guxukai
ab38c9110f
[CVCUDA]add op Python API: Cast, HWC2CHW, Normalize, PadToSize, Resize, StridePad ( #1589 )
...
* add Cast, HWC2CHW, Normalize, PadToSize, StridePad
* add comments
* fix comments
* fix manager.cc
2023-03-14 19:16:07 +08:00
Jason
3d36e26b8a
[Backend] Remove some deprecated api ( #1574 )
...
Remove some deprecated api
2023-03-13 13:42:43 +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
heliqi
a14480ae2b
Update fd_tensor.cc ( #1561 )
2023-03-10 09:08:38 +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
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
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
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
yunyaoXYY
53ad450227
Merge pull request #1448 from yunyaoXYY/develop
...
[Other] Improve the Predict Interface of PP-OCR models.
2023-03-02 14:20:25 +08:00
Wang Xinyu
044ab993d2
[CVCUDA] PP-OCR Cls & Rec preprocessor support CV-CUDA ( #1470 )
...
* ppocr cls preprocessor use manager
* hwc2chw cvcuda
* ppocr rec preproc use manager
* ocr rec preproc cvcuda
* fix rec preproc bug
* ppocr cls&rec preproc set normalize
* fix pybind
* address comment
2023-03-02 10:50:44 +08:00
Zheng-Bicheng
610b4c532b
[Bug Fix] fixed rknn bugs ( #1468 )
...
fixed rknn bugs
2023-03-01 10:21:58 +08:00
yunyaoXYY
803521002f
Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into develop
2023-02-28 08:01:36 +00:00
yunyaoXYY
d09fbd861e
Improve interface
2023-02-28 07:51:22 +00:00
WJJ1995
fe9aff15f2
[Benchmark] Add SaveBenchmarkResult func for benchmark ( #1442 )
...
* 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
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-02-28 11:55:22 +08:00
DefTruth
e86905ca0d
[Bug Fix] move enable_valid_backend_check option -> runtime_option ( #1450 )
...
* [Model] Add skip valid backend check option -> FastDeployModel
* [Model] Add skip valid backend check option -> FastDeployModel
* [Model] Add skip valid backend check option -> FastDeployModel
* [FastDeploy] move enable_valid_backend_check option -> runtime_option
2023-02-28 09:57:31 +08:00
DefTruth
7e5e690367
[Model] Add skip valid backend check option -> FastDeployModel ( #1445 )
...
* [Model] Add skip valid backend check option -> FastDeployModel
* [Model] Add skip valid backend check option -> FastDeployModel
* [Model] Add skip valid backend check option -> FastDeployModel
2023-02-27 15:37:01 +08:00
Zheng-Bicheng
8c3ccc2cc2
[Hackathon 182 Model] Update PPOCRV3 For RKNPU2 ( #1403 )
...
* update ppocrv3 for rknpu2
* add config
* add config
* detele unuseful
* update useful results
* Repair note
* Repair note
* fixed bugs
* update
2023-02-27 15:01:17 +08:00
Zheng-Bicheng
8e50fa307c
[Bug Fix] Fixed the segment error during the visualization of the detection model ( #1420 )
...
fixed detection bug
2023-02-25 12:49:38 +08:00
Jack Zhou
524c85745b
[Backend] Add fixed size optimization for transformer model ( #1430 )
...
Add enable_fixed_size_opt flag
2023-02-24 09:45:04 +08:00
WJJ1995
d3845eb4e1
[Benchmark]Compare diff for OCR ( #1415 )
...
* avoid mem copy for cpp benchmark
* set CMAKE_BUILD_TYPE to Release
* Add SegmentationDiff
* change pointer to reference
* fixed bug
* cast uint8 to int32
* Add diff compare for OCR
* Add diff compare for OCR
* rm ppocr pipeline
* Add yolov5 diff compare
* Add yolov5 diff compare
* deal with comments
* deal with comments
* fixed bug
* fixed bug
2023-02-23 18:57:39 +08:00
Jason
0c664fd006
[Other] Fix some memory leak problem ( #1422 )
...
* Fix memory leak problem for paddleseg model
* Fix bug
* Update postprocessor.cc
---------
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
2023-02-23 16:03:40 +08:00
Jason
062b4fd327
[Bug Fix] Fix memory leak problem for paddleseg model ( #1421 )
...
