DefTruth
ade27d29cb
[Sync][Internal] sync some internal features of paddle3d inference ( #2118 )
...
* [Sync][Internal] sync some internal codes
* [Sync][Internal] sync some internal features of paddle3d inference
* [Sync][Internal] sync some internal features of paddle3d inference
2023-07-17 23:06:51 +08:00
DefTruth
681ccc4c24
[Sync][Internal] sync some internal paddle3d codes ( #2108 )
2023-07-13 22:06:28 +08:00
DefTruth
99c2b6592d
[Backend] refactor paddle custom ops -> fastdeploy::paddle_custom_ops ( #2101 )
...
* [cmake] upgrade windows paddle inference -> 2.5.0
* [cmake] upgrade windows paddle inference -> 2.5.0
* fix paddle custom ops bug on windows
* [Backend] refactor paddle custom ops
2023-07-13 09:00:03 +08:00
DefTruth
b2426aefa9
[Backend] add paddle custom ops compatible policy ( #2070 )
...
* Add centerpoint
* fix postprocess op file name
* [Backend] add paddle custom ops compatible policy
* [Backend] add paddle custom ops compatible policy
* [Backend] add paddle custom ops compatible policy
* upgrade linx paddle gpu -> 2.5
* add custom op compatible policy for paddle 2.5
* add custom op compatible policy for paddle 2.5
* add custom op compatible policy for paddle 2.5
* add collect_trt_shape_by_device option for paddle backend
* add collect_trt_shape_by_device option for paddle backend
* add custom op option for python build
* fix python build bugs
* update paddle linux x86 cpu only lib
* update paddle linux gpu lib
* update patchelf cmake
* fix paddle backend option pybind
* update paddle_inference.cmake
* add cuda sm_80 support (A100)
---------
Co-authored-by: zengshao0622 <peter_z96@163.com >
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-29 22:32:14 +08:00
DefTruth
90e4fccbf8
[benchmark] update paddlex2.0 benchmark scripts ( #2063 )
...
* [Backend] Add backward compatiable for paddle infernence 2.4.x
* [Backend] Add backward compatiable for paddle infernence 2.4.x
* [benchmark] update paddlex2.0 benchmark scripts
2023-06-25 19:45:43 +08:00
DefTruth
4aff3221fd
[benchmark] update paddlex benchmark scripts ( #2060 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
* [benchmark] adjust paddlex dino trt shapes
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add ort/paddle h2d gpu configs for paddlex
* [benchmark] update paddlex benchmark scripts
* [benchmark] update paddlex benchmark scripts
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-22 18:30:01 +08:00
DefTruth
a180fb3c8f
[benchmark] add ort/paddle h2d gpu configs for paddlex ( #2059 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
* [benchmark] adjust paddlex dino trt shapes
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add ort/paddle h2d gpu configs for paddlex
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-22 17:48:37 +08:00
DefTruth
ff835690a2
[benchmark] add max_workspace_size flags for tensorrt/pptrt backend ( #2058 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
* [benchmark] adjust paddlex dino trt shapes
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-22 16:43:39 +08:00
DefTruth
269d65a9bb
[benchmark] adjust paddlex dino trt shapes ( #2057 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
* [benchmark] adjust paddlex dino trt shapes
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-22 15:59:26 +08:00
DefTruth
c503298f87
[benchmark] support paddlex ppyoloe pptrt benchmark ( #2055 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-21 18:40:00 +08:00
DefTruth
e171710044
[Bug Fix] fixed paddlex dino benchmark trt shapes ( #2050 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-21 00:07:22 +08:00
DefTruth
f5bea8bf37
[Bug Fix] fixed paddlex ppseg pp-trt infer error ( #2049 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
2023-06-20 23:24:31 +08:00
DefTruth
1144e0a484
[benchmark] fixed paddlex benchmark for picodet 320 ( #2046 )
2023-06-20 14:14:22 +08:00
DefTruth
147060ac60
[benchmark] add paddlex benchmark run scripts ( #2015 )
2023-06-05 23:19:05 +08:00
CoolCola
c634a9260d
[Benchmark] support CLIP and DINO ( #2014 )
...
* support ocrv4 det
* add clip dino
2023-06-02 19:01:56 +08:00
CoolCola
05b3c1febd
[Benchmark]support ocrv4 det ( #2013 )
...
support ocrv4 det
2023-06-02 17:32:29 +08:00
DefTruth
126ac9e915
[Bug Fix] fixed runtime benchmark bin error ( #2010 )
2023-06-02 14:45:31 +08:00
DefTruth
de8f0fe1f2
[Cherry Pick][benchmark] Pick PaddleX benchmark codes from <- paddlex ( #2009 )
...
