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
wzpei9
Paddle
提交
24ced1d0
P
Paddle
项目概览
wzpei9
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
1
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
1
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
1
Issue
1
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
24ced1d0
编写于
7月 12, 2018
作者:
L
Luo Tao
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add independent demo for test static fluid library
上级
092d6201
变更
4
显示空白变更内容
内联
并排
Showing
4 changed file
with
15 addition
and
16 deletion
+15
-16
paddle/contrib/inference/demo_ci/CMakeLists.txt
paddle/contrib/inference/demo_ci/CMakeLists.txt
+0
-2
paddle/contrib/inference/demo_ci/run.sh
paddle/contrib/inference/demo_ci/run.sh
+6
-8
paddle/fluid/inference/CMakeLists.txt
paddle/fluid/inference/CMakeLists.txt
+7
-6
paddle/scripts/paddle_build.sh
paddle/scripts/paddle_build.sh
+2
-0
未找到文件。
paddle/contrib/inference/demo_ci/CMakeLists.txt
浏览文件 @
24ced1d0
...
...
@@ -54,9 +54,7 @@ endif()
if
(
WITH_STATIC_LIB
)
set
(
DEPS
"-Wl,--whole-archive"
${
PADDLE_LIB
}
/paddle/fluid/inference/libpaddle_fluid.a
"-Wl,--no-whole-archive"
${
PADDLE_LIB
}
/contrib/inference/libpaddle_inference_api.a
)
else
()
# Note: libpaddle_inference_api.so must put before libpaddle_fluid.so
...
...
paddle/contrib/inference/demo_ci/run.sh
浏览文件 @
24ced1d0
...
...
@@ -11,24 +11,22 @@ fi
mkdir
-p
build
cd
build
for
WITH_STATIC_LIB
in
false
;
do
for
WITH_STATIC_LIB
in
ON OFF
;
do
rm
-rf
*
cmake ..
-DPADDLE_LIB
=
${
PADDLE_ROOT
}
/build/fluid_install_dir/
\
-DWITH_MKL
=
$WITH_MKL
\
-DDEMO_NAME
=
simple_on_word2vec
\
-DWITH_GPU
=
$WITH_GPU
\
-DWITH_STATIC_LIB
=
$WITH_STATIC_LIB
make
make
-j
for
use_gpu
in
$use_gpu_list
;
do
./simple_on_word2vec
\
--dirname
=
${
PADDLE_ROOT
}
/build/python/paddle/fluid/tests/book/word2vec.inference.model
\
--use_gpu
=
$use_gpu
done
done
if
[
$?
-eq
0
]
;
then
exit
0
else
if
[
$?
-ne
0
]
;
then
echo
"inference demo runs fail."
exit
1
fi
fi
done
done
set
+x
paddle/fluid/inference/CMakeLists.txt
浏览文件 @
24ced1d0
# analysis and tensorrt must be added before creating static library,
# otherwise, there would be undefined reference to them in static library.
add_subdirectory
(
analysis
)
if
(
TENSORRT_FOUND
)
add_subdirectory
(
tensorrt
)
endif
()
set
(
FLUID_CORE_MODULES proto_desc memory lod_tensor executor
)
# TODO(panyx0718): Should this be called paddle_fluid_inference_api_internal?
...
...
@@ -35,9 +42,3 @@ if(WITH_TESTING)
# both tests/book and analysis depends the models that generated by python/paddle/fluid/tests/book
add_subdirectory
(
tests/book
)
endif
()
add_subdirectory
(
analysis
)
if
(
TENSORRT_FOUND
)
add_subdirectory
(
tensorrt
)
endif
()
paddle/scripts/paddle_build.sh
浏览文件 @
24ced1d0
...
...
@@ -508,6 +508,7 @@ function gen_fluid_inference_lib() {
Deploying fluid inference library ...
========================================
EOF
cmake ..
-DWITH_DISTRIBUTE
=
OFF
make
-j
`
nproc
`
inference_lib_dist
cd
${
PADDLE_ROOT
}
/build
cp
-r
fluid_install_dir fluid
...
...
@@ -569,6 +570,7 @@ function main() {
fluid_inference_lib
)
cmake_gen
${
PYTHON_ABI
:-
""
}
gen_fluid_inference_lib
test_fluid_inference_lib
;;
check_style
)
check_style
...
...
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