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
2,162 Commits 19 Branches 8 Tags
6be2c0367b91c6228c9ca5dec77c3c9138fb032e
Commit Graph

453 Commits

Author SHA1 Message Date
Zheng-Bicheng
cd5a54cd75 [Bug Fix] Fix the bug reported by RK3568 Runtime under the latest driver (#1311) 
* 更新rkyolo runtime 在rk3568最新驱动下报错的问题

* 删除debug代码
 2023-02-14 15:40:15 +08:00
WJJ1995
2dfda1db85 [Benchmark] Remove pmap and use mem api (#1309) 
* add GPL lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* support yolov8

* add pybind for yolov8

* add yolov8 readme

* add cpp benchmark

* add cpu and gpu mem

* public part split

* add runtime mode

* fixed bugs

* add cpu_thread_nums

* deal with comments

* deal with comments

* deal with comments

* rm useless code

* add FASTDEPLOY_DECL

* add FASTDEPLOY_DECL

* fixed for windows

* mv rss to pss

* mv rss to pss

* Update utils.cc

* use thread to collect mem

* Add ResourceUsageMonitor

* rm useless code

* fixed bug

* fixed typo

* update ResourceUsageMonitor

* fixed bug

* fixed bug

* add note for ResourceUsageMonitor

* deal with comments

* add macros

* deal with comments

* deal with comments

* deal with comments

* re-lint

* rm pmap and use mem api

* rm pmap and use mem api

* add mem api

* Add PrintBenchmarkInfo func

* Add PrintBenchmarkInfo func

* Add PrintBenchmarkInfo func

* deal with comments

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-02-14 15:00:05 +08:00
Wang Bojun
a0fc0d5e49 Merge branch 'develop' into set_stream_infer-shareExData 2023-02-14 14:23:33 +08:00
wwbitejotunn
727fdc5863 reuse setStream c++ interface, add set_raw_stream python api 2023-02-14 06:22:47 +00:00
huangjianhui
f4371b3c6d Merge branch 'develop' into matting 2023-02-14 11:41:17 +08:00
huangjianhui
0a6869b650 Update visualize.h 2023-02-14 11:32:33 +08:00
huangjianhui
c62dbb7367 Update visualize.h 2023-02-14 11:24:08 +08:00
huangjianhui
7bd8bbfb84 Update visualize_pybind.cc 2023-02-14 11:21:44 +08:00
felixhjh
619b561817 Update api && comments 2023-02-14 03:18:54 +00:00
wwbitejotunn
f1ab47a4ef code revine 2023-02-13 18:16:45 +00:00
felixhjh
815c42c73d Update VisMatting function supports matting with transparent background 2023-02-13 15:28:02 +00:00
felixhjh
031d02275b Merge branch 'encrypt_model' of https://github.com/felixhjh/FastDeploy into encrypt_model 2023-02-13 06:32:19 +00:00
felixhjh
45b070e495 Format code 2023-02-13 06:31:04 +00:00
wwbitejotunn
289d353d99 Merge branch 'develop' of https://github.com/paddlepaddle/fastdeploy into set_stream_infer-shareExData 2023-02-13 03:14:18 +00:00
wwbitejotunn
abfa9fd850 prebind output by shareExternalData 2023-02-13 03:11:31 +00:00
huangjianhui
a30213b504 Merge branch 'develop' into encrypt_model 2023-02-13 10:42:46 +08:00
Zheng-Bicheng
6a3ac91057 [Model] Update rkyolo pybind (#1294) 
更新rkyolo pybind
 2023-02-11 09:09:53 +08:00
WJJ1995
59a4ab343f [Benchmark]Add ResourceUsageMonitor to collect memory info (#1269) 
* add GPL lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* support yolov8

