Commit Graph

48 Commits

Author SHA1 Message Date
Wang Xinyu c8d6c8244e [Model] Yolov5/v5lite/v6/v7/v7end2end: CUDA preprocessing (#370)
* add yolo cuda preprocessing

* cmake build cuda src

* yolov5 support cuda preprocessing

* yolov5 cuda preprocessing configurable

* yolov5 update get mat data api

* yolov5 check cuda preprocess args

* refactor cuda function name

* yolo cuda preprocess padding value configurable

* yolov5 release cuda memory

* cuda preprocess pybind api update

* move use_cuda_preprocessing option to yolov5 model

* yolov5lite cuda preprocessing

* yolov6 cuda preprocessing

* yolov7 cuda preprocessing

* yolov7_e2e cuda preprocessing

* remove cuda preprocessing in runtime option

* refine log and cmake variable name

* fix model runtime ptr type

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-10-19 16:04:58 +08:00
Jack Zhou 173bbf5af4 [Backend] Integrate TensorRT in Paddle Inference backend by default (#381)
* Modify filter of trt

* Add Note for trt libs

* Use paddle inference with trt package

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-10-18 15:29:06 +08:00
WJJ1995 f5c94e5471 Support Poros Backend (#188)
* Add poros backend

* Add torch lib

* Add python3 lib

* set c++ 14 for poros

* fixed bugs

* fixed grammer bugs

* fixed grammer bugs

* fixed code bugs

* fixed code bugs

* fixed CreatePorosValue bug

* Add AtType2String for Log

* fixed trt_option

* fixed poros.cmake path

* fixed grammer bug

* fixed grammer bug

* fixed ambiguous reference

* fixed ambiguous reference

* fixed reference error

* fixed include files

* rm ENABLE_TRT_BACKEND in poros

* update CMakeLists.txt

* fixed CMakeLists.txt

* Add libtorch.so in CMakeLists.txt

* Fixed CMakeLists.txt

* Fixed CMakeLists.txt

* Fixed copy bug

* Fixed copy bug

* Fixed copy bug

* Fixed Cmake

* Fixed Cmake

* debug

* debug

* debug

* debug

* debug

* debug

* debug utils

* debug utils

* copy to cpu

* rm log info

* test share mem

* test share mem

* test share mem

* test multi outputs

* test multi outputs

* test multi outputs

* test multi outputs

* test multi outputs

* test multi outputs

* test multi outputs

* time cost

* time cost

* fixed bug

* time collect

* mem copy

* mem copy

* rm time log

* rm share mem

* fixed multi inputs bug

* add set_input_dtypes func

* add SetInputDtypes

* fixed bug

* fixed bug

* fixed prewarm data order

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* debug

* fixed bug

* Add compile func

* Add compile func

* Add compile func

* Add is_dynamic option

* Add is_dynamic option

* Add is_dynamic option

* Add is_dynamic option

* rm infer log

* add cuda11.6 poros lib

* fixed bug

* fixed bug

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* fixed multi outputs

* rm logs

* test

* test

* test

* add test log

* add test log

* add test log

* add test log

* support cpu

* support cpu

* support cpu

* support cpu

* support member variable definition

* rm useless log

* fixed name

* resolve conflict

* resolve conflict

* resolve conflict

* fixed cmake

* add GetInputInfos&GetOutputInfos

* add GetInputInfos&GetOutputInfos

* fixed bug

* fixed runtime.py

* add compile func

* add np

* deal with comments

* rm to_inter func

* add property
2022-10-17 15:28:12 +08:00
DefTruth e24c592f43 [osx] fixed mac osx arm64 and x86_64 0.3.0 rpath error (#374)
* Update paddle_inference.cmake

* Update process_libraries.py.in

* Update process_libraries.py.in

* Update paddle_inference.cmake

* Update CMakeLists.txt

* Update VERSION_NUMBER

* Update VERSION_NUMBER

* Update download_prebuilt_libraries.md

* Update gpu.md

* Update cpu.md

* Update download_prebuilt_libraries.md

* Update jetson.md

* Update tensorrt_tricks.md

* Update cpp.md

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-10-16 15:23:35 +08:00
Jason 3ff562aa77 Bump up to version 0.3.0 (#371)
* Update VERSION_NUMBER