Fix memory leak problem for paddleseg model
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
2023-02-23 12:45:25 +08:00
Wang Xinyu
91a1c72f98
[CVCUDA] PP-OCR detector preprocessor integrate CV-CUDA ( #1382 )
...
* move manager initialized_ flag to ppcls
* update dbdetector preprocess api
* declare processor op
* ppocr detector preprocessor support cvcuda
* move cvcuda op to class member
* ppcls use manager register api
* refactor det preprocessor init api
* add set preprocessor api
* add create processor macro
* new processor call api
* ppcls preprocessor init resize on cpu
* ppocr detector preprocessor set normalize api
* revert ppcls pybind
* remove dbdetector set preprocessor
* refine dbdetector preprocessor includes
* remove mean std in py constructor
* add comments
* update comment
* Update __init__.py
2023-02-22 19:39:11 +08:00
WJJ1995
2f8d9c9a57
[Benchmark]Add SegmentationDiff to compare SegmentationResult diff ( #1404 )
...
* avoid mem copy for cpp benchmark
* set CMAKE_BUILD_TYPE to Release
* Add SegmentationDiff
* change pointer to reference
* fixed bug
* cast uint8 to int32
2023-02-22 14:42:21 +08:00
Jason
dd527388bc
Update option.h
2023-02-22 11:28:04 +08:00
WJJ1995
721e6efb81
[Benchmark] Add ClassifyDiff to compare ClassifyResult diff ( #1381 )
...
* 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
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-02-21 18:01:13 +08:00
Jason
18e33bae5c
[Other] Optimize runtime module ( #1356 )
...
* Optimize runtime
* fix error
* [Backend] Add option to print tensorrt conversion log (#1386 )
Add option to print tensorrt conversion log
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
---------
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
2023-02-21 17:01:32 +08:00
yunyaoXYY
7dc15e4a77
[Other] Remove useless OpenCV usage for PP-OCR. ( #1375 )
...
* Add Huawei Ascend NPU deploy through PaddleLite CANN
* Add NNAdapter interface for paddlelite
* Modify Huawei Ascend Cmake
* Update way for compiling Huawei Ascend NPU deployment
* remove UseLiteBackend in UseCANN
* Support compile python whlee
* Change names of nnadapter API
* Add nnadapter pybind and remove useless API
* Support Python deployment on Huawei Ascend NPU
* Fix links in readme
* Fix links in readme
* Update PPOCRv2/v3 examples
* Update auto compression configs
* Add neww quantization support for paddleclas model
* Update quantized Yolov6s model download link
* Improve PPOCR comments
* Add models suppor for ascend
* Add PPOCR rec reszie for ascend
* fix conflict for ascend
* Rename CANN to Ascend
* Rename CANN to Ascend
* Improve ascend
* fix ascend bug
* improve ascend docs
* improve ascend docs
* improve ascend docs
* Add English doc for quantization
* Improve Ascend
* Improve Ascend
* Move ascend python demo
* Imporve ascend
* Fix PPOCR rec model bug
* Improve ascend
* Improve ascend
* Improve ascend
* Improve ascend
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Imporve ascend
* Imporve ascend
* Improve ascend
* acc eval script
* acc eval
* remove acc_eval from branch huawei
* Add detection and segmentation examples for Ascend deployment
* Add detection and segmentation examples for Ascend deployment
* Add Ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add PPOCR example for ascend deploy
* Imporve paddle lite compiliation
* Add FlyCV doc
* Add FlyCV doc
* Add FlyCV doc
* Imporve Ascend docs
* Imporve Ascend docs
* Improve PPOCR example
* Support Ascend deployment on X86 platform
* Improve Ascend docs
* Improve ascend
* Improve ascend
* Change Paddle Lite Ascend URL
* fix ascend docs
* fix ascend docs
* Fix Paddle Lite Ascend Lib
* Imporve compile of Ascend
* Imporve compile of Ascend
* fix paddle lite compile
* Remove useless opencv code for ocr
2023-02-20 18:32:49 +08:00
Jason
dc5b4be7a9
[Other] Enable to hidden INFO/WARNING log informations ( #1368 )
...
