Commit Graph

2178 Commits

Author SHA1 Message Date
DefTruth
022b90de8a [Benchmark] Update get_models.sh 2023-03-10 15:15:10 +08:00
guxukai
c6480de736 [CVCUDA] Vision Processor Python API and Tutorial (#1394)
* bind success

* bind success fix

* FDMat pybind, ResizeByShort pybind

* FDMat pybind, ResizeByShort pybind, remove initialized_

* override BindProcessorManager::Run in python is available

* PyProcessorManager done

* vision_pybind fix

* manager.py fix

* add tutorials

* remove Apply() bind

* remove Apply() bind and fix

* fix reviewed problem

* fix reviewed problem

* fix reviewed problem readme

* fix reviewed problem readme etc

* apply return outputs

* nits

* update readme

* fix FDMatbatch

* add op pybind: CenterCrop, Pad

* add op overload for pass FDMatBatch

---------

Co-authored-by: Wang Xinyu <shaywxy@gmail.com>
2023-03-10 14:42:32 +08:00
Wang Xinyu
cb7c8a07d4 [CVCUDA] PaddleDetection preprocessor support CV-CUDA (#1493)
* ppdet preproc use manager

* pad_to_size chw opencv

* pad_to_size chw flycv

* fix pad_to_size flycv

* add warning message

* cvcuda convert cubic to linear, padToSize cvcuda

* stridedpad cvcuda

* fix flycv include

* fix flycv include

* fix flycv build

* cast cvcuda

* fix pybind

* fix normalize permute cuda

* base processor move funcs to cc

* Update pad_to_size.cc
2023-03-10 12:43:57 +08:00
WJJ1995
9ee2118e1f [Benchmark]Romove porxy (#1573)
* 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

* fixed enable_paddle_to_trt

* add log for paddle_trt

* support ppcls benchmark

* use new trt option api

* update benchmark info

* simplify benchmark.cc

* simplify benchmark.cc

* deal with comments

* Add ppseg && ppocr benchmark

* add OCR rec img

* add ocr benchmark

* fixed trt shape

* add trt shape

* resolve conflict

* add ENABLE_BENCHMARK define

* Add ClassifyDiff

* Add Resize for ClassifyResult

* deal with comments

* add convert info script

* resolve conflict

* Add SaveBenchmarkResult func

* fixed bug

* fixed bug

* fixed bug

* add config.txt for option

* fixed bug

* fixed bug

* fixed bug

* add benchmark.sh

* mv thread_nums from 8 to 1

* deal with comments

* deal with comments

* fixed readme

* deal with comments

* add all platform shell

* Update config.arm.txt

* Update config.gpu.txt

* Update config.x86.txt

* fixed printinfo bug

* rm proxy

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-10 12:41:00 +08:00
Jack Zhou
f7ef464412 [Other] Use symbolic link pointed to TensorRT library (#1461)
* Add force rpath

* update to dev-6

* remove force-rpath

* remove nvinfer so

* Add symbol link creation when import fastdeploy first

* Add dst

* update symbol link creation

* Add logging

* logging -> logger

* update tips

* Set logging level

* Add --force-rpath
2023-03-10 09:09:04 +08:00
heliqi
a14480ae2b Update fd_tensor.cc (#1561) 2023-03-10 09:08:38 +08:00
WJJ1995
098b06754f [Benchmark]Fixed PrintBenchmarkInfo bug (#1570)
* 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

