
in1_data
,
in1_rows
.
data
(),
out_data
,
in1_row_numel
,
block_size
);
auto
out_eigen
=
framework
::
EigenVector
<
T
>::
Flatten
(
*
output
);
auto
in2_eigen
=
framework
::
EigenVector
<
T
>::
Flatten
(
input2
);
...
...
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