* Enable to hidden INFO/WARNING log informations
* Fix build error
---------
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
2023-02-20 17:24:12 +08:00
WJJ1995
b6658b8094
[Benchmark] Add ppocr && ppseg benchmark ( #1344 )
...
* 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
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-02-20 15:59:27 +08:00
Jason
db471c3466
[Other] Optimize poros backend ( #1331 )
...
* Optimize poros backend
* Fix pybind error
---------
Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com >
2023-02-17 14:32:35 +08:00
yunyaoXYY
c38b7d4377
[Backend] Support onnxruntime DirectML inference. ( #1304 )
...
* Fix links in readme
* Fix links in readme
* Update PPOCRv2/v3 examples
* Update auto compression configs
* Add neww quantization support for paddleclas model
* Update quantized Yolov6s model download link
* Improve PPOCR comments
* Add English doc for quantization
* Fix PPOCR rec model bug
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Add new paddleseg quantization support
* Add Ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Add ascend model list
* Support DirectML in onnxruntime
* Support onnxruntime DirectML
* Support onnxruntime DirectML
* Support onnxruntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Support OnnxRuntime DirectML
* Remove DirectML vision model example
* Imporve OnnxRuntime DirectML
* Imporve OnnxRuntime DirectML
* fix opencv cmake in Windows
* recheck codestyle
2023-02-17 10:53:51 +08:00
Wang Xinyu
efa46563f3
[nvJPEG] Integrate nvJPEG decoder ( #1288 )
...
* nvjpeg cmake
* add common decoder, nvjpeg decoder and add image name predict api
* ppclas support nvjpeg decoder
* remove useless comments
* image decoder support opencv
* nvjpeg decode fallback to opencv
* fdtensor add nbytes_allocated
* single image decode api
* fix bug
* add pybind
* ignore nvjpeg on jetson
* fix cmake in
* predict on fdmat
* remove image names predict api, add image decoder tutorial
* Update __init__.py
* fix pybind
2023-02-17 10:27:05 +08:00
Zheng-Bicheng
b829a4e23c
Merge branch 'develop' into tiny_pose
2023-02-16 17:35:02 +08:00
DefTruth
ee85a3cade
[Benchmark] Add precision evaluation api from benchmark ( #1310 )
...
* [Benchmark] Init benchmark precision api
* [Benchmark] Init benchmark precision api
* [Benchmark] Add benchmark precision api
* [Benchmark] Calculate the statis of diff
* [Benchmark] Calculate the statis of diff
* [Benchmark] Calculate the statis of diff
* [Benchmark] Calculate the statis of diff
* [Benchmark] Calculate the statis of diff
* [Benchmark] Add SplitDataLine utils
* [Benchmark] Add LexSortByXY func
* [Benchmark] Add LexSortByXY func
* [Benchmark] Add LexSortDetectionResultByXY func
* [Benchmark] Add LexSortDetectionResultByXY func
* [Benchmark] Add tensor diff presicion test
* [Benchmark] fixed conflicts
* [Benchmark] fixed calc tensor diff
* fixed build bugs
* fixed ci bugs when WITH_TESTING=ON
2023-02-16 17:16:14 +08:00
Zheng-Bicheng
2b7c23683a
按照要求更新
2023-02-16 10:38:10 +08:00
Zheng-Bicheng
8faca05280
更新pybind
2023-02-15 21:03:15 +08:00
Zheng-Bicheng
8c42b708f6
删除无用代码，更新python脚本
2023-02-15 21:01:06 +08:00
Zheng-Bicheng
2b1631b563
更新pptinypose模型
2023-02-15 20:55:26 +08:00
Zheng-Bicheng
53333c5db6
更新example 和模型转换代码
2023-02-15 20:37:42 +08:00
Zheng-Bicheng
4ccfbead16
更新Preprocess代码
2023-02-15 19:25:44 +08:00
huangjianhui
328b306d27
Merge branch 'develop' into matting
2023-02-15 11:18:36 +08:00
felixhjh
5dfd590741
Merge branch 'matting' of https://github.com/felixhjh/FastDeploy into matting
2023-02-15 03:18:15 +00:00
felixhjh
5daedd21a3
Refactor by comments
2023-02-15 03:17:51 +00:00