[benchmark] add paddlex benchmark codes
2023-06-02 11:14:49 +08:00
DefTruth
284b1b46c8
[Serving] Support XPU encrypt & auth server ( #2007 )
...
* [patchelf] fix patchelf error for inference xpu
* [serving] add xpu dockerfile and support fd server
* [serving] add xpu dockerfile and support fd server
* [Serving] support XPU + Tritron
* [Serving] support XPU + Tritron
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] add comments for xpu tritron dockerfile
* [Doruntime] fix xpu infer error
* [Doruntime] fix xpu infer error
* [XPU] update xpu dockerfile
* add xpu triton server docs
* add xpu triton server docs
* add xpu triton server docs
* add xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* [XPU] Update XPU L3 Cache setting docs
* [XPU] Add Encryption and AUTH support for XPU Server
* [XPU] Add Encryption and AUTH support for XPU Server
* [Bug Fix] fix paddle reader error
* [Serving] Support XPU encrypt & auth server
* [Serving] Support XPU encrypt & auth server
* [Serving] Support XPU encrypt & auth server
* [Serving] Support XPU encrypt & auth server
* [Triton] switch TAG 22.12 -> TAG 21.10wq
* update xpu auth server script
2023-06-01 21:36:44 +08:00
DefTruth
387c5695b3
[XPU] Update XPU L3 Cache setting docs ( #2001 )
...
* [patchelf] fix patchelf error for inference xpu
* [serving] add xpu dockerfile and support fd server
* [serving] add xpu dockerfile and support fd server
* [Serving] support XPU + Tritron
* [Serving] support XPU + Tritron
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] update xpu tritron docker file -> paddle 0.0.0
* [Dockerfile] add comments for xpu tritron dockerfile
* [Doruntime] fix xpu infer error
* [Doruntime] fix xpu infer error
* [XPU] update xpu dockerfile
* add xpu triton server docs
* add xpu triton server docs
* add xpu triton server docs
* add xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* update xpu triton server docs
* [XPU] Update XPU L3 Cache setting docs
2023-05-30 11:21:04 +08:00
co63oc
3a9904411a
[C API] Fix some c api document typos ( #1997 )
2023-05-29 13:43:54 +08:00
DefTruth
49c033a828
[XPU] Support XPU via Paddle Inference backend ( #1987 )
...
* [backend] Support XPU via Paddle Inference backend
* [backend] Support XPU via Paddle Inference backend
* [backend] Support XPU via Paddle Inference backend
* [XPU] support XPU benchmark via paddle inference
* [XPU] support XPU benchmark via paddle inference
* [benchmark] add xpu paddle h2d config files
2023-05-25 14:13:40 +08:00
DefTruth
2672e2b881
[benchmark] optimize benchmark bin options ( #1984 )
...
* [benchmark] optimize benchmark bin options
* [benchmark] optimize benchmark bin options
2023-05-24 14:56:00 +08:00
DefTruth
1f66d5d9d3
[benchmark] support lite light api & optimize benchmark flags ( #1950 )
...
* [benchmark] support lite light api & optimize benchmark flags
* [backend] remove un-used option member
* [backend] remove un-used option member
2023-05-17 18:51:32 +08:00
DefTruth
a5a7c962d0
[benchmark] Add lite opencl gpu option support ( #1944 )
...
[benchmark] add lite opencl gpu option support
2023-05-15 20:41:10 +08:00
linyangshi
b12d330076
[Bug Fix] Fix get_models bug ( #1943 )
...
* 添加paddleclas模型
* 更新README_CN
* 更新README_CN
* 更新README
* update get_model.sh
* update get_models.sh
* update paddleseg models
* update paddle_seg models
* update paddle_seg models
* modified test resources
* update benchmark_gpu_trt.sh
* add paddle detection
* add paddledetection to benchmark
* modified benchmark cmakelists
* update benchmark scripts
* modified benchmark function calling
* modified paddledetection documents
* upadte getmodels.sh
* add PaddleDetectonModel
* reset examples/paddledetection
* resolve conflict
* update pybind
* resolve conflict
* fix bug
* delete debug mode
* update checkarch log
* update trt inputs example
* Update README.md
* add ppocr_v4
* update ppocr_v4
* update ocr_v4
* update ocr_v4
* update ocr_v4
* update ocr_v4
* update get_models.sh
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-05-15 16:02:59 +08:00
linyangshi
643f41e711
[Model] Support PP-OCRv4 pipeline ( #1913 )
...
