apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-27 18:41:02 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity
3,104 Commits 21 Branches 8 Tags
56e2d7e6683ecef34684fd07cd49b7adeaa23f5c
Commit Graph

3104 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
heliqi
831ef42207 fix paddle-mkldnn bug (#366) 
* fix input name bug

* fix paddle-mkldnn bug
 2022-10-13 21:37:31 +08:00
Jason
6f497b32f5 Fix error of visualize function (#363) 
Co-authored-by: PaddleCI <paddle_ci@example.com>
 2022-10-13 19:35:11 +08:00
leiqing
94ab801e12 Update jetson.md 2022-10-13 17:49:24 +08:00
leiqing
bc9158b5bf Update gpu.md 2022-10-13 17:49:01 +08:00
leiqing
fda7bc3c7e Update README_CN.md 2022-10-13 17:43:25 +08:00
leiqing
104100ce1f Update README_EN.md 2022-10-13 17:43:01 +08:00
leiqing
27c2e1196c Update cpu.md 2022-10-13 17:39:34 +08:00
leiqing
7904bd1cca Update and rename prebuilt.md to download_prebuilt_libraries.md 2022-10-13 17:35:53 +08:00
leiqing
10e1d7ea98 Update README.md 2022-10-13 17:35:08 +08:00
huangjianhui
8465227839 Update release task script (#359) 
* Update cpp_run.bat

Update wget in bat

* Update py_run.bat

Update wget in bat file

* Update release task bat script && Add download.py

* Update release task script
 2022-10-13 15:39:08 +08:00
yunyaoXYY
c681aaacba Make model link come from PaddleOCR (#350) 
* 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

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-13 11:49:57 +08:00
heliqi
8a3ad3eb43 fix input name bug (#352) 2022-10-13 11:49:27 +08:00
Jason
2c4a555929 Update FastDeploy.cmake.in 2022-10-13 11:23:45 +08:00
Jack Zhou
e268ef08d2 Fix openvino cmake (#348) 
fix openvino
 2022-10-12 21:13:44 +08:00
ziqi-jin
c5446670c9 Modify docs for PP-Matting, change VisMattingAlpha to VisMatting, fix Squeeze function. (#354) 
* 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

* modify PPMatting to PP-Matting, fix squeeze, modify VisMattingAlpha to VisMatting

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>
 2022-10-12 20:36:57 +08:00
Jason
e6f8bd90cf Revert Paddle Inference to No TRT version (#355) 2022-10-12 19:39:37 +08:00
WJJ1995
b557dbc2d8 Add YOLOv5-cls Model (#335) 
* add yolov5cls

* fixed bugs

* fixed bugs

* fixed preprocess bug

* add yolov5cls readme

* deal with comments

* Add YOLOv5Cls Note

* add yolov5cls test

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-12 15:57:26 +08:00
Jason
945e197bd1 Fix bug of get input/output information from PaddleBackend (#339) 
* Fix bug of get input/output information from PaddleBackend

* Support Paddle Inference with TensorRT (#340)

* Fix bug
 2022-10-12 11:37:26 +08:00
huangjianhui
3faaeaea36 Doc (#345) 
* Update docs for wrong path

* Update README.md

* Update README.md

* Update README.md
 2022-10-12 08:56:38 +08:00
Jason
9728e77fd6 Update README_CN.md 2022-10-11 21:33:17 +08:00
Jason
548777a283 Add document describes some tricks while using TensorRT backend (#343) 
* add tensorrt tricks doc

