[Other] Change release task demo image url (#968)

felixhjh · root · joey12300 · web-flow · commit 8a986c23ec3d · 2022-12-26T15:49:30.000+08:00
* Fix release_task cpp_run.sh

 Author:    felixhjh &lt;852142024@qq.com&gt;
 Date:      Thu Nov 10 07:26:48 2022 +0000

* Add option for infer_ppyoloe.cc

  author:    felixhjh &lt;852142024@qq.com&gt;

* Fix bug in release task scripts

* Add error check function

* Format code

* Add new download dir for release version

* Fix precision diff for osx-arm64

* Update py_run.sh

* Add threshold for osx-arm64

* Add osx-x86_64 threshold

* Add error check function

* Remove root commit author

* Add error check function

* Format code

* [Bug Fix]Remove profile (#579)

remove profile

* Add new download dir for release version

* [Bug Fix]Add check return code function (#581)

* Fix release_task cpp_run.sh

 Author:    felixhjh &lt;852142024@qq.com&gt;
 Date:      Thu Nov 10 07:26:48 2022 +0000

* Add option for infer_ppyoloe.cc

  author:    felixhjh &lt;852142024@qq.com&gt;

* Fix bug in release task scripts

* Add error check function

* Format code

 Author:    felixhjh &lt;852142024@qq.com&gt;

* [Quantization] Remove extra requirements for fd-auto-compress package (#582)

* Add PaddleOCR Support

* Add PaddleOCR Support

* Add PaddleOCRv3 Support

* Add PaddleOCRv3 Support

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Add PaddleOCRv3 Support

* Add PaddleOCRv3 Supports

* Add PaddleOCRv3 Suport

* Fix Rec diff

* Remove useless functions

* Remove useless comments

* Add PaddleOCRv2 Support

* Add PaddleOCRv3 &amp; PaddleOCRv2 Support

* remove useless parameters

* Add utils of sorting det boxes

* Fix code naming convention

* Fix code naming convention

* Fix code naming convention

* Fix bug in the Classify process

* Imporve OCR Readme

* Fix diff in Cls model

* Update Model Download Link in Readme

* Fix diff in PPOCRv2

* Improve OCR readme

* Imporve OCR readme

* Improve OCR readme

* Improve OCR readme

* Imporve OCR readme

* Improve OCR readme

* Fix conflict

* Add readme for OCRResult

* Improve OCR readme

* Add OCRResult readme

* Improve OCR readme

* Improve OCR readme

* Add Model Quantization Demo

* Fix Model Quantization Readme

* Fix Model Quantization Readme

* Add the function to do PTQ quantization

* Improve quant tools readme

* Improve quant tool readme

* Improve quant tool readme

* Add PaddleInference-GPU for OCR Rec model

* Add QAT method to fastdeploy-quantization tool

* Remove examples/slim for now

* Move configs folder

* Add Quantization Support for Classification Model

* Imporve ways of importing preprocess

* Upload YOLO Benchmark on readme

* Upload YOLO Benchmark on readme

* Upload YOLO Benchmark on readme

* Improve Quantization configs and readme

* Add support for multi-inputs model

* Add backends and params file for YOLOv7

* Add quantized model deployment support for YOLO series

* Fix YOLOv5 quantize readme

* Fix YOLO quantize readme

* Fix YOLO quantize readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Fix bug, change Fronted to ModelFormat

* Change Fronted to ModelFormat

* Add examples to deploy quantized paddleclas models

* Fix readme

* Add quantize Readme

* Add quantize Readme

* Add quantize Readme

* Modify readme of quantization tools

* Modify readme of quantization tools

* Improve quantization tools readme

* Improve quantization readme

* Improve PaddleClas quantized model deployment  readme

* Add PPYOLOE-l quantized deployment examples

* Improve quantization tools readme

* Improve Quantize Readme

* Fix conflicts

* Fix conflicts

* improve readme

* Improve quantization tools and readme

* Improve quantization tools and readme

* Add quantized deployment examples for PaddleSeg model

* Fix cpp readme

* Fix memory leak of reader_wrapper function

* Fix model file name in PaddleClas quantization examples

* Update Runtime and E2E benchmark

* Update Runtime and E2E benchmark

* Rename quantization tools to auto compression tools

* Remove PPYOLOE data when deployed on MKLDNN

* Fix readme

* Support PPYOLOE with OR without NMS and update readme

* Update Readme

* Update configs and readme

* Update configs and readme

* Add Paddle-TensorRT backend in quantized model deploy examples

* Support PPYOLOE+ series

* Add reused_input_tensors for PPYOLOE

* Improve fastdeploy tools usage

* improve fastdeploy tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* remove modify

