apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-24 17:49:42 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity
1,824 Commits 40 Branches 17 Tags
41c5f2de5acb16c4e644c8dfd83e9cce2a4f9d32
Commit Graph

47 Commits

Author SHA1 Message Date
Jack Zhou 41c5f2de5a Merge pull request #1305 from wwbitejotunn/set_stream_infer-shareExData 
[Backend] Set inference with extra stream and prebind output tensor with share ex data
 2023-02-14 17:08:56 +08:00
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
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
wwbitejotunn f1ab47a4ef code revine 2023-02-13 18:16:45 +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
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
Jason a4b0565b9a [Other] Optimize paddle backend (#1265) 
* Optimize paddle backend

* optimize paddle backend

* add version support
 2023-02-08 19:12:03 +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
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
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
Jason a711f99c69 [Other] Optimize runtime module (#1211) 
* modify ort option

* update code

* Unify backend
 2023-02-02 13:10:40 +08:00
Jason b4e322af63 [Other] Optimize load model from memory function (#1205) 
Optimize option for runtime
 2023-02-01 15:50:38 +08:00
huangjianhui 76df90afc3 [Other] FastDeploy TensorRT && ONNX backend support to load model form memory (#1130) 
* Update all backends load model from buffer

* Delete redundant code

* Format code style

* Format code style

* Delete redundant code

* Delete redundant code

* Add some FDASSERTs

* Update load model form memory when cloning engine

* Update clone engine code

* Update set_model_buffer api parameters with char pointer

* Release memory buffer variables after finish init backends

* Fix conflict

* Fix bug
 2023-02-01 11:36:09 +08:00
Jason 54ceb93670 [Other] Optimize runtime module (#1195) 
* Optimize code

* optimize code

* fix bug
 2023-01-31 10:11:16 +08:00
DefTruth 2613e9c5d0 [Android] support fastdeploy build with static deps(60Mb->29~31Mb) (#1176) 
* [Android] support fastdeploy build with static deps(70Mb->17~19Mb)

* [Android] support fastdeploy build with static deps(60Mb->29~30Mb)

* fixed ci

* fixed ci

* [staticlib] support fd android static lib

* [static] optimize bundle_static_library func

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] add api_helpers.h -> staticlib headers

* [staticlib] Fixed Paddle Lite paddle_use_kernels.h to support fd armv7 static lib

* [staticlib] Add strip -> fd static lib target

* [staticlib] optimize bundle_static_library func

* [staticlib] add strip for fd static lib on  mac osx

* [staticlib] move api_helpers -> lite/option

* [staticlib] optimize bundle_static_library

* [staticlib] add Android limit
 2023-01-30 19:39:56 +08:00
yeliang2258 829fe0721d [Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116) 
* add fp16 cuda kernel

* fix code bug

* update code
 2023-01-13 19:44:00 +08:00
Jason d00df3d621 [Backend] Remove all lite options in RuntimeOption (#1109) 
* Remove all lite options in RuntimeOption

* Fix code error

* move pybind

* Fix build error
 2023-01-13 19:40:34 +08:00
WJJ1995 aa6931bee9 [Model] Add YOLOv5-seg (#988) 
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

* Add Monitor for benchmark

* update mem monitor

* Set trt_max_batch_size default 1

* fixed ocr benchmark bug

* support yolov5 in serving

* Fixed yolov5 serving

* Fixed postprocess

* update yolov5 to 7.0

* add poros runtime demos

* update readme

* Support poros abi=1

* rm useless note

* deal with comments

* support pp_trt for ppseg

* fixed symlink problem

* Add is_mini_pad and stride for yolov5

* Add yolo series for paddle format

* fixed bugs

* fixed bug

* support yolov5seg

* fixed bug

* refactor yolov5seg

* fixed bug

* mv Mask int32 to uint8

* add yolov5seg example

* rm log info

* fixed code style

* add yolov5seg example in python

* fixed dtype bug

* update note

* deal with comments

* get sorted index

* add yolov5seg test case

* Add GPL-3.0 License

* add round func

* deal with comments

* deal with commens

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2023-01-11 15:36:32 +08:00
Dantès de70e8366c add ocr, ppyoloe, picodet examples (#1076) 
* add ocr examples

* add ppyoloe examples

add picodet examples

* remove /ScaleFactor in ppdet/postprocessor.cc
 2023-01-10 16:34:26 +08:00
Jason fc314f1696 [Other] Rename directory op_cuda_kernels to common/cuda (#1104) 
rename directory name
 2023-01-10 16:31:37 +08:00
heliqi 7fdbedcc99 [Bug Fix]The TRT Backend Clone Interface is restored to Runtime.Init (#1101) 
Update runtime.cc
 2023-01-10 10:32:07 +08:00
Jason df20b2a02b [Other] Remove useless macros (#1095) 
* Remove useless macros

* triger ci

* fix check error

* rename INTEGRATE_PADDLE2ONNX to ENABLE_PADDLE2ONNX
 2023-01-09 21:35:23 +08:00
Jason 054dfec43a [Other] Remove some build options (#1090) 
* remove some flags

* add gpu check in cmake
 2023-01-09 17:36:07 +08:00
Jason 4aa4ebd7c3 [Other] [Part2] Upgrade runtime module (#1080) 
[Other] Upgrade runtime module
 2023-01-09 13:22:51 +08:00
Jason d7a65e5c70 [Other] Upgrade runtime module (#1068) 
* Upgrade runtime module

* Update option.h

* Fix build error

* Move enumerates

* little modification

* little modification

* little modification:

* Remove some useless flags
 2023-01-06 13:44:05 +08:00