* add quick start
 2022-10-11 21:19:55 +08:00
heliqi
5328fbc861 support build cpu images (#341) 2022-10-11 14:17:27 +08:00
jiangjiajun
ce0e3fc43d update new docs 2022-10-11 06:12:42 +00:00
jiangjiajun
6dfe2e0ed0 update new docs 2022-10-11 06:12:10 +00:00
jiangjiajun
964aaf051c add api docs 2022-10-11 06:01:18 +00:00
Jason
1733a73db9 Update README_CN.md 2022-10-11 13:53:38 +08:00
leiqing
24c5d56737 Update README_CN.md 2022-10-11 11:24:09 +08:00
leiqing
0ada2d7590 Update README_EN.md 2022-10-11 11:23:14 +08:00
Jason
677a7ae45e Update VERSION_NUMBER 2022-10-11 11:11:19 +08:00
Jason
47c4c11a23 Update README_CN.md 2022-10-11 11:04:12 +08:00
Jason
8177b57dbe Update README.md 2022-10-11 10:59:08 +08:00
Jason
05e97fae1b Update README.md 2022-10-11 10:57:21 +08:00
jiangjiajun
c4625a2cb6 add new docs 2022-10-11 02:43:34 +00:00
jiangjiajun
301bb59683 Update new docs 2022-10-11 02:06:36 +00:00
Zheng_Bicheng
9c3ac8f0da [vision] Add AdaFace model support (#301) 
* 新增adaface模型

* 新增adaface模型python代码

* 新增adaface模型example代码

* 删除无用的import

* update

* 修正faceid文档的错误

* 修正faceid文档的错误

* 删除无用文件

* 新增adaface模型paddleinference推理代码,模型文件先提交方便测试后期会删除

* 新增adaface模型paddleinference推理代码,模型文件先提交方便测试后期会删除

* 按照要求修改并跑通cpp example

* 测试python example

* python cpu测试通过，修改了文档

* 修正文档，替换了模型下载地址

* 修正文档

* 修正文档

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-10-11 09:55:18 +08:00
jiangjiajun
a6847c5432 modify new docs 2022-10-10 06:25:46 +00:00
jiangjiajun
0694378e9b remove readthedocs 2022-10-10 06:15:11 +00:00
jiangjiajun
684c46863d update new docs 2022-10-10 06:13:47 +00:00
Jason
cf86c4ed55 Update runtime.h 2022-10-10 13:59:35 +08:00
huangjianhui
1635c5a8b3 Update docs for wrong path (#338) 2022-10-10 13:51:53 +08:00
Jack Zhou
f8cf99d5c8 Add main page of uie (#334) 
Add main page of uie; update uie cpp README
 2022-10-10 10:21:37 +08:00
leiqing
7c2f9ae388 Update README_EN.md 2022-10-09 22:28:20 +08:00
yeliang2258
2a68a23baf Add paddle quantize model support for ORT, TRT and MKLDNN deploy backend (#257) 
* add quantize model support for trt and paddle

* fix bugs

* fix

* update paddle2onnx version

* update version

* add quantize test

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-09 20:00:05 +08:00
yunyaoXYY
ff5e798b7f Add Initialize function to PP-OCR (#326) 
* 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

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-09 17:31:37 +08:00
leiqing
56730a6517 update model list (#333) 
* Update README_CN.md

* Update README_CN.md

* Update README_EN.md
 2022-10-09 11:44:12 +08:00
jiangjiajun
7afcd4b373 Correct PP-Series models' name 2022-10-09 02:49:58 +00:00
Jason
0a0b601853 Integrate FalconCV to boost image preprocessing (#331) 
Remove opencv cuda code
 2022-10-09 10:34:51 +08:00
Jason
5d4372955f Add some comments for python api (#327) 
* Add some comments for python api

* Update setup.py

* Update runtime.py
 2022-10-09 10:05:18 +08:00
heliqi
a3fa5989d2 Fix set_paddle_mkldnn python interface (#328) 
* fd serving add dockerfile

* fix enable_paddle_mkldnn

* delete disable_paddle_mkldnn

* fix python set_paddle_mkldnn

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-08 16:49:40 +08:00
heliqi
d57e997fa0 Fd serving add docker images correlation and docs (#311) 
* fd serving add dockerfile

* fix enable_paddle_mkldnn

* delete disable_paddle_mkldnn

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-10-08 16:08:07 +08:00