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Remove extra requirements for fd-auto-compress package

* [Backend] cuda normalize and permute, cuda concat, optimized ppcls, ppdet &amp; ppseg (#546)

* cuda normalize and permute, cuda concat

* add use cuda option for preprocessor

* ppyoloe use cuda normalize

* ppseg use cuda normalize

* add proclib cuda in processor base

* ppcls add use cuda preprocess api

* ppcls preprocessor set gpu id

* fix pybind

* refine ppcls preprocessing use gpu logic

* fdtensor device id is -1 by default

* refine assert message

Co-authored-by: heliqi &lt;1101791222@qq.com&gt;

* [Doc] Fix dead links (#584)

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* Develop (#13)

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

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* 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

* add python comments for external models

* modify resnet c++ comments

* modify C++ comments for external models

* modify python comments and add result class comments

* fix comments compile error

* modify result.h comments

* deadlink check

* deadlink check

* deadlink check

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

* [Bug Fix] Fix preprocessor pybind api bug (#585)

* Fix preprocessor pybind api bug

* Update fd_tensor.cc

* [Android] Update Android SDK usage docs (#586)

* [FlyCV] Add global SetProcLibCpuNumThreads method

* [Android] Support segmentation and facedet in Android

* [Android] add JNI instance check to j_runtime_option_obj

* [Model] fixed ppseg flycv resize error

* [FlyCV] fix FlyCV resize flags

* [cmake] remove un-need lite compile option

* [Android] add PaddleSegModel JNI and fix some bugs

* [Android] bind PaddleSegModel via JNI

* [Android] bind VisSegmentation via JNI

* [Android] bind YOLOv5Face and SCRFD via JNI

* [Android] fix NewJavaFaceDetectionResultFromCxx error

* [Android] remove un-need option in Java RuntimeOption

* [Android] fixed OcrMainActivity setting errors

* [Android] Update Android SDK usage docs

* [Android] Update Android SDK usage docs

* Update PULL_REQUEST_TEMPLATE.md

* polish build docs

* [Android] fix JNI OCRResult allocate errors (#588)

* [FlyCV] Add global SetProcLibCpuNumThreads method

* [Android] Support segmentation and facedet in Android

* [Android] add JNI instance check to j_runtime_option_obj

* [Model] fixed ppseg flycv resize error

* [FlyCV] fix FlyCV resize flags

* [cmake] remove un-need lite compile option

* [Android] add PaddleSegModel JNI and fix some bugs

* [Android] bind PaddleSegModel via JNI

* [Android] bind VisSegmentation via JNI

* [Android] bind YOLOv5Face and SCRFD via JNI

* [Android] fix NewJavaFaceDetectionResultFromCxx error

* [Android] remove un-need option in Java RuntimeOption

* [Android] fixed OcrMainActivity setting errors

* [Android] Update Android SDK usage docs

* [Android] Update Android SDK usage docs

* [Android] fix JNI OCRResult allocate errors

* [Other] Support batch eval for detection (#587)

* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* [Model] Refactor YOLOv5 module (#562)

* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&amp;&amp;reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

Co-authored-by: Jason &lt;928090362@qq.com&gt;
Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Model] Refactor PaddleDetection module (#575)

* Add namespace for functions

* Refactor PaddleDetection module

* finish all the single image test

* Update preprocessor.cc

* fix some litte detail

* add python api

* Update postprocessor.cc

* add more tests

* [Benchmark] Add benchmark for ernie sequence classification (#444)

* Add benchmark for ernie sequence classification

* Add pretty print

* Update benchmark of ernie

* get_table -&gt; get_statistics_table

* add comments

* Update the output

* Add cpu gpu memory statitis

* Add gpu utilization sampling

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* Update jetson.md

* [Android] Add classification app examples (#590)

* 1.Classification Code submission;
2.Specification code format.

* Specification code format.