* fixed enable_paddle_to_trt

* add log for paddle_trt

* support ppcls benchmark

* use new trt option api

* update benchmark info

* simplify benchmark.cc

* simplify benchmark.cc

* deal with comments

* Add ppseg && ppocr benchmark

* add OCR rec img

* add ocr benchmark

* fixed trt shape

* add trt shape

* resolve conflict

* add ENABLE_BENCHMARK define

* Add ClassifyDiff

* Add Resize for ClassifyResult

* deal with comments

* add convert info script

* resolve conflict

* Add SaveBenchmarkResult func

* fixed bug

* fixed bug

* fixed bug

* add config.txt for option

* fixed bug

* fixed bug

* fixed bug

* add benchmark.sh

* mv thread_nums from 8 to 1

* deal with comments

* deal with comments

* fixed readme

* deal with comments

* add all platform shell

* Update config.arm.txt

* Update config.gpu.txt

* Update config.x86.txt

* fixed printinfo bug

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-09 22:12:58 +08:00
Jack Zhou
f0dbfd9ae9 Merge pull request #1563 from joey12300/update_serving
[Serving] Add delete pass, disable_trt_ops and enable_fixed_size_opt for fastdeploy serving
2023-03-09 22:05:03 +08:00
Zheng-Bicheng
32f0d2e350 [Model] update PPDet pybind and docs (#1550)
update pybind and docs
2023-03-09 16:22:31 +08:00
zhoushunjie
cd9cb577fe disable_trt_ops->delete_passes 2023-03-09 06:14:53 +00:00
zhoushunjie
90942a7ada DisablePaddleTrtOP->DisableTrtOps 2023-03-09 06:01:48 +00:00
zhoushunjie
f88b06a4ff Add delete pass, disable_trt_ops and enable_fixed_size_opt for serving 2023-03-09 03:18:22 +00:00
chenjian
091e039991 [C API] Add create api for c results (#1547)
add create api for c results
2023-03-09 11:11:47 +08:00
DefTruth
ad14d0e0bd [Benchmark] Update benchmark_ppyolov8 codes (#1558) 2023-03-08 20:27:48 +08:00
Jack Zhou
f4736e7931 Merge pull request #1552 from joey12300/fix_delete_pass
[Backend] Fix delete pass of paddle inference
2023-03-08 19:57:08 +08:00
Jason
6be2c0367b [Example] Update runtime examples (#1542)
* Add notes for tensors

* Optimize some apis

* move some warnings
2023-03-08 16:56:04 +08:00
zhoushunjie
384eca14fd Fix delete pass 2023-03-08 06:32:27 +00:00
yeliang2258
3d31834193 [Doc] Fix docs for KunlunXin, A311D and issue template (#1551)
fix docs
2023-03-08 13:47:40 +08:00
Zheng-Bicheng
0687d3b0ad [Model] Add Solov2 For PaddleDetection (#1435)
* update solov2

* Repair note

* update solov2 postprocess

* update

* update solov2

* update solov2

* fixed bug

* fixed bug

* update solov2

* update solov2

* fix build android bug

* update docs

* update docs

* update docs

* update

* update

* update arch and docs

* update

* update

* update solov2 python

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-08 10:01:32 +08:00
shirukai
96a3698271 [Model] Support size param to ResizeImage preprocessor (#1527)
feat: ResizeImage函数新增支持按照size处理图片
2023-03-08 09:53:33 +08:00
Zheng-Bicheng
547910f70a Merge pull request #1543 from Zheng-Bicheng/rknn_pybind
[Pybind] update rknpu2 pybind
2023-03-08 09:25:15 +08:00
Zheng-Bicheng
1e56d5069c update 2023-03-07 23:02:43 +08:00
Zheng-Bicheng
b5fb9fad4e Merge remote-tracking branch 'origin/rknn_pybind' into rknn_pybind 2023-03-07 22:54:01 +08:00
Zheng-Bicheng
7bed7a5053 update 2023-03-07 22:46:34 +08:00
Zheng-Bicheng
c16f528c0e Merge branch 'develop' into rknn_pybind 2023-03-07 21:36:13 +08:00
Zheng-Bicheng
c2d377a1d6 [Doc] update rknn and ppocr example docs (#1538)
* update docs

* update
2023-03-07 18:54:27 +08:00
Jason
7e4ef4a72c Merge branch 'develop' into rknn_pybind 2023-03-07 18:53:53 +08:00
Jason
8ec1353cd8 [Doc] Add notes for tensors (#1533)
Add notes for tensors
2023-03-07 18:46:48 +08:00
Zheng-Bicheng
458523fc29 update pybind 2023-03-07 15:50:49 +08:00
leiqing
190d254a95 Update README_CN.md 2023-03-07 13:58:22 +08:00
leiqing
60937cebe9 Update README.md 2023-03-07 13:57:37 +08:00
DefTruth
febbc31cf5 [Doc] Update cpp benchmark usage docs. 2023-03-07 11:02:03 +08:00
Jason
29f1bcb764 Update FastDeploy.cmake.in 2023-03-07 10:29:26 +08:00
Jason
bf2ba72f1b [Compile] Support build FastDeploy with GLIBCXX_ABI=0 (#1528)
* Support abi=0 build

* trigger ci

* fix cmake
2023-03-07 09:45:30 +08:00
leiqing
5411a30138 Update README_CN.md 2023-03-06 16:07:02 +08:00
WJJ1995
8febff9379 [Benchmark] Add x86/Arm/XPU/GPU benchmark scripts (#1522)
* 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