* add pybind for yolov8

* add yolov8 readme

* add cpp benchmark

* add cpu and gpu mem

* public part split

* add runtime mode

* fixed bugs

* add cpu_thread_nums

* deal with comments

* deal with comments

* deal with comments

* rm useless code

* add FASTDEPLOY_DECL

* add FASTDEPLOY_DECL

* fixed for windows

* mv rss to pss

* mv rss to pss

* Update utils.cc

* use thread to collect mem

* Add ResourceUsageMonitor

* rm useless code

* fixed bug

* fixed typo

* update ResourceUsageMonitor

* fixed bug

* fixed bug

* add note for ResourceUsageMonitor

* deal with comments

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-02-10 17:13:22 +08:00
huangjianhui
e8b55ab3c6 Merge branch 'develop' into encrypt_model 2023-02-10 13:03:40 +08:00
felixhjh
5160771a1c Update runtime_option.h 2023-02-10 03:24:45 +00:00
felixhjh
942cee83d7 Add decrypt function to load encrypted model 2023-02-09 14:04:10 +00:00
wwbitejotunn
898b063216 get cache dir 2023-02-09 20:56:55 +08:00
wwbitejotunn
c2e5f6317e fix paddle backend 2023-02-09 20:56:55 +08:00
wwbitejotunn
59c5fedc36 set stream by raw size_t 2023-02-09 12:53:08 +00:00
yeliang2258
4742f97819 [Bug Fix] Fix KunlunXin valid_places (#1285) 
fix KunlunXin valid_places
 2023-02-09 20:39:44 +08:00
wwbitejotunn
4b293a89de fix paddle backend 2023-02-09 05:51:30 +00:00
DefTruth
ab5377b5fa [Benchmark] Add PaddleYOLOv8 cpp benchmark example & lite flags option (#1270) 
* [Android] Add PaddleYOLOv8 cpp benchmark example & lite flags option

* [Benchmark] add linux x86_64 gpu benchmark build script
 2023-02-09 11:58:07 +08:00
Jason
b8afb0d040 [Other] Move comments for deprecated functions (#1275) 
Move comments for deprecated functions
 2023-02-09 10:04:18 +08:00
Jason
0fb2f26352 [Other] Optimize sophgo backend (#1273) 
optimize sophgo backend
 2023-02-08 19:50:37 +08:00
Zheng-Bicheng
e077c005df [Bug Fix] Update RKYOLO code format (#1254) 
* 更新rkyolo细节

* 更新rkyolov5 format
 2023-02-08 19:46:11 +08:00
Jason
a4b0565b9a [Other] Optimize paddle backend (#1265) 
* Optimize paddle backend

* optimize paddle backend

* add version support
 2023-02-08 19:12:03 +08:00
WJJ1995
66f059b65b [Benchmark] Benchmark cpp for YOLOv5 (#1260) 
* add GPL lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* support yolov8

* add pybind for yolov8

* add yolov8 readme

* add cpp benchmark

* add cpu and gpu mem

* public part split

* add runtime mode

* fixed bugs

* add cpu_thread_nums

* deal with comments

* deal with comments

* deal with comments

* rm useless code

* add FASTDEPLOY_DECL

* add FASTDEPLOY_DECL

* fixed for windows

* mv rss to pss

* mv rss to pss

* Update utils.cc

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2023-02-08 15:49:28 +08:00
guxukai
9cd00ad4c5 [Model] Refactoring code of YOLOv5Cls with new model type (#1237) 
* Refactoring code of YOLOv5Cls with new model type

* fix reviewed problem

* Normalize&HWC2CHW -> NormalizeAndPermute

* remove cast()
 2023-02-08 11:19:00 +08:00
Jason
c5b414a774 [Other] Unify initialize api for lite/trt backend (#1249) 
* Unify initialize api for lite/trt backend

* Unify initialize api for lite/trt backend
 2023-02-08 11:16:39 +08:00
Jason
c25aa71fa9 Revert "[Benchmark]Benchmark cpp for YOLOv5" (#1250) 
Revert "[Benchmark]Benchmark cpp for YOLOv5 (#1224)"

This reverts commit c487359e33.
 2023-02-07 22:14:48 +08:00
WJJ1995
c487359e33 [Benchmark]Benchmark cpp for YOLOv5 (#1224) 
* add GPL lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* add GPL-3.0 lisence

* support yolov8

* add pybind for yolov8

* add yolov8 readme

* add cpp benchmark

* add cpu and gpu mem

* public part split

* add runtime mode

* fixed bugs

* add cpu_thread_nums

* deal with comments

* deal with comments

* deal with comments

* rm useless code

* add FASTDEPLOY_DECL

* add FASTDEPLOY_DECL
 2023-02-07 21:26:04 +08:00
Jason
713afe7f1c [Other] Deprecate some option api and parameters (#1243) 
* Optimize Poros backend

* fix error

* Add more pybind

* fix conflicts

* add some deprecate notices

* [Other] Deprecate some apis in RuntimeOption (#1240)

* Deprecate more options

* modify serving

* Update option.h

* fix tensorrt error

* Update option_pybind.cc

* Update option_pybind.cc

* Fix error in serving

* fix word spell error
 2023-02-07 17:57:46 +08:00
guxukai
1c115bb237 [Model] Add facedet model: CenterFace (#1131) 
* cpp example run success