* Update strings.xml

Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;

* [Bug Fix] fix import download module error in python3.6 (#591)

fix import download module error in python3.6

* [Bug Fix] Fixed MattingResult bug (#593)

* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* [Android] Run button shutter in sub Ui Thread (#598)

* [Backend] fix lite backend save model error

* [Backend] fixed typos

* [FlyCV] optimize the integration of FlyCV

* [cmake] close some tests options

* [cmake] close some test option

* [FlyCV] remove un-need warnings

* [FlyCV] remove un-need GetMat method

* [FlyCV] optimize FlyCV codes

* [cmake] remove un-need cmake function in examples/CMakelists

* [cmake] support gflags for Android

* [Android] Run button shutter in sub Ui Thread

* [Android] Update CameraSurfaceView

* [Serving]Update images version to 0.6.0  (#594)

* serving images update to 0.6

* serving images update to 0.6

* serving images update to 0.6

* [Doc] Update Android SDK usage docs (#605)

* [Backend] fix lite backend save model error

* [Backend] fixed typos

* [FlyCV] optimize the integration of FlyCV

* [cmake] close some tests options

* [cmake] close some test option

* [FlyCV] remove un-need warnings

* [FlyCV] remove un-need GetMat method

* [FlyCV] optimize FlyCV codes

* [cmake] remove un-need cmake function in examples/CMakelists

* [cmake] support gflags for Android

* [Android] Run button shutter in sub Ui Thread

* [Android] Update CameraSurfaceView

* [Android] Update Android SDK usage docs

* [Bug Fix]  fix import error in python3.6 (#608)

fix import error in python3.6

* [Model] Add PIPNet and FaceLandmark1000 Support  (#548)

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* Develop (#13)

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

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* 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

* add python comments for external models

* modify resnet c++ comments

* modify C++ comments for external models

* modify python comments and add result class comments

* fix comments compile error

* modify result.h comments

* c++ version for FaceLandmark1000

* add pipnet land1000 sigle test and python code

* fix facelandmark1000 sigle test

* fix python examples for PIPNet and FaceLandmark1000

* fix examples links for PIPNet and FaceLandmark1000

* modify test_vision_colorspace_convert.cc

* modify facealign readme

* retrigger ci

* modify README

* test ci

* fix download_prebuilt_libraries.md

* fix download_prebuilt_libraries.md

* modify for comments

* modify supported_num_landmarks

* retrigger ci

* check code style

* check code style

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

* modify docs

* Update download_prebuilt_libraries.md

* [Android] Add facedet Android app example (#614)

* [Backend] fix lite backend save model error

* [Backend] fixed typos

* [FlyCV] optimize the integration of FlyCV

* [cmake] close some tests options

* [cmake] close some test option

* [FlyCV] remove un-need warnings

* [FlyCV] remove un-need GetMat method

* [FlyCV] optimize FlyCV codes

* [cmake] remove un-need cmake function in examples/CMakelists

* [cmake] support gflags for Android

* [Android] Run button shutter in sub Ui Thread

* [Android] Update CameraSurfaceView

* [Android] Update Android SDK usage docs

* [Android] Add facedet Android app example

* [Bug Fix] fix FastDeploy.cmake.in errors for Android (#616)

* [Backend] fix lite backend save model error

* [Backend] fixed typos

* [FlyCV] optimize the integration of FlyCV

* [cmake] close some tests options

* [cmake] close some test option

* [FlyCV] remove un-need warnings

* [FlyCV] remove un-need GetMat method

* [FlyCV] optimize FlyCV codes

* [cmake] remove un-need cmake function in examples/CMakelists

* [cmake] support gflags for Android

* [Android] Run button shutter in sub Ui Thread

* [Android] Update CameraSurfaceView

* [Android] Update Android SDK usage docs

* [Android] Add facedet Android app example

* [cmake] fix FastDeploy.cmake.in errors for Android

* [Doc] update SetProcLibCpuNumThreads API doc

* Update README_CN.md

* Update README_EN.md

* [Bug Fix] fix CopyShutterBitmap and async camera pause (#617)

* [Backend] fix lite backend save model error

* [Backend] fixed typos

* [FlyCV] optimize the integration of FlyCV

* [cmake] close some tests options

* [cmake] close some test option

* [FlyCV] remove un-need warnings

* [FlyCV] remove un-need GetMat method

* [FlyCV] optimize FlyCV codes

* [cmake] remove un-need cmake function in examples/CMakelists

* [cmake] support gflags for Android

* [Android] Run button shutter in sub Ui Thread

* [Android] Update CameraSurfaceView

* [Android] Update Android SDK usage docs

* [Android] Add facedet Android app example

* [cmake] fix FastDeploy.cmake.in errors for Android

* [Doc] update SetProcLibCpuNumThreads API doc

* [Bug Fix] fix CopyShutterBitmap and async camera pause

* Fix precision diff for osx-arm64

* [Serving]support uie model (#599)