* 添加paddleclas模型
* 更新README_CN
* 更新README_CN
* 更新README
* update get_model.sh
* update get_models.sh
* update paddleseg models
* update paddle_seg models
* update paddle_seg models
* modified test resources
* update benchmark_gpu_trt.sh
* add paddle detection
* add paddledetection to benchmark
* modified benchmark cmakelists
* update benchmark scripts
* modified benchmark function calling
* modified paddledetection documents
* upadte getmodels.sh
* add PaddleDetectonModel
* reset examples/paddledetection
* resolve conflict
* update pybind
* resolve conflict
* fix bug
* delete debug mode
* update checkarch log
* update trt inputs example
* Update README.md
* add ppocr_v4
* update ppocr_v4
* update ocr_v4
* update ocr_v4
* update ocr_v4
* update ocr_v4
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-05-11 16:09:50 +08:00
DefTruth
77cb9db6da
[Model] Support PP-ShiTuV2 models for PaddleClas ( #1900 )
...
* [cmake] add faiss.cmake -> pp-shituv2
* [PP-ShiTuV2] Support PP-ShituV2-Det model
* [PP-ShiTuV2] Support PP-ShiTuV2-Det model
* [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support
* [PP-ShiTuV2] Add PPShiTuV2Recognizer c++&python support
* [Bug Fix] fix ppshitu_pybind error
* [benchmark] Add ppshituv2-det c++ benchmark
* [examples] Add PP-ShiTuV2 det & rec examples
* [vision] Update vision classification result
* [Bug Fix] fix trt shapes setting errors
2023-05-08 14:04:09 +08:00
linyangshi
9164796645
[Model] Support DINO & DETR and add PaddleDetectionModel class ( #1837 )
...
* 添加paddleclas模型
* 更新README_CN
* 更新README_CN
* 更新README
* update get_model.sh
* update get_models.sh
* update paddleseg models
* update paddle_seg models
* update paddle_seg models
* modified test resources
* update benchmark_gpu_trt.sh
* add paddle detection
* add paddledetection to benchmark
* modified benchmark cmakelists
* update benchmark scripts
* modified benchmark function calling
* modified paddledetection documents
* add PaddleDetectonModel
* reset examples/paddledetection
* resolve conflict
* update pybind
* resolve conflict
* fix bug
* delete debug mode
* update checkarch log
* update trt inputs example
* Update README.md
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-05-05 14:10:33 +08:00
DefTruth
6d0261e9e4
[Model] Support PP-StructureV2-Layout model ( #1867 )
...
* [Model] init pp-structurev2-layout code
* [Model] init pp-structurev2-layout code
* [Model] init pp-structurev2-layout code
* [Model] add structurev2_layout_preprocessor
* [PP-StructureV2] add postprocessor and layout detector class
* [PP-StructureV2] add postprocessor and layout detector class
* [PP-StructureV2] add postprocessor and layout detector class
* [PP-StructureV2] add postprocessor and layout detector class
* [PP-StructureV2] add postprocessor and layout detector class
* [pybind] add pp-structurev2-layout model pybind
* [pybind] add pp-structurev2-layout model pybind
* [Bug Fix] fixed code style
* [examples] add pp-structurev2-layout c++ examples
* [PP-StructureV2] add python example and docs
* [benchmark] add pp-structurev2-layout benchmark support
2023-05-05 13:05:58 +08:00
thunder95
2c5fd91a7f
[Hackthon_4th 242] Support en_ppstructure_mobile_v2.0_SLANet ( #1816 )
...
* first draft
* update api name
* fix bug
* fix bug and
* fix bug in c api
* fix bug in c_api
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-04-27 10:45:14 +08:00
DefTruth
430fc424ac
[benchmark] optimize benchmark bin usage ( #1868 )
...
* [benchmark] add disable_mkldnn option for paddle infer backend to support 3D model
* [benchmark] optimize benchmark bin usage
* [benchmark] optimize benchmark bin usage
2023-04-25 11:43:59 +08:00
DefTruth
37794d5f45
[benchmark] add disable_mkldnn option for paddle infer backend to support 3D model benchmark ( #1866 )
...
