Files
FastDeploy/tests/release_task/cpp_run.sh
T
Jason 43cabceb6d Update release/0.4 (#423)
* [Backend] TRT backend & PP-Infer backend support pinned memory (#403)

* TRT backend use pinned memory

* refine fd tensor pinned memory logic

* TRT enable pinned memory configurable

* paddle inference support pinned memory

* pinned memory pybindings

Co-authored-by: Jason <jiangjiajun@baidu.com>

* [Bug Fix] release task scripts (#411)

* Update py_run.bat

* Update cpp_run.bat

* Update compare_with_gt.py

Increase score_diff and boxes_diff_ratio threshold

* Update cpp_run.bat

* Update release task scripts according to diffrent platforms

* Delete CMAKE_CXX_COMPILER in cpp_run.bat

* [Doc] add contributor for js application (#413)

add contributor

* [Other] Refactor js submodule (#415)

* Refactor js submodule

* Remove change-log

* Update ocr module

* Update ocr-detection module

* Update ocr-detection module

* Remove change-log

* [Doc] Add PicoDet & PaddleClas Android demo docs (#412)

* [Backend] Add override flag to lite backend

* [Docs] Add Android C++ SDK build docs

* [Doc] fix android_build_docs typos

* Update CMakeLists.txt

* Update android.md

* [Doc] Add PicoDet Android demo docs

* [Doc] Update PicoDet Andorid demo docs

* [Doc] Update PaddleClasModel Android demo docs

* [Doc] Update fastdeploy android jni docs

* [Doc] Update fastdeploy android jni usage docs

Co-authored-by: Jason <jiangjiajun@baidu.com>

* Update README.md

* Update README_CN.md

* Update README_CN.md

* Update README_EN.md

* [Doc] Add  tutorial of supporting new models (#418)

* first commit for yolov7

* pybind for yolov7

* CPP README.md

* CPP README.md

* modified yolov7.cc

* README.md

* python file modify

* delete license in fastdeploy/

* repush the conflict part

* README.md modified

* README.md modified

* file path modified

* file path modified

* file path modified

* file path modified

* file path modified

* README modified

* README modified

* move some helpers to private

* add examples for yolov7

* api.md modified

* api.md modified

* api.md modified

* YOLOv7

* yolov7 release link

* yolov7 release link

* yolov7 release link

* copyright

* change some helpers to private

* change variables to const and fix documents.

* gitignore

* Transfer some funtions to private member of class

* Transfer some funtions to private member of class

* Merge from develop (#9)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* first commit for yolor

* for merge

* Develop (#11)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* Yolor (#16)

* Develop (#11) (#12)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* Develop (#13)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* documents

* Develop (#14)

* Fix compile problem in different python version (#26)

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>

* Add PaddleDetetion/PPYOLOE model support (#22)

* add ppdet/ppyoloe

* Add demo code and documents

* add convert processor to vision (#27)

* update .gitignore

* Added checking for cmake include dir

* fixed missing trt_backend option bug when init from trt

* remove un-need data layout and add pre-check for dtype

* changed RGB2BRG to BGR2RGB in ppcls model

* add model_zoo yolov6 c++/python demo

* fixed CMakeLists.txt typos

* update yolov6 cpp/README.md

* add yolox c++/pybind and model_zoo demo

* move some helpers to private

* fixed CMakeLists.txt typos

* add normalize with alpha and beta

* add version notes for yolov5/yolov6/yolox

* add copyright to yolov5.cc

* revert normalize

* fixed some bugs in yolox

* fixed examples/CMakeLists.txt to avoid conflicts

* add convert processor to vision

* format examples/CMakeLists summary

* Fix bug while the inference result is empty with YOLOv5 (#29)

* Add multi-label function for yolov5

* Update README.md

Update doc

* Update fastdeploy_runtime.cc

fix variable option.trt_max_shape wrong name

* Update runtime_option.md

Update resnet model dynamic shape setting name from images to x

* Fix bug when inference result boxes are empty

* Delete detection.py

Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>
Co-authored-by: Jason <928090362@qq.com>

* add is_dynamic for YOLO series (#22)

* modify ppmatting backend and docs

* modify ppmatting docs

* fix the PPMatting size problem

* fix LimitShort's log

* retrigger ci

* modify PPMatting docs

* modify the way  for dealing with  LimitShort

* change develop_a_new_model.md dir

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: huangjianhui <852142024@qq.com>
Co-authored-by: Jason <928090362@qq.com>

* [Doc] add readme for js packages  (#421)

* add contributor

* add package readme

* refine ocr readme

* refine ocr readme

Co-authored-by: Wang Xinyu <wangxinyu_es@163.com>
Co-authored-by: huangjianhui <852142024@qq.com>
Co-authored-by: Double_V <liuvv0203@163.com>
Co-authored-by: chenqianhe <54462604+chenqianhe@users.noreply.github.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
Co-authored-by: leiqing <54695910+leiqing1@users.noreply.github.com>
Co-authored-by: ziqi-jin <67993288+ziqi-jin@users.noreply.github.com>
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>
2022-10-24 16:48:48 +08:00