* serving support uie model

* serving support uie model

* delete comment

* Update README_EN.md

* [Android] Add PaddleSeg Android app example   (#620)

[Android] Add PaddleSeg Android app example

* [Backend] Support Intel GPU with OpenVINO (#472)

* Update ov_backend.cc

* Update ov_backend.cc

* support set openvino device

* [Serving]ppcls preprocessor support gpu (#615)

* serving ppcls support gpu

* serving ppcls preprocessor use cpu

* [Model] Add move assignment for DetectionResult (#600)

* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* [Android] Configure face recognition and segmentation details page (#619)

* 1.Classification Code submission;
2.Specification code format.

* Specification code format.

* Update strings.xml

* 1.Display ocr, detection and classification results.
2.Specification code format.

* Configure face recognition and semantic segmentation details page.

Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;

* [Doc] Fix ResNet PIPNet and Facelandmark1000 comments (#622)

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* Develop (#13)

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

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* 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

* add python comments for external models

* modify resnet c++ comments

* modify C++ comments for external models

* modify python comments and add result class comments

* fix comments compile error

* modify result.h comments

* fix resnet, pipnet and facelandmark1000 comments

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

* [Doc] update version in docs (#623)

update version in docs

* [Bug Fix] fix android app detail page errors (#624)

* move tests

* [Bug Fix] fix realtime camera mode and shutter (#625)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Model] Refactor YOLOv7 module (#611)

* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&amp;&amp;reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

* refactor yolov7

* add yolov7 testcase

* rm resize_after_load and add is_scale_up

* fixed bug

* set multi_label true

Co-authored-by: Jason &lt;928090362@qq.com&gt;

* [Bug Fix] fix AllocateFaceDetectionResultFromJava error (#628)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Model] change ocr pre and post (#568)

* change ocr pre and post

* add pybind

* change ocr

* fix bug

* fix bug

* fix bug

* fix bug

* fix bug

* fix bug

* fix copy bug

* fix code style

* fix bug

* add new function

* fix windows ci bug

* [Other] Update detection example codes using download_model api  (#613)

update detection example

* Fix a typing error (#633)

* Update fastdeploy_init.sh

* Update fastdeploy_init.sh

* Update fastdeploy_init.sh

* Update README_CN.md

* [Bug Fix] fix camera preview size setting problem (#638)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Bug Fix] fix camera preview size setting problem

* [Model] use uint8 buffer instead of fp32 in ppseg postprocess

* [Model] revert changes in ppseg

* [Model] revert postprocess changes in ppseg

* Update README_EN.md

* Update README_EN.md

* [Model] add vsr serials models (#518)

* [Model] add vsr serials models

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* [Model] add vsr serials models

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* fix build problem

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* fix code style

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* modify according to review suggestions

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* modify vsr trt example

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;

* update sr directory

* fix BindPPSR

* add doxygen comment

* add sr unit test

* update model file url

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;
Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Tools] Add x2paddle tool (#631)

* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* Update README_EN.md

* [Model] Add Picodet RKNPU2 (#635)

* * 更新picodet cpp代码

* * 更新文档
* 更新picodet cpp example

* * 删除无用的debug代码
* 新增python example

* * 修改c++代码

* * 修改python代码

* * 修改postprocess代码

* 修复没有scale_factor导致的bug

* 修复错误

* 更正代码格式

* 更正代码格式

* [Other] faster_tokenizer-&gt;fast_tokenizer (#636)

* faster_tokenizer-&gt;fast_tokenizer

* ErnieFasterTokenizer-&gt;ErnieFastTokenizer

* update the fastdeploy_init

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* Remove static libraries while building

* [Android] add fastdeploy android sdk download task (#646)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Bug Fix] fix camera preview size setting problem

* [Model] use uint8 buffer instead of fp32 in ppseg postprocess

* [Model] revert changes in ppseg

* [Model] revert postprocess changes in ppseg

* [Android] add fastdeploy android sdk download task

* [Bug Fix] Fix PPOCRv2 python example (#645)

* Imporve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Make all the model links come from PaddleOCR

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add comments to create API docs

* Improve OCR comments

* Rename OCR and add comments

* Make sure previous python example works

* Make sure previous python example works

* Fix Rec model bug

* Fix Rec model bug

* Fix rec model bug

* Add SetTrtMaxBatchSize function for TensorRT

* Add SetTrtMaxBatchSize Pybind

* Add set_trt_max_batch_size python function

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Fix PPOCRv2 python example

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Other] Remove static libraries while building (#644)

Remove static libraries while building

* Delete Doxyfile

* [Android] Remove redundant code for segmentation app (#642)

Remove redundant code for segmentation.

Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;

* [Bug Fix] fix yolov5face scale error in small image (#649)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Bug Fix] fix camera preview size setting problem

* [Model] use uint8 buffer instead of fp32 in ppseg postprocess

* [Model] revert changes in ppseg

* [Model] revert postprocess changes in ppseg

* [Android] add fastdeploy android sdk download task

* [Bug Fix] fix yolov5face scale error in small image

* [Bug Fix] fix cosine_similarity error in examples (#648)

cosine_similarity is error

余弦相似度计算错误
np.linalg.norm 二范数 已经开过根号

Co-Authored-By: Chris Kong &lt;chriskong93@163.com&gt;

* Fix wrong api in fastdeploy model

* Fix wrong api in fastdeploy model

* Fix build error on Windows (#653)

* [Doc] Fix the version statement for all example docs (#654)

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* Develop (#13)

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

* fix some usage problem in linux

* Fix compile problem

Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;

* 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 &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: huangjianhui &lt;852142024@qq.com&gt;

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

* 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

* add python comments for external models

* modify resnet c++ comments

* modify C++ comments for external models

* modify python comments and add result class comments

* fix comments compile error

* modify result.h comments

* modify examples' cpp docs for all models

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

* [cmake] change -Os flag -&gt; Ofast to boost performance on Android (#652)

- change -Os flag -&gt; Ofast to boost performance on Android

* [Doc] Update Android SDK usage docs (#657)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Bug Fix] fix camera preview size setting problem

* [Model] use uint8 buffer instead of fp32 in ppseg postprocess

* [Model] revert changes in ppseg

* [Model] revert postprocess changes in ppseg

* [Android] add fastdeploy android sdk download task

* [Bug Fix] fix yolov5face scale error in small image

* [Doc] Update Android SDK docs

* [Doc] Update Android SDK usage docs

* [Doc] Update download_prebuilt_libraries.md (#659)

Update download_prebuilt_libraries.md

* [Serving] add ppdet serving example (#641)

* serving support ppdet

* Update README.md

update ppadet/README

* [Model] Optimize RVM Preprocess (#658)

* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&amp;&amp;reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

* refactor yolov7

* add yolov7 testcase

* rm resize_after_load and add is_scale_up

* fixed bug

* set multi_label true

* optimize rvm preprocess

Co-authored-by: Jason &lt;928090362@qq.com&gt;
Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Doc] Update paddledetection/android app example (#663)

* [Bug Fix] fix android app detail page errors

* [Android] fix realtime camera mode and shutter

* [Bug Fix] fix AllocateSegmentationResultFromJava error

* [Bug Fix] fix camera preview size setting problem

* [Model] use uint8 buffer instead of fp32 in ppseg postprocess

* [Model] revert changes in ppseg

* [Model] revert postprocess changes in ppseg

* [Android] add fastdeploy android sdk download task

* [Bug Fix] fix yolov5face scale error in small image

* [Doc] Update Android SDK docs

* [Doc] Update Android SDK usage docs

* [Android] Update paddledetection/android app example

* [Doc] Add Preprocessor&amp;&amp;Postprocessor API (#665)

* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* add http params in serving/scripts/build.sh (#661)

* add http params in serving/scripts/build.sh

* Update build.sh

Co-authored-by: heliqi &lt;1101791222@qq.com&gt;

* [Quantization] Improve the usage of FastDeploy tools. (#660)

