apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-27 18:41:02 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Add Benchmark test (#200)

Browse Source 
* add ppcls benchmark

* add ppcls benchmark

* add ppcls benchmark

* add ppcls benchmark

* fixed txt path

* resolve conflict

* resolve conflict

* deal with comments

* Add enable_trt_fp16 option

* Add OV backend for seg and det

* fixed valid backends in ppdet

* fixed valid backends in yolo

* add copyright and rm Chinese Notes

* add ppdet&ppseg&yolo benchmark

* add cpu/gpu mem info

Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
WJJ1995
2022-09-14 20:15:01 +08:00
committed by GitHub
parent 695034fdad
commit 06908b8beb
19 changed files with 1014 additions and 190 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/vision/detection/contrib/yolov7.cc
View File

@@ -61,8 +61,8 @@ YOLOv7::YOLOv7(const std::string& model_file, const std::string& params_file,
const RuntimeOption& custom_option,
const Frontend& model_format) {
if (model_format == Frontend::ONNX) {
valid_cpu_backends = {Backend::ORT}; // 指定可用的CPU后端
valid_gpu_backends = {Backend::ORT, Backend::TRT}; // 指定可用的GPU后端
valid_cpu_backends = {Backend::OPENVINO, Backend::ORT};
valid_gpu_backends = {Backend::ORT, Backend::TRT};
} else {
valid_cpu_backends = {Backend::PDINFER};
valid_gpu_backends = {Backend::PDINFER};