apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-01 04:12:58 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity
2,780 Commits 19 Branches 8 Tags
85a78d695d5a588131b0b25e243a7e9ff3a90c9c
Commit Graph

2780 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jason
e91cfc9e43 Update __init__.py 2022-08-10 13:59:09 +08:00
leiqing
0e710a3087 Update README.md 2022-08-10 13:46:09 +08:00
Jason
b480a03cb4 Fix import error (#90) 
Update __init__.py
 2022-08-10 13:38:41 +08:00
Jason
fec7ecaa3b Delete config.h 2022-08-10 12:22:58 +08:00
Jason
309a1397f2 Update vision_pybind.cc 2022-08-10 12:22:45 +08:00
leiqing
2f7e5f4b9e Update requirements.md 2022-08-10 12:02:49 +08:00
jiangjiajun
90a46af18e Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into develop 2022-08-10 03:52:00 +00:00
jiangjiajun
1a7bdc32ad add prebuilt library doc 2022-08-10 03:51:28 +00:00
leiqing
ecdb28335e Update README.md 2022-08-10 11:44:51 +08:00
leiqing
7069e9a196 Update README.md 2022-08-10 11:44:21 +08:00
leiqing
bef3d42068 Update README.md 2022-08-10 11:39:41 +08:00
leiqing
25eb275edc Update README.md 2022-08-10 11:34:33 +08:00
leiqing
a1c64cd3b4 Update README.md 2022-08-10 11:29:54 +08:00
leiqing
de730742c5 Update README.md 2022-08-10 11:26:46 +08:00
leiqing
c54714fa7f Update README.md 2022-08-10 11:25:47 +08:00
leiqing
206971ba0a Update README.md 2022-08-10 11:25:15 +08:00
Jason
7c0949c0da Update README.md 2022-08-10 11:05:26 +08:00
jiangjiajun
72eb130193 add csrc code 2022-08-10 02:52:36 +00:00
Jason
22ca63982b Refine code structure (#89) 
* refine code structure

* refine code structure
 2022-08-10 10:50:22 +08:00
Jack Zhou
c7d37b6732 Add reduce functions for FDTensor (#81) 
* Add eigen tensor structure

* Add Reduce function

* Add cpp unittest framework

* Add reduce function unittest

* Add pr template

* Add comments and docs for reduce function

* Fix typo

* Add ENABLE_FDTENSOR_FUNC macro

* Add Todo comment

* Add CheckData overload

* Fix CheckData overload operator()

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-08-10 10:31:04 +08:00
ziqi-jin
9918374d74 Modify YOLOv7 Infer file and the external model namespace (#87) 
* 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 namespace for yolov5lite

* modify namespace for external detection models

* modify namespace for yolov5lite

* modify namespace for face models

* py namespace for external model

* fix compile error and infer file

* change paddleyolox to yolox

* delete space in cmakelist

* check code specification

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>
 2022-08-10 10:28:07 +08:00
Jason
de2a87a8f2 Refine paddledetection directory (#88) 2022-08-10 10:13:22 +08:00
DefTruth
79120251b7 [fix][backend] fixed backend virtual deconstructor (#84) 
fixed backend virtual deconstructor
 2022-08-10 10:10:37 +08:00
leiqing
74c574a394 Add yolov7 docs (#86) 
* ‘’

* ‘’

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-08-09 20:54:53 +08:00
leiqing
78b0cc56f2 ‘fixed-yolov7-doc’ (#85) 
‘’
 2022-08-09 20:52:58 +08:00
leiqing
36a54f2955 Update requirements.md 2022-08-09 16:34:24 +08:00
Jason
c955d36ab8 Update README.md 2022-08-09 16:19:35 +08:00
Jason
be48c6dc8a Update README.md 2022-08-09 16:18:43 +08:00
leiqing
efdd651771 Update README.md 2022-08-09 14:40:34 +08:00
leiqing
dc8c1f0ce4 Update README.md 2022-08-09 14:39:40 +08:00
leiqing
0e15c5a0ff Update README.md 2022-08-09 14:32:31 +08:00
Jason
1b662e8d1e Update README.md 2022-08-09 14:22:22 +08:00
leiqing
3216912516 Update README.md 2022-08-09 14:22:17 +08:00
Jason
985697c550 Update README.md 2022-08-09 14:21:55 +08:00
Jason
8c8818c48f Add sample doc and example code (#83) 
* modify yolov7 and visualize functions

* Add a sample document and example code

* Delete .README.md.swp

* Update README.md

* Update README.md

* Update README.md
 2022-08-09 14:18:49 +08:00
Jason
b2cd30e64f Modify yolov7 and visualize functions (#82) 
modify yolov7 and visualize functions
 2022-08-09 10:16:41 +08:00
ZeyuChen
36b2bfaa33 Update README 2022-08-09 00:15:36 +08:00
ZeyuChen
57dc2c1ad3 Update README 2022-08-09 00:11:20 +08:00
DefTruth
549050c61f [fix][vision] fixed python instance check error (#80) 2022-08-08 20:17:37 +08:00
Jack Zhou
60ac898ece Use unique_ptr instead of raw pointer (#77) 2022-08-08 19:41:01 +08:00
DefTruth
0e45a7e4aa Add MODNet(Matting) model support (#76) 
* Add MODNet(Matting) model support

* from pre_commit.main import main
 2022-08-08 19:39:59 +08:00
Jason
9c67653e34 support build cpu/gpu package (#75) 
* support build cpu/gpu package

* remove useless modification
 2022-08-08 15:24:36 +08:00
leiqing
0494fdc96b ‘fixed_readme’ (#73) 
‘’
 2022-08-08 14:03:26 +08:00
Jack Zhou
32c2154bbe Unify the data type of tensor shape (#74) 
int32_t->int64_t
 2022-08-08 14:02:56 +08:00
Jack Zhou
0587c4bbac Add const Data of FDTensor (#72) 
* Add const Data of FDTensor

* use SetExternalData instead of memcpy

* Add Softmax

* Add Max

* Add viterbi decode for ernie tokencls
 2022-08-08 08:51:51 +08:00
Jack Zhou
d792af059a Add text examples (#69) 
* Add text init file

* Fix some cmake

* Add TextModel, TextResult, PredictionOption

* Add text preprocessor, postprocessor, pipeline of text model prediction

* remove Text prefix

* Add faster_tokenizer deps

* Add ernie IE examples

* Add eigen computation

* eigen.h->compute.h

* Add python ernie examples

* Fix some comments
 2022-08-05 15:24:02 +08:00
Jason
904f1e198d Merge branch 'new_ppdet1' into develop 2022-08-05 09:43:08 +08:00
Jason
821dc756e6 Add lots of paddle detection models (#67) 
* Fix runtime with python

* Add CenterNet/PicoDet/PPYOLO/PPYOLOv2/YOLOv3

* add more ppdet models

* add model

* fix some usage bugs for detection models
 2022-08-05 09:34:12 +08:00
Jason
fa2fced432 Merge branch 'develop' into new_ppdet1 2022-08-05 09:27:16 +08:00
DefTruth
2f362e1645 Add many face recognition models support (#70) 2022-08-05 09:27:03 +08:00