* Add PaddleOCR Support

* Add PaddleOCR Support

* Add PaddleOCRv3 Support

* Add PaddleOCRv3 Support

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Add PaddleOCRv3 Support

* Add PaddleOCRv3 Supports

* Add PaddleOCRv3 Suport

* Fix Rec diff

* Remove useless functions

* Remove useless comments

* Add PaddleOCRv2 Support

* Add PaddleOCRv3 &amp; PaddleOCRv2 Support

* remove useless parameters

* Add utils of sorting det boxes

* Fix code naming convention

* Fix code naming convention

* Fix code naming convention

* Fix bug in the Classify process

* Imporve OCR Readme

* Fix diff in Cls model

* Update Model Download Link in Readme

* Fix diff in PPOCRv2

* Improve OCR readme

* Imporve OCR readme

* Improve OCR readme

* Improve OCR readme

* Imporve OCR readme

* Improve OCR readme

* Fix conflict

* Add readme for OCRResult

* Improve OCR readme

* Add OCRResult readme

* Improve OCR readme

* Improve OCR readme

* Add Model Quantization Demo

* Fix Model Quantization Readme

* Fix Model Quantization Readme

* Add the function to do PTQ quantization

* Improve quant tools readme

* Improve quant tool readme

* Improve quant tool readme

* Add PaddleInference-GPU for OCR Rec model

* Add QAT method to fastdeploy-quantization tool

* Remove examples/slim for now

* Move configs folder

* Add Quantization Support for Classification Model

* Imporve ways of importing preprocess

* Upload YOLO Benchmark on readme

* Upload YOLO Benchmark on readme

* Upload YOLO Benchmark on readme

* Improve Quantization configs and readme

* Add support for multi-inputs model

* Add backends and params file for YOLOv7

* Add quantized model deployment support for YOLO series

* Fix YOLOv5 quantize readme

* Fix YOLO quantize readme

* Fix YOLO quantize readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Improve quantize YOLO readme

* Fix bug, change Fronted to ModelFormat

* Change Fronted to ModelFormat

* Add examples to deploy quantized paddleclas models

* Fix readme

* Add quantize Readme

* Add quantize Readme

* Add quantize Readme

* Modify readme of quantization tools

* Modify readme of quantization tools

* Improve quantization tools readme

* Improve quantization readme

* Improve PaddleClas quantized model deployment  readme

* Add PPYOLOE-l quantized deployment examples

* Improve quantization tools readme

* Improve Quantize Readme

* Fix conflicts

* Fix conflicts

* improve readme

* Improve quantization tools and readme

* Improve quantization tools and readme

* Add quantized deployment examples for PaddleSeg model

* Fix cpp readme

* Fix memory leak of reader_wrapper function

* Fix model file name in PaddleClas quantization examples

* Update Runtime and E2E benchmark

* Update Runtime and E2E benchmark

* Rename quantization tools to auto compression tools

* Remove PPYOLOE data when deployed on MKLDNN

* Fix readme

* Support PPYOLOE with OR without NMS and update readme

* Update Readme

* Update configs and readme

* Update configs and readme

* Add Paddle-TensorRT backend in quantized model deploy examples

* Support PPYOLOE+ series

* Add reused_input_tensors for PPYOLOE

* Improve fastdeploy tools usage

* improve fastdeploy tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* remove modify

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Improve fastdeploy auto compression tool

* Remove extra requirements for fd-auto-compress package

* Imporve fastdeploy-tools package

* Install fastdeploy-tools package when build fastdeploy-python

* Imporve quantization readme

* [Bug Fix] Fix PPOCR dynamic input shape bug (#667)

* Imporve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Make all the model links come from PaddleOCR

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add comments to create API docs

* Improve OCR comments

* Rename OCR and add comments

* Make sure previous python example works

* Make sure previous python example works

* Fix Rec model bug

* Fix Rec model bug

* Fix rec model bug

* Add SetTrtMaxBatchSize function for TensorRT

* Add SetTrtMaxBatchSize Pybind

* Add set_trt_max_batch_size python function

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Fix PPOCRv2 python example

* Fix PPOCR dynamic input shape bug

* Remove useless code

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* Update model.h

* [Functions] Add +-*/ operators and reshape for FDTensor (#655)

* Add +-*/ functions

* Add same dims test case for operations

* add broadcast 0

* Add broadcast dim2 testcase

* Add broadcast dim3 and dim4 testcase

* Add +-*/ operators

* Add mixed operation

* refresh code style

* Add reshape op

* update code style

* Update setup.py

* [Android] Add CxxBuffer to native and Java PaddleSegModel (#677)

[Android] Add CxxBuffer to native PaddleSegModel

* [Android] Add PaddleSeg android app example (#678)

