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
ba3ebe20
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
未验证
提交
ba3ebe20
编写于
6月 01, 2022
作者:
S
shangliang Xu
提交者:
GitHub
6月 01, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
[TIPC] fix cpp_infer, not use trt/mkldnn (#6102)
上级
bdf86c58
变更
26
显示空白变更内容
内联
并排
Showing
26 changed file
with
30 addition
and
28 deletion
+30
-28
test_tipc/configs/keypoint/tinypose_128x96_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_l_640_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_l_640_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_lcnet_1_5x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_m_416_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_m_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_mobilenetv3_large_1x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_r18_640_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_s_320_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_s_320_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_shufflenetv2_1x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/picodet/picodet_xs_320_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolo_mbv3_large_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolo_mbv3_small_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolo_r18vd_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolo_tiny_650e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyoloe/ppyoloe_crn_l_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyoloe/ppyoloe_crn_m_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/ppyoloe/ppyoloe_crn_x_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/configs/yolov3/yolov3_darknet53_270e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
...model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
+1
-1
test_tipc/test_inference_cpp.sh
test_tipc/test_inference_cpp.sh
+5
-3
未找到文件。
test_tipc/configs/keypoint/tinypose_128x96_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_l_640_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_l_640_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_lcnet_1_5x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_m_416_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_m_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_mobilenetv3_large_1x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_r18_640_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_s_320_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_s_320_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_shufflenetv2_1x_416_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/picodet/picodet_xs_320_coco_lcnet_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolo_mbv3_large_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolo_mbv3_small_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolo_r18vd_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolo_r50vd_dcn_1x_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolo_tiny_650e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolov2_r101vd_dcn_365e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyoloe/ppyoloe_crn_l_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyoloe/ppyoloe_crn_m_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyoloe/ppyoloe_crn_s_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/ppyoloe/ppyoloe_crn_x_300e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/configs/yolov3/yolov3_darknet53_270e_coco_model_linux_gpu_normal_normal_infer_cpp_linux_gpu_cpu.txt
浏览文件 @
ba3ebe20
...
...
@@ -18,7 +18,7 @@ infer_mode:norm
infer_quant:False
inference:./deploy/cpp/build/main
--device:gpu|cpu
--use_mkldnn:
True|
False
--use_mkldnn:False
--cpu_threads:4
--batch_size:1|2
--use_tensorrt:null
...
...
test_tipc/test_inference_cpp.sh
浏览文件 @
ba3ebe20
...
...
@@ -131,7 +131,9 @@ fi
# build program
# TODO: set PADDLE_DIR and TENSORRT_ROOT
if
[
-z
$PADDLE_DIR
]
;
then
PADDLE_DIR
=
/paddle/Paddle/build/paddle_inference_install_dir/
wget
-nc
https://paddle-inference-lib.bj.bcebos.com/2.2.2/cxx_c/Linux/GPU/x86-64_gcc8.2_avx_mkl_cuda11.1_cudnn8.1.1_trt7.2.3.4/paddle_inference.tgz
--no-check-certificate
tar
zxf paddle_inference.tgz
PADDLE_DIR
=
$(
pwd
)
/paddle_inference
fi
if
[
-z
$TENSORRT_ROOT
]
;
then
TENSORRT_ROOT
=
/usr/local/TensorRT6-cuda10.1-cudnn7
...
...
@@ -146,8 +148,8 @@ mkdir -p build
cd
./build
cmake ..
\
-DWITH_GPU
=
ON
\
-DWITH_MKL
=
O
N
\
-DWITH_TENSORRT
=
O
N
\
-DWITH_MKL
=
O
FF
\
-DWITH_TENSORRT
=
O
FF
\
-DPADDLE_LIB_NAME
=
libpaddle_inference
\
-DPADDLE_DIR
=
${
PADDLE_DIR
}
\
-DCUDA_LIB
=
${
CUDA_LIB
}
\
...
...
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