* fixed enable_paddle_to_trt

* add log for paddle_trt

* support ppcls benchmark

* use new trt option api

* update benchmark info

* simplify benchmark.cc

* simplify benchmark.cc

* deal with comments

* Add ppseg && ppocr benchmark

* add OCR rec img

* add ocr benchmark

* fixed trt shape

* add trt shape

* resolve conflict

* add ENABLE_BENCHMARK define

* Add ClassifyDiff

* Add Resize for ClassifyResult

* deal with comments

* add convert info script

* resolve conflict

* Add SaveBenchmarkResult func

* fixed bug

* fixed bug

* fixed bug

* add config.txt for option

* fixed bug

* fixed bug

* fixed bug

* add benchmark.sh

* mv thread_nums from 8 to 1

* deal with comments

* deal with comments

* fixed readme

* deal with comments

* add all platform shell

* Update config.arm.txt

* Update config.gpu.txt

* Update config.x86.txt

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-06 15:32:55 +08:00
DefTruth
e5287548b2 Update use_sdk_on_windows.md 2023-03-06 14:19:40 +08:00
DefTruth
46f5bb15de Update use_sdk_on_windows_build.md 2023-03-06 14:19:01 +08:00
DefTruth
81386e59b2 [Doc] Update benchmark xpu_l3_cache option docs.
Update benchmark xpu_l3_cache option docs.
2023-03-06 14:17:29 +08:00
lishicheng1996
dfe027dbbd [stable-diffusion] paddle swift+coreml demo (#1494)
* paddle sd

* renew ml-stable-diffusion submodule

* stable diffusion swift demo
2023-03-06 13:34:29 +08:00
DefTruth
767647d88e [Android] Add WITH_TENSOR_FUNCS option -> Android (#1512)
* [Android] Add WITH_TENSOR_FUNCS option -> Android

* [Android] move android cmake codes -> android.cmake

* [Android] move android cmake codes -> android.cmake
2023-03-06 13:33:43 +08:00
yunyaoXYY
e796658e54 [Bug Fix] Fix OCR Serving bug. (#1516)
fix ocr_serving bug
2023-03-06 13:32:05 +08:00
DefTruth
40cec53c27 [XPU] Update Lite XPU lib & add l3 cache benchmark option (#1503)
* [XPU] Update Lite XPU lib & add l3 cache benchmark option

* Update build_linux_x86_64_cpp_xpu_with_benchmark.sh

* Update kunlunxin.cmake

* Update build_linux_x86_64_cpp_xpu_with_benchmark.sh
2023-03-06 11:48:15 +08:00
Edward Zhou
81c2c75c5c 修正 [examples/vision/segmentation/paddleseg/cpu-gpu/cpp/infer.cc] 第93行末尾漏了';' (#1507)
修正第93行末尾漏了';'
2023-03-04 11:24:56 +08:00
Zeref996
d21d48810e mac intel compile debug, do not merge (#1500) 2023-03-04 10:57:19 +08:00
leiqing
21919d8e14 Update README_CN.md 2023-03-03 18:44:43 +08:00
Jason
6756269efd Update cpu.md 2023-03-03 16:57:15 +08:00
Jason
dee80ae388 Update cpu.md 2023-03-03 16:53:39 +08:00
WJJ1995
99b1bc5d6e [Benchmark] Add run_benchmark_cpu.sh (#1465)
* 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

* fixed enable_paddle_to_trt

* add log for paddle_trt

* support ppcls benchmark

* use new trt option api

* update benchmark info

* simplify benchmark.cc

* simplify benchmark.cc

* deal with comments

* Add ppseg && ppocr benchmark

* add OCR rec img

* add ocr benchmark

* fixed trt shape

* add trt shape

* resolve conflict

* add ENABLE_BENCHMARK define

* Add ClassifyDiff

* Add Resize for ClassifyResult

* deal with comments

* add convert info script

* resolve conflict

* Add SaveBenchmarkResult func

* fixed bug

* fixed bug

* fixed bug

* add config.txt for option

* fixed bug

* fixed bug

* fixed bug

* add benchmark.sh

* mv thread_nums from 8 to 1

* deal with comments

* deal with comments

* fixed readme

* deal with comments

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-02 19:11:21 +08:00
DefTruth
a157da17a4 [Docs] Update use_sdk_on_windows_build.md (#1490)
Update use_sdk_on_windows_build.md
2023-03-02 16:46:35 +08:00