* add landmarks

* fix reviewed problem

* add pybind

* add readme in examples

* fix reviewed problem

* new file:   tests/models/test_centerface.py

* fix reviewed problem 230202
 2023-02-07 14:05:08 +08:00
Wang Xinyu
d3d914856d [CVCUDA] Utilize CV-CUDA batch processing function (#1223) 
* norm and permute batch processing

* move cache to mat, batch processors

* get batched tensor logic, resize on cpu logic

* fix cpu compile error

* remove vector mat api

* nits

* add comments

* nits

* fix batch size

* move initial resize on cpu option to use_cuda api

* fix pybind

* processor manager pybind

* rename mat and matbatch

* move initial resize on cpu to ppcls preprocessor

---------

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2023-02-07 13:44:30 +08:00
Jason
7c9bf11c44 [Other] Optimize Poros backend (#1232) 
* Optimize Poros backend

* fix error

* Add more pybind

* fix conflicts

* add some deprecate notices
 2023-02-07 10:18:03 +08:00
DefTruth
f73a538f61 [Backend] support bechmark mode for runtime and backend (#1201) 
* [backend] support bechmark mode for runtime and backend

* [backend] support bechmark mode for runtime and backend

* [pybind11] add benchmark methods pybind

* [pybind11] add benchmark methods pybind

* [Other] Update build scripts

* [Other] Update cmake/summary.cmake

* [Other] update build scripts

* [Other] add ENABLE_BENCHMARK option -> setup.py

* optimize backend time recording

* optimize backend time recording

* optimize trt backend time record

* [backend] optimze backend_time recording for trt

* [benchmark] remove redundant logs

* fixed ov_backend confilct

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] fixed paddle_backend conflicts

* [benchmark] remove use_gpu option from ort backend option

* [benchmark] update benchmark_ppdet.py

* [benchmark] update benchmark_ppcls.py

* fixed lite backend conflicts

* [Lite] fixed lite xpu

* add benchmark macro

* add RUNTIME_PROFILE_LOOP macros

* add comments for RUNTIME_PROFILE macros

* add comments for new apis

* add comments for new apis

* update benchmark_ppdet.py

* afixed bugs

* remove unused codes

* optimize RUNTIME_PROFILE_LOOP macros

* optimize RUNTIME_PROFILE_LOOP macros

* add comments for benchmark option and result

* add docs for benchmark namespace
 2023-02-06 14:29:35 +08:00
CoolCola
42d14e7119 [Model] Support BlazeFace Model (#1172) 
* fit yolov7face file path

* TODO：添加yolov7facePython接口Predict

* resolve yolov7face.py

* resolve yolov7face.py

* resolve yolov7face.py

* add yolov7face example readme file

* [Doc] fix yolov7face example readme file

* [Doc]fix yolov7face example readme file

* support BlazeFace

* add blazeface readme file

* fix review problem

* fix code style error

* fix review problem

* fix review problem

* fix head file problem

* fix review problem

* fix review problem

* fix readme file problem

* add English readme file

* fix English readme file
 2023-02-06 14:24:12 +08:00
WJJ1995
cfc7af2d45 [Benchmark] avoid Result mem copy for cpp benchmark (#1203) 
* avoid mem copy for cpp benchmark

* set CMAKE_BUILD_TYPE to Release
 2023-02-06 10:19:44 +08:00
Jason
5033000f41 [Other] Optimize OpenVINO backend (#1228) 
* Optimize OpenVINO backend

* Update ov_backend.cc
 2023-02-03 14:18:30 +08:00
Jason
3c5824c862 [Other] Refine Paddle Lite backend (#1202) 
* Refine Paddle Lite backend

* fix error

* Fix compile error

* Fix build error

* modify cpu configure

* fix error

* Fix comment

* Fix error
 2023-02-02 17:40:03 +08:00
huangjianhui
ba6d75f526 Delete redundant code (#1222) 
Update paddle_backend.cc

Delete redundant code

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2023-02-02 15:44:52 +08:00
Zheng-Bicheng
afa3b886f3 [Bug Fix] fixed labels setting of YOLOv5 (#1213) 
修复自己训练的yolov5无法指定label个数的错误
 2023-02-02 15:28:38 +08:00
Jason
a711f99c69 [Other] Optimize runtime module (#1211) 
* modify ort option

* update code

* Unify backend
 2023-02-02 13:10:40 +08:00
Jack Zhou
147cb2c32e [Model] Fix model format of uie (#1218) 
Fix model format of uie
 2023-02-02 10:34:27 +08:00
Jason
b4e322af63 [Other] Optimize load model from memory function (#1205) 
Optimize option for runtime
 2023-02-01 15:50:38 +08:00