Commit Graph

1237 Commits

Author SHA1 Message Date
leiqing
3d68f5660a Update how_to_use_sdk_on_windows.md 2022-09-13 21:09:26 +08:00
Jack Zhou
54bea3160d Add uie python api (#214)
* add uie pybind

* Add uie result pybind

* Add uie python class

* fix UIEModel pythonargs

* Add schema node pybind

* remove uie print

* Fix cpp build ci
2022-09-13 19:03:06 +08:00
yunyaoXYY
82580ac11e Improve OCR readme (#220)
* 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 & 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

* Update ppocr_system_v2.cc

* Update ppocr_system_v2.cc

Co-authored-by: Jason <928090362@qq.com>
2022-09-13 17:10:45 +08:00
ChaoII
f17fddbfdd Merge branch 'PaddlePaddle:develop' into develop 2022-09-13 09:20:31 +08:00
leiqing
6d7b50b94e Update README_CN.md 2022-09-12 09:08:13 +08:00
leiqing
6c39c83f2f Update README.md 2022-09-12 09:07:40 +08:00
Jason
84ebc44628 Update README.md 2022-09-09 18:51:19 +08:00
leiqing
cb33b32751 Update README.md 2022-09-09 15:43:50 +08:00
ChaoII
40013ef24c Merge branch 'PaddlePaddle:develop' into develop 2022-09-09 14:00:10 +08:00
ChaoII
49ebd94ef8 update reademe_cn link (#211) 2022-09-09 13:22:45 +08:00
huangjianhui
4361d2021e Update ppdet example code (#210) 2022-09-09 13:20:33 +08:00
leiqing
ea27f089a6 Update README.md 2022-09-09 10:34:53 +08:00
leiqing
85eec16549 Update README.md 2022-09-09 10:25:04 +08:00
leiqing
1365bd4e11 Update README.md 2022-09-09 10:18:32 +08:00
leiqing
53be2f8d94 Update README.md 2022-09-09 10:16:49 +08:00
ChaoII
2a2b09ca92 update reademe_cn link 2022-09-09 08:50:03 +08:00
leiqing
fa955665c3 Add files via upload 2022-09-09 00:33:12 +08:00
leiqing
ba546f1f94 Add files via upload 2022-09-08 23:43:39 +08:00
leiqing
3aa63d5ee5 Add files via upload 2022-09-08 23:33:03 +08:00
leiqing
7efdfe698f Update README.md 2022-09-08 23:31:26 +08:00
leiqing
fcb43fff54 Update README.md 2022-09-08 23:30:08 +08:00
leiqing
643e6c5efc Add files via upload 2022-09-08 23:29:31 +08:00
leiqing
d7e4f200bb Add files via upload 2022-09-08 23:28:43 +08:00
leiqing
0ec57f65cb Update README.md 2022-09-08 23:27:02 +08:00
leiqing
ec5d299823 Update README.md 2022-09-08 23:25:55 +08:00
leiqing
ec1f2eeccd Add files via upload 2022-09-08 23:24:57 +08:00
leiqing
66006920e5 Add files via upload 2022-09-08 23:22:24 +08:00
leiqing
01aad72828 Update README.md 2022-09-08 23:20:23 +08:00
leiqing
8613a8a67d Update README.md 2022-09-08 23:12:28 +08:00
leiqing
9955e3a2ac Update README.md 2022-09-08 22:40:13 +08:00
leiqing
4e39e1ce34 Rename README_ch.md to README_CN.md 2022-09-08 22:39:27 +08:00
leiqing
25d2288b77 Create README.md
add readme_en
2022-09-08 22:31:56 +08:00
leiqing
3d7bdbb687 Update and rename README.md to README_ch.md 2022-09-08 21:19:40 +08:00
ziqi-jin
ff8a0ca4c4 Fix ResizeByShort function (#208)
* 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

* fix ResizeByLong Fuction

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>
2022-09-08 18:58:09 +08:00
Jack Zhou
eee5edad68 Fix openvino python lib error in windows (#207)
* Fix openvino lib import error in linux

* Fix windows legal file

* Revert "Fix windows legal file"

This reverts commit 1b6f6d798b.

* Revert "Fix openvino lib import error in linux"

This reverts commit fc5794eff8.

* Fix windows legal file
2022-09-08 18:57:34 +08:00
Jason
46a0b62ea5 Support PPYOLOE plus model (#205) 2022-09-08 18:57:12 +08:00
heliqi
4d1f264d01 FDTensor support GPU device (#190)
* fdtensor support GPU

* TRT backend support GPU FDTensor

* FDHostAllocator add FASTDEPLOY_DECL

* fix FDTensor Data

* fix FDTensor dtype

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-09-08 16:53:08 +08:00
Jack Zhou
bc8e9e4dae Fix openvino libiomp.so import error in linux (#204)
Fix openvino lib import error in linux
2022-09-08 16:35:35 +08:00
Jack Zhou
ea68104216 Reconstruct uie structure (#191)
* Reconstruct the uie model

* Abstract ConstructChildRelations

* Use string and vector args instead of SchemaNode
2022-09-08 14:20:31 +08:00
Jack Zhou
b2c724b641 Merge pull request #202 from PaddlePaddle/fix_ov_order
Fix inputs/outputs order of openvino backend
2022-09-08 14:13:54 +08:00
jiangjiajun
35433ae2ce fix inputs/outputs order of openvino backend 2022-09-08 05:29:51 +00:00
Jason
c6db239313 Update CPP_prebuilt_libraries.md 2022-09-08 10:34:37 +08:00
Jason
e5123bc9f4 Update how_to_use_sdk_on_windows.md 2022-09-08 10:32:41 +08:00
leiqing
945ba92a2e Create README.md 2022-09-07 17:55:51 +08:00
leiqing
6c6aaa3df6 Delete README.md 2022-09-07 17:44:13 +08:00
leiqing
903f9d4656 Delete README.md 2022-09-07 17:42:22 +08:00
leiqing
8a9f4b869c Add files via upload 2022-09-07 17:42:05 +08:00
leiqing
fa14dbe55f Update install_python_sdk.md 2022-09-07 17:39:24 +08:00
leiqing
3d9486ae5d Update install_cpp_sdk.md 2022-09-07 17:38:47 +08:00
leiqing
ff5e085da5 Add files via upload 2022-09-07 17:26:40 +08:00