ChaoII
d43e9011eb
[Bug Fix]fix tracking 'LetterBoxResize' ( #1711 )
2023-03-27 14:03:09 +08:00
guxukai
631f94d276
[CVCUDA] Update CV-CUDA to v0.2.1, add vision processor C++ tutorial ( #1678 )
...
* update cvcuda 0.2.0 -> 0.2.1
* add cpp tutorials demo
* fix reviewed problem
2023-03-24 16:57:35 +08:00
yeliang2258
cae341e6c5
[Backend] Add fp16 support for ONNXRuntime-GPU ( #1239 )
...
* add fp16 support for ort-gpu
* add enable_ort_fp16 option
* fix
* fix bugs
* use fp16 for test
* update code
* update code
* fix windows bug
2023-03-23 18:23:13 +08:00
guxukai
4d57b62f83
[Doc] add vision processors cpp api doc ( #1624 )
...
* add vision processors cpp api doc
* add base class Processor in api doc
* Update base.h
---------
Co-authored-by: Wang Xinyu <shaywxy@gmail.com >
2023-03-17 13:20:38 +08:00
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
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
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
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
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
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
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
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
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
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
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
huangjianhui
9a74b44f8a
Merge branch 'develop' into matting
2023-02-14 18:49:39 +08:00
CoolCola
a5d23c57d0
[Bug fix]add yolov7face landmarks ( #1297 )
...
* add yolov7face benchmark
* fix review problem
* fix review problems
2023-02-14 18:36:28 +08:00
felixhjh
39639009d1
Refactor code
2023-02-14 09:34:06 +00:00
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
felixhjh
815c42c73d
Update VisMatting function supports matting with transparent background
2023-02-13 15:28:02 +00:00
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
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
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
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
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
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