* [Android] Add CxxBuffer to native PaddleSegModel

* [Android] Add PaddleSeg android app example

* Add maximum functions

* Add sqrt, exp, round, log functions

* Add clip function

* [Android] Add SCRFD android app example (#682)

* [Android] Add CxxBuffer to native PaddleSegModel

* [Android] Add PaddleSeg android app example

* [Android] Add SCRFD android app example

* [Doc] fix typos

* [Android] revert camera setting changes

* Update README_EN.md

* Update README_EN.md

* Update README_CN.md

* [Backend] Add ORT CPU and CUDA kernel for adaptive_pool OP (#609)

* add ORT CPU and CUDA kernel for adaptive_pool

* update code

* update paddle2onnx version

* fix serving/scripts/build.sh for docker build CI task (#688)

* fix serving/scripts/build.sh for docker build CI task

* Update build.sh

Co-authored-by: heliqi &lt;1101791222@qq.com&gt;

* [Android] Add classification and ocr app examples (#676)

* Remove redundant code for segmentation.

* Classification Documentation and example improvement.

* Ocr Documentation and example improvement.

Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;

* Update py_run.sh

* Add threshold for osx-arm64

* [Bug Fix] Fix bugs in publish task scripts (#693)

* Fix release_task cpp_run.sh

 Author:    felixhjh &lt;852142024@qq.com&gt;
 Date:      Thu Nov 10 07:26:48 2022 +0000

* Add option for infer_ppyoloe.cc

  author:    felixhjh &lt;852142024@qq.com&gt;

* Fix bug in release task scripts

* Add error check function

* Format code

* Add new download dir for release version

* Fix precision diff for osx-arm64

Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming2.bjyz.baidu.com&gt;

* [Bug Fix] fixed ppdet postprocess empty result error (#691)

* [Android] Add CxxBuffer to native PaddleSegModel

* [Android] Add PaddleSeg android app example

* [Android] Add SCRFD android app example

* [Doc] fix typos

* [Android] revert camera setting changes

* [Bug Fix] fixed ppdet postprocess empty result error

* [Bug Fix] Fix PPOCR bug when cls model is not used (#695)

* Imporve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Make all the model links come from PaddleOCR

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add comments to create API docs

* Improve OCR comments

* Rename OCR and add comments

* Make sure previous python example works

* Make sure previous python example works

* Fix Rec model bug

* Fix Rec model bug

* Fix rec model bug

* Add SetTrtMaxBatchSize function for TensorRT

* Add SetTrtMaxBatchSize Pybind

* Add set_trt_max_batch_size python function

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Fix PPOCRv2 python example

* Fix PPOCR dynamic input shape bug

* Remove useless code

* Fix PPOCR bug

Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Bug Fix] add enableCamera method to fix app crash (#696)

* [Android] Add CxxBuffer to native PaddleSegModel

* [Android] Add PaddleSeg android app example

* [Android] Add SCRFD android app example

* [Doc] fix typos

* [Android] revert camera setting changes

* [Bug Fix] fixed ppdet postprocess empty result error

* [Android] add enableCamera method to fix app crash

* Update README_CN.md

* Update issue templates

* Update issue templates

* Update 报告issue.md

* Update 报告issue.md

* Create other.md

* add tile

* Add tile unittest

* Add linspace

* Add abs functions

* Add cumprod function

* Add split functions

* update args

* [Model] Optimizer RVM Postprocess (#679)

* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&amp;&amp;reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

* refactor yolov7

* add yolov7 testcase

* rm resize_after_load and add is_scale_up

* fixed bug

* set multi_label true

* optimize rvm preprocess

* optimizer rvm postprocess

* fixed bug

* deal with comments

Co-authored-by: Jason &lt;928090362@qq.com&gt;
Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;

* [Serving]add paddledetection serving README (#702)