84 lines
3.3 KiB
Bash

#!/bin/bash
export no_proxy=bcebos.com,xly.bce.baidu.com,aliyun.com
CURRENT_DIR=$(cd $(dirname $0); pwd)
PLATFORM=$1
DEVICE=$2
VERSION=$3
if [ "$DEVICE" = "gpu" ];then
CPP_FASTDEPLOY_PACKAGE=fastdeploy-$PLATFORM-$DEVICE-$VERSION
else
CPP_FASTDEPLOY_PACKAGE=fastdeploy-$PLATFORM-$VERSION
fi
echo $CPP_FASTDEPLOY_PACKAGE
LINUX_X64_GPU_CASE=('ort' 'paddle' 'trt')
LINUX_X64_CPU_CASE=('ort' 'paddle' 'openvino')
#LINUX_AARCH_CPU_CASE=('ort' 'openvino')
LINUX_AARCH_CPU_CASE=('ort')
MACOS_INTEL_CPU_CASE=('ort' 'paddle' 'openvino')
MACOS_ARM64_CPU_CASE=('default')
wget -q https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
wget -q https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
wget -q https://bj.bcebos.com/paddlehub/fastdeploy/release_task_groud_truth_result.txt
tar -xvf ppyoloe_crn_l_300e_coco.tgz
IMAGE_PATH=$CURRENT_DIR/000000014439.jpg
MODEL_PATH=$CURRENT_DIR/ppyoloe_crn_l_300e_coco
GROUND_TRUTH_PATH=$CURRENT_DIR/release_task_groud_truth_result.txt
COMPARE_SHELL=$CURRENT_DIR/compare_with_gt.py
RUN_CASE=()
CONF_THRESHOLD=0
if [ "$DEVICE" = "gpu" ] && [ "$PLATFORM" = "linux-x64" ];then
RUN_CASE=(${LINUX_X64_GPU_CASE[*]})
elif [ "$DEVICE" = "cpu" ] && [ "$PLATFORM" = "linux-x64" ];then
RUN_CASE=(${LINUX_X64_CPU_CASE[*]})
elif [ "$DEVICE" = "cpu" ] && [ "$PLATFORM" = "linux-aarch64" ];then
RUN_CASE=(${LINUX_AARCH_CPU_CASE[*]})
elif [ "$DEVICE" = "cpu" ] && [ "$PLATFORM" = "osx-x86_64" ];then
RUN_CASE=(${MACOS_INTEL_CPU_CASE[*]})
elif [ "$DEVICE" = "cpu" ] && [ "$PLATFORM" = "osx-arm64" ];then
RUN_CASE=(${MACOS_ARM64_CPU_CASE[*]})
CONF_THRESHOLD=0.5
fi
case_number=${#RUN_CASE[@]}
wget -q https://fastdeploy.bj.bcebos.com/dev/cpp/$CPP_FASTDEPLOY_PACKAGE.tgz
tar xvf $CPP_FASTDEPLOY_PACKAGE.tgz
mkdir build && cd build
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../$CPP_FASTDEPLOY_PACKAGE -DCMAKE_CXX_COMPILER=$CMAKE_CXX_COMPILER
make -j
for((i=0;i<case_number;i+=1))
do
backend=${RUN_CASE[i]}
echo "Cpp Backend:" $backend
if [ "$backend" != "trt" ];then
./infer_ppyoloe_demo --model_dir=$MODEL_PATH --image_file=$IMAGE_PATH --device=cpu --backend=$backend >> cpp_cpu_result.txt
python $COMPARE_SHELL --gt_path $GROUND_TRUTH_PATH --result_path cpp_cpu_result.txt --platform $PLATFORM --device cpu --conf_threshold $CONF_THRESHOLD
fi
if [ "$DEVICE" = "gpu" ];then
if [ "$backend" = "trt" ];then
./infer_ppyoloe_demo --model_dir=$MODEL_PATH --image_file=$IMAGE_PATH --device=gpu --backend=$backend >> cpp_trt_result.txt
python $COMPARE_SHELL --gt_path $GROUND_TRUTH_PATH --result_path cpp_trt_result.txt --platform $PLATFORM --device trt --conf_threshold $CONF_THRESHOLD
else
./infer_ppyoloe_demo --model_dir=$MODEL_PATH --image_file=$IMAGE_PATH --device=gpu --backend=$backend >> cpp_gpu_result.txt
python $COMPARE_SHELL --gt_path $GROUND_TRUTH_PATH --result_path cpp_gpu_result.txt --platform $PLATFORM --device gpu --conf_threshold $CONF_THRESHOLD
fi
fi
done
ret=$?
res_file="result.txt"
if [ ! -f $res_file ];then
if [ $ret -ne 0 ];then
exit -1
fi
exit 0
else
cat $res_file
exit -1
fi