* Update paddle_inference.cmake

* Delete docs directory

* release new docs

* update version number

* add vision result doc

* update version

* fix dead link

* fix vision

* fix dead link

* Update README_EN.md

* Update README_EN.md

* Update README_EN.md

* Update README_EN.md

* Update README_EN.md

* Update README_CN.md

* Update README_EN.md

* Update README_CN.md

* Update README_EN.md

* Update README_CN.md

* Update README_EN.md

* Update README_EN.md

Co-authored-by: leiqing <54695910+leiqing1@users.noreply.github.com>
2022-10-15 22:01:27 +08:00
Jack Zhou e268ef08d2 Fix openvino cmake (#348)
fix openvino
2022-10-12 21:13:44 +08:00
Jason e6f8bd90cf Revert Paddle Inference to No TRT version (#355) 2022-10-12 19:39:37 +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
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
DefTruth 584ba3de68 [win] Add fastdeploy_init.bat and update docs (#320)
* [cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk

* [cmake] fixed patchelf download on mac and android

* [lite] Add threads and power_mode option support

* [pybind] update runtime pybind for lite power mode

* [python] Add set_lite_power_mode api to runtime

* [Lite] add lite enable_fp16 option support

* [lite] add more options for lite backend.

* [cmake] fixed Paddle Lite typo

* [runtime] format LitePowerMode enum comments

* [runtime] format lite option comments

* [win] Add fastdeploy_init.bat and update docs

* [win] Add fastdeploy_init.bat and update docs
2022-10-06 15:57:18 +08:00
DefTruth c4288a92e1 [lite] add more options for lite backend (#313)
* [cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk

* [cmake] fixed patchelf download on mac and android

* [lite] Add threads and power_mode option support

* [pybind] update runtime pybind for lite power mode

* [python] Add set_lite_power_mode api to runtime

* [Lite] add lite enable_fp16 option support

* [lite] add more options for lite backend.

* [cmake] fixed Paddle Lite typo

* [runtime] format LitePowerMode enum comments

* [runtime] format lite option comments
2022-10-04 17:31:48 +08:00
ChaoII 97bcf5ac5d [cmake]fix find tbb package in utils.cmake 2022-09-29 11:38:16 +08:00
ChaoII de88bb61c7 Update opencv.cmake 2022-09-28 18:18:20 +08:00
ChaoII 68e049d93f [fix] # Win/Linux/Mac specified opencv path unable to take effect 2022-09-28 18:09:39 +08:00
DefTruth 42d8b300f4 [cmake] fixed patchelf download on mac and android (#296)
* [cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk

* [cmake] fixed patchelf download on mac and android
2022-09-28 14:46:50 +08:00
Jason 7af1fa0946 Fix patchelf problem (#295)
fix patchelf
2022-09-28 12:33:32 +08:00
Jason 311a59c62d Add patchelf to solve the build problem on Linux without patchelf (#291)
* add patchelf as tool

* Update CMakeLists.txt
2022-09-28 10:48:49 +08:00
DefTruth 4ead287f5a [cmake] support Android armv8 & armv7 native c++ sdk (#288)
[cmake] support Android arm64-v8a & armeabi-v7a native c++ sdk
2022-09-27 20:58:44 +08:00
Jason 1f35f2036e Decrease wheel package size (#287)
* Decrease wheel package size

* Decrease wheel package size

* Decrease wheel package size
2022-09-27 18:02:34 +08:00
Jason d855c28073 Rename third libraries' name (#286)
* Rename third libraries' name

* remove existing directory
2022-09-27 14:16:34 +08:00
Jack Zhou b83cb993ac Simplify cmake and add openvino directory (#285)
* simplify the opencv.cmake

* Add OPENVINO_DIRECTORY option

* Add openvino directory
2022-09-27 10:02:34 +08:00
DefTruth 9e09a55abb [docs] update win build docs with cmake-gui+vs2019 (#280)
* Delete redundant Chinese comments