add paddledetection serving README

* Remove root commit author

* Change release task demo image url

Signed-off-by: ChaoII &lt;849453582@qq.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming2.bjyz.baidu.com&gt;
Co-authored-by: Jack Zhou &lt;zhoushunjie@baidu.com&gt;
Co-authored-by: yunyaoXYY &lt;109218879+yunyaoXYY@users.noreply.github.com&gt;
Co-authored-by: Wang Xinyu &lt;wangxinyu_es@163.com&gt;
Co-authored-by: heliqi &lt;1101791222@qq.com&gt;
Co-authored-by: ziqi-jin &lt;67993288+ziqi-jin@users.noreply.github.com&gt;
Co-authored-by: Jason &lt;jiangjiajun@baidu.com&gt;
Co-authored-by: root &lt;root@bjyz-sys-gpu-kongming3.bjyz.baidu.com&gt;
Co-authored-by: DefTruth &lt;31974251+DefTruth@users.noreply.github.com&gt;
Co-authored-by: Jason &lt;928090362@qq.com&gt;
Co-authored-by: WJJ1995 &lt;wjjisloser@163.com&gt;
Co-authored-by: Winter &lt;1558270516@qq.com&gt;
Co-authored-by: chenjian &lt;chenjian26@baidu.com&gt;
Co-authored-by: Thomas Young &lt;35565423+HexToString@users.noreply.github.com&gt;
Co-authored-by: jm12138 &lt;2286040843@qq.com&gt;
Co-authored-by: Xiue &lt;30972246+Xiue233@users.noreply.github.com&gt;
Co-authored-by: leiqing &lt;54695910+leiqing1@users.noreply.github.com&gt;
Co-authored-by: ChaoII &lt;849453582@qq.com&gt;
Co-authored-by: Zheng_Bicheng &lt;58363586+Zheng-Bicheng@users.noreply.github.com&gt;
Co-authored-by: Chris Kong &lt;609027949@qq.com&gt;
Co-authored-by: Chris Kong &lt;chriskong93@163.com&gt;
Co-authored-by: Zeref996 &lt;53218160+Zeref996@users.noreply.github.com&gt;
Co-authored-by: yeliang2258 &lt;30516196+yeliang2258@users.noreply.github.com&gt;
diff --git a/tests/release_task/cpp_run.bat b/tests/release_task/cpp_run.bat
@@ -30,7 +30,7 @@ if "%DEVICE%" == "gpu" (
 echo "CPP_FASTDEPLOY_PACKAGE: " %CPP_FASTDEPLOY_PACKAGE%
 echo "RUN_CASES" %RUN_CASES%
 
-python -c "import wget; wget.download('https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg')"
+python -c "import wget; wget.download('https://fastdeploy.bj.bcebos.com/resource/images/000000014439.jpg')"
 python -c "import wget; wget.download('https://bj.bcebos.com/paddlehub/fastdeploy/release_task_groud_truth_result.txt')"
 python -c "from download import *; download_and_decompress('https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz', './')"
 
diff --git a/tests/release_task/cpp_run.sh b/tests/release_task/cpp_run.sh
@@ -22,7 +22,7 @@ LINUX_AARCH_CPU_CASE=('ort')
 MACOS_INTEL_CPU_CASE=('ort' '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://fastdeploy.bj.bcebos.com/resource/images/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
diff --git a/tests/release_task/py_run.bat b/tests/release_task/py_run.bat
@@ -27,7 +27,7 @@ if "%DEVICE%" == "gpu" (
 echo "PY_FASTDEPLOY_PACKAGE: " %PY_FASTDEPLOY_PACKAGE%
 echo "RUN_CASES" %RUN_CASES%
 
-python -c "import wget; wget.download('https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg')"
+python -c "import wget; wget.download('https://fastdeploy.bj.bcebos.com/resource/images/000000014439.jpg')"
 python -c "import wget; wget.download('https://bj.bcebos.com/paddlehub/fastdeploy/release_task_groud_truth_result.txt')"
 python -c "from download import *; download_and_decompress('https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz', './')"
 
diff --git a/tests/release_task/py_run.sh b/tests/release_task/py_run.sh
@@ -17,7 +17,7 @@ LINUX_AARCH_CPU_CASE=('ort')
 MACOS_INTEL_CPU_CASE=('ort' '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://fastdeploy.bj.bcebos.com/resource/images/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=$CURRENT_DIR/000000014439.jpg
@@ -63,7 +63,6 @@ do
                fi
        fi
        if [ "$DEVICE" = "gpu" ];then
-
 	       if [ "$backend" = "trt" ];then
                        python infer_ppyoloe.py --model_dir $MODEL_PATH --image $IMAGE_PATH --device gpu --backend $backend >> py_trt_result.txt
                        python $COMPARE_SHELL --gt_path $GROUND_TRUTH_PATH --result_path py_trt_result.txt --platform $PLATFORM --device trt
@@ -86,4 +85,3 @@ else
        cat $res_file
        exit -1
 fi
-