[benchmark] add disable_mkldnn option for paddle infer backend to support 3D model
2023-04-25 10:43:08 +08:00
DefTruth
eb00817598
[benchmark] Update runtime benchmark bin docs ( #1865 )
...
* [benchmark] update runtime benchmark bin docs
* [benchmark] update runtime benchmark bin docs
2023-04-24 17:13:49 +08:00
DefTruth
bc27eb4967
[benchmark] Update benchmark_xpu.sh ( #1862 )
2023-04-24 15:53:05 +08:00
DefTruth
4f24ca16c6
[benchmark] Update benchmark_xpu.sh
2023-04-24 15:39:51 +08:00
thunder95
51be3fea78
[Hackthon_4th 177] Support PP-YOLOE-R with BM1684 ( #1809 )
...
* first draft
* add robx iou
* add benchmark for ppyoloe_r
* remove trash code
* fix bugs
* add pybind nms rotated option
* add missing head file
* fix bug
* fix bug2
* fix shape bug
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-04-21 10:48:05 +08:00
DefTruth
17cde190c7
[Bug Fix] fix benchmark model download links ( #1841 )
2023-04-19 20:29:26 +08:00
linyangshi
60a44f5af1
[Benchmark] add PaddleDetection to benchmark ( #1675 )
...
* 添加paddleclas模型
* 更新README_CN
* 更新README_CN
* 更新README
* update get_model.sh
* update get_models.sh
* update paddleseg models
* update paddle_seg models
* update paddle_seg models
* modified test resources
* update benchmark_gpu_trt.sh
* add paddle detection
* add paddledetection to benchmark
* modified benchmark cmakelists
* update benchmark scripts
* modified benchmark function calling
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-04-13 10:29:49 +08:00
DefTruth
a40d6ee093
[benchmark] Update config.xpu.lite.fp32.l3.e2e.mem.txt
2023-04-07 10:41:36 +08:00
WJJ1995
82ce988573
[Benchmark]Fixed benchmark config default device id ( #1749 )
...
* 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
* add e2e/mem configs
* fixed typo
* open collect_mem
* fixed typo
* add trt cache option
* fixed bug
* fixed repeat times
* test for benchmark
* test for det benchmark
* for benchmark
* fixed for x86
* add h2d and d2h config
* renmae txt file
* add dynamic shape for pp_trt
* fixed typo
* Update option.h
* add collect shape
* add default value for SetShape()
* add test
* test
* fixed benchmark config
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-30 21:20:56 +08:00
DefTruth
452885b089
[benchmark] fixed runtime benchmark bin macros bug ( #1748 )
...
* [Benchmark] Add pure runtime benchmark bin
* [Benchmark] add cpu/gpu memory collect -> benchmark bin
* [Backend] update trt max_batch_size policy
* [backend] Update trt backend max_batch_size policy
* [Benchmark] Add more model format support -> benchmark bin
* [benchmark] fixed runtime benchmark bin marcos bug
2023-03-30 21:08:38 +08:00
DefTruth
7d1b706caf
[Benchmark] Add pure runtime benchmark bin ( #1731 )
...
* [Benchmark] Add pure runtime benchmark bin
* [Benchmark] add cpu/gpu memory collect -> benchmark bin
* [Backend] update trt max_batch_size policy
* [backend] Update trt backend max_batch_size policy
* [Benchmark] Add more model format support -> benchmark bin
2023-03-30 19:03:30 +08:00
Zeref996
3ef48f7746
add fdbenchmark run_gpu.sh and run_x86.sh ( #1741 )
2023-03-29 19:36:58 +08:00
DefTruth
b15df7a8ee
Update benchmark_gpu_trt.sh
2023-03-28 13:29:30 +08:00
DefTruth
3ed3e303aa
Update config.gpu.trt.fp32.txt
2023-03-28 11:55:51 +08:00
DefTruth
dda23bce95
Update config.gpu.trt.fp32.h2d.txt
2023-03-28 11:55:34 +08:00
DefTruth
fe7c40f1ff
Update config.gpu.trt.fp32.e2e.txt
2023-03-28 11:55:11 +08:00
DefTruth
7be66c811e
Update config.gpu.trt.fp32.e2e.mem.txt
2023-03-28 11:54:47 +08:00
DefTruth
57b5c598a7
Update config.gpu.trt.fp16.txt
2023-03-28 11:54:22 +08:00