* [docs] update win build docs with cmake-gui+vs2019

* [docs] update win build docs with cmake-gui+vs2019

* [examples] replace some cn comments with en

* [cmake] update FastDeploy.cmake.in

* [docs] update windows c++ sdk usage docs

* [cmake] update FastDeploy.cmake.in

* [docs] update windows sdk usage docs

Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-09-26 19:25:12 +08:00
Jack Zhou 355382ad63 Move eigen to third party (#282)
* remove useless statement

* Add eigen to third_party dir

* remove reducdant lines
2022-09-26 19:24:02 +08:00
jiangjiajun 85c44d562e Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into develop 2022-09-26 16:19:58 +08:00
jiangjiajun 4af89d27dc Optimize build on jetson 2022-09-26 16:19:36 +08:00
Jason 4421fc5a8f Merge branch 'develop' into add_openvino_mac 2022-09-26 11:32:15 +08:00
Jason 12fed103e6 Update eigen.cmake 2022-09-26 11:31:35 +08:00
zhoushunjie ad03e771dd Add remove_duplicate_libraries function 2022-09-26 11:24:57 +08:00
zhoushunjie f142fcdf60 Add get_openvino_libs 2022-09-25 18:26:04 +08:00
zhoushunjie 870c22c8e9 fix windows bug 2022-09-25 11:56:30 +08:00
zhoushunjie c53d8fd82c Fix windows compile bug 2022-09-25 11:43:16 +08:00
zhoushunjie 749319e2a8 Use omp version in linux 2022-09-24 11:01:47 +08:00
zhoushunjie 99062df866 remove useless file in openvino 2022-09-22 21:19:49 +08:00
DefTruth 189646f08f [Android] support fastdeploy with armeabi-v7a and arm64-v8a (#268)
* [Andorid] support fastdeploy with armeabi-v7a and arm64-v8a

* [Android] support fastdeploy with armeabi-v7a and arm64-v8a

* [cmake] fixed custom opencv_directory error for android
2022-09-22 19:10:14 +08:00
zhoushunjie 13580aeb0d use download_and_decompress instead of external_add 2022-09-22 18:30:18 +08:00
zhoushunjie f4b4264d73 remove fatal error in mac 2022-09-22 18:30:18 +08:00
zhoushunjie 4cf835479b remove tbb path 2022-09-22 18:30:18 +08:00
zhoushunjie 5251cc2e8e remove tbb path 2022-09-22 18:30:18 +08:00
zhoushunjie df18c56470 Use find_package for tbb 2022-09-22 18:30:18 +08:00
zhoushunjie 177da78bb0 Add tbb and tbb malloc dependency for openvino 2022-09-22 18:30:18 +08:00
zhoushunjie 523610da68 Update openvino url 2022-09-22 18:30:18 +08:00
zhoushunjie 9671005e84 add message status 2022-09-22 18:30:18 +08:00
zhoushunjie fac68d408b Adjust message status 2022-09-21 20:05:19 +08:00
zhoushunjie 662b1e6113 add ORT_DIRECTORY compiler option 2022-09-21 20:05:19 +08:00
Jack Zhou e7f741292e Add some lib directories compiler option (#255)
* Add OPENCV_DIRECTORY option to provide the ability to specify the installed opecv lib pat

* Use find_package for opencv in windows, mac and linux

* Fix opencv cmake

* Fix python lib rpath setting

* fix mac python package

* Add some promt when use different opencv lib

* add status message

* Fix the backslash

* Fix python package user defined libs

* Fix windows python process libs

* Add windows lib set path
2022-09-21 13:25:56 +08:00
Jason addce837bc Add paddlelite backend support (#260)
* Add paddlelite backend support

* Update CMakeLists.txt

* Update __init__.py
2022-09-21 13:22:34 +08:00
Jason 5046574b95 Fix bug for part of detection model (#243)
* fix error for part of detection model

* fix error for part of detection model

* add patch paddle inference
2022-09-16 16:31:34 +08:00
Jason 695034fdad Modify directory external and build_scripts name (#225)
modify directory name
2022-09-14 20:13:35 +08:00