wangguoya
bf6caeb2ce
modify sd demo infer.py for using paddle_kunlunxin_fp16 ( #1612 )
...
* modify sd infer.py for using paddle_kunlunxin_fp16
* Update infer.py
2023-03-16 19:48:15 +08:00
Yi-sir
66275bcbfa
[Example] Merge Download Paddle Model, Paddle->ONNX, ONNX -> MLIR, MLIR -> BModel into infer.py ( #1622 )
...
fix infer.py and README
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-16 19:47:50 +08:00
Jason
2de2166472
Delete .paddlex directory
2023-03-16 18:40:28 +08:00
WJJ1995
281d6140ce
[Benchmark]Adjust warmup/repeat times ( #1632 )
...
* 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
* add more model support
* all backend config.txt
* deal with comments
* Add MattingDiff compare
* fixed predict bug
* adjust warmup/repeat times
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-16 13:08:16 +08:00
Jason
dd01aaaf16
Create how_to_add_backend.md
2023-03-16 11:44:17 +08:00
linyangshi
21b1cb8742
[Benchmark] Add more PaddleClas models to benchmark ( #1629 )
...
* 添加paddleclas模型
* 更新README_CN
* 更新README_CN
* 更新README
* update get_model.sh
* update get_models.sh
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-16 10:45:54 +08:00
Jack Zhou
960818a86a
Merge pull request #1630 from joey12300/accelarate_serving_compiling
...
[Serving] Accelarate the compilation of serving
2023-03-16 07:59:28 +08:00
zhoushunjie
f3daf90f4d
Set proxy when compile serving
2023-03-15 13:05:19 +00:00
WJJ1995
a598e7adc4
[Benchmark]Add MattingResult Compare ( #1619 )
...
* 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
* add more model support
* all backend config.txt
* deal with comments
* Add MattingDiff compare
* fixed predict bug
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-15 17:41:19 +08:00
Jason
78cc41396a
Create README.md
2023-03-15 10:30:53 +08:00
Jason
69c6508b4b
Delete examples/multimodal/stable_diffusion/swift_coreml_diffusers directory
2023-03-15 10:30:27 +08:00
Jason
c97d44ad8e
Create README.md
2023-03-15 10:27:57 +08:00
Jason
74bf90f113
Create README.md
2023-03-15 10:27:27 +08:00
jiangjiajun
589963ea5e
remove submodules
2023-03-15 02:24:30 +00:00
Jack Zhou
c73e2ad093
Merge pull request #1615 from joey12300/remove_bind_output_tensor_info
...
[Backend] Remove FDINFO in BindOutputTensor
2023-03-14 21:58:47 +08:00
Jack Zhou
68163083f9
Merge pull request #1614 from joey12300/update_2.4dev_7
...
[Backend] Update paddle inference to 2.4-dev7
2023-03-14 21:58:22 +08:00
zhoushunjie
b7fb3aff08
remoove fdinfo in BindOutputTensor
2023-03-14 12:53:37 +00:00
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
zhoushunjie
8489e22b4b
update paddle inference to 2.4-dev7
2023-03-14 09:56:16 +00:00
Zheng-Bicheng
41ee93c75e
[Doc] Update RKNPU2 Docs ( #1608 )
...
* update rknpu2 docs
* update rknpu2 docs
2023-03-14 17:49:12 +08:00
DefTruth
043cde3665
[Benchmark] fixed benchmark cpp README.md typo
2023-03-14 14:10:13 +08:00
CoolCola
745d0018fa
[DOC]fix death url ( #1598 )
...
fix death url
2023-03-14 10:22:52 +08:00
Hu Chuqi
4ae772c2c7
[Doc] Update readme files in English version ( #1592 )
...
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
2023-03-13 20:23:51 +08:00
leiqing
0464b4ec1c
Update README.md
2023-03-13 20:22:26 +08:00
leiqing
f38e7d63d7
Update README_CN.md
2023-03-13 20:17:19 +08:00
lishicheng1996
fbaf80e266
[bug fix] delete another long-path file(xcuserdata) ( #1594 )
...
delete long-path file(xcuserdata)
2023-03-13 19:29:05 +08:00
Wang Xinyu
38240cc975
[PaddleX] PaddleX PaddleClas example ( #1564 )
...
* paddlex ppcls cpp example
* paddlex ppcls python example
* paddlex ppcls serving example
* update readme
* add paddlex main readme
* ppcls use new dir structure
* Update README_CN-linux-cpp.md
* Delete README.md
* Rename README_CN.md to README.md
* Update README.md
* Update README.md
* Update README.md
* use new api
* add linux python and win cpp doc
* Update README-linux-python.md
* Update README-windows-cpp.md
* Update README-linux-python.md
* Update README-windows-cpp.md
* Update README-linux-cpp.md
* Update README-linux-python.md
* Update README-windows-cpp.md
* add serving and windows readme
---------
Co-authored-by: leiqing <54695910+leiqing1@users.noreply.github.com >
2023-03-13 17:13:48 +08:00
lishicheng1996
15485a1952
[buf fix] delete long name files in ml-stable-diffusion ( #1590 )
...
delete long name files in ml-stable-diffusion
2023-03-13 16:21:19 +08:00
DefTruth
ae2a145f9f
[Benchmark] fixed benchmark cpp README.md typo
2023-03-13 15:41:41 +08:00
WJJ1995
11dd2512c5
[Benchmark] Add all backend config ( #1587 )
...
* 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
* add more model support
* all backend config.txt
* deal with comments
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-13 15:36:30 +08:00
guxukai
f8d56a2424
[CVCUDA] wrap C processors in Python API ( #1576 )
...
* wrap C ops in Python API
* add comments
* change processor create style
* processors class inherit
2023-03-13 13:56:25 +08:00
Jason
3d36e26b8a
[Backend] Remove some deprecated api ( #1574 )
...
Remove some deprecated api
2023-03-13 13:42:43 +08:00
Edward Zhou
f2821b6241
修正cpp文件名与CMakeLists.txt中的配置一致 ( #1579 )
...
* 修正第93行末尾漏了';'
* 修正cpp文件名与CMakeFiles.txt中的配置一致
2023-03-13 13:42:12 +08:00
DefTruth
57decf349e
[Benchmark] Optimize log info for use_fp16 flag on CPU/XPU
2023-03-13 13:38:10 +08:00
DefTruth
5a708f5163
[Benchmark] Add LD_LIBRARY_PATH setting in arm script
2023-03-12 21:06:03 +08:00
WJJ1995
23c4fa6743
[Benchmark] Add Det/Matting models for benchmark ( #1580 )
...
* 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
* add more model support
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-12 20:36:22 +08:00
guxukai
b06279378a
[Bug Fix] need sphinx_book_theme in docs/api_docs/python/requirements.txt ( #1575 )
...
bug : need sphinx_book_theme in docs/api_docs/python/requirements.txt
2023-03-10 15:30:33 +08:00
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
