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
PaddleDetection
提交
efb73aec
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
695
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
efb73aec
编写于
6月 13, 2023
作者:
Y
YuBaoku
提交者:
GitHub
6月 13, 2023
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
fix the error of defined more than once (#8351)
* fix the error of defined more than once * fix the error of defined
上级
3e5bf8a6
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
3 addition
and
3 deletion
+3
-3
deploy/cpp/src/main.cc
deploy/cpp/src/main.cc
+3
-3
未找到文件。
deploy/cpp/src/main.cc
浏览文件 @
efb73aec
...
@@ -62,7 +62,7 @@ DEFINE_int32(gpu_id, 0, "Device id of GPU to execute");
...
@@ -62,7 +62,7 @@ DEFINE_int32(gpu_id, 0, "Device id of GPU to execute");
DEFINE_bool
(
run_benchmark
,
DEFINE_bool
(
run_benchmark
,
false
,
false
,
"Whether to predict a image_file repeatedly for benchmark"
);
"Whether to predict a image_file repeatedly for benchmark"
);
DEFINE_bool
(
use
_mkldnn
,
false
,
"Whether use mkldnn with CPU"
);
DEFINE_bool
(
run
_mkldnn
,
false
,
"Whether use mkldnn with CPU"
);
DEFINE_int32
(
cpu_threads
,
1
,
"Num of threads with CPU"
);
DEFINE_int32
(
cpu_threads
,
1
,
"Num of threads with CPU"
);
DEFINE_int32
(
trt_min_shape
,
1
,
"Min shape of TRT DynamicShapeI"
);
DEFINE_int32
(
trt_min_shape
,
1
,
"Min shape of TRT DynamicShapeI"
);
DEFINE_int32
(
trt_max_shape
,
1280
,
"Max shape of TRT DynamicShapeI"
);
DEFINE_int32
(
trt_max_shape
,
1280
,
"Max shape of TRT DynamicShapeI"
);
...
@@ -91,7 +91,7 @@ void PrintBenchmarkLog(std::vector<double> det_time, int img_num) {
...
@@ -91,7 +91,7 @@ void PrintBenchmarkLog(std::vector<double> det_time, int img_num) {
LOG
(
INFO
)
<<
"precision: "
LOG
(
INFO
)
<<
"precision: "
<<
"fp32"
;
<<
"fp32"
;
}
}
LOG
(
INFO
)
<<
"enable_mkldnn: "
<<
(
FLAGS_
use
_mkldnn
?
"True"
:
"False"
);
LOG
(
INFO
)
<<
"enable_mkldnn: "
<<
(
FLAGS_
run
_mkldnn
?
"True"
:
"False"
);
LOG
(
INFO
)
<<
"cpu_math_library_num_threads: "
<<
FLAGS_cpu_threads
;
LOG
(
INFO
)
<<
"cpu_math_library_num_threads: "
<<
FLAGS_cpu_threads
;
LOG
(
INFO
)
<<
"----------------------- Data info -----------------------"
;
LOG
(
INFO
)
<<
"----------------------- Data info -----------------------"
;
LOG
(
INFO
)
<<
"batch_size: "
<<
FLAGS_batch_size
;
LOG
(
INFO
)
<<
"batch_size: "
<<
FLAGS_batch_size
;
...
@@ -386,7 +386,7 @@ int main(int argc, char** argv) {
...
@@ -386,7 +386,7 @@ int main(int argc, char** argv) {
// Load model and create a object detector
// Load model and create a object detector
PaddleDetection
::
ObjectDetector
det
(
FLAGS_model_dir
,
PaddleDetection
::
ObjectDetector
det
(
FLAGS_model_dir
,
FLAGS_device
,
FLAGS_device
,
FLAGS_
use
_mkldnn
,
FLAGS_
run
_mkldnn
,
FLAGS_cpu_threads
,
FLAGS_cpu_threads
,
FLAGS_run_mode
,
FLAGS_run_mode
,
FLAGS_batch_size
,
FLAGS_batch_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