WJJ1995
409c5dc056
[Backend]Add default value for TRT SetShape() ( #1712 )
...
* 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()
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-03-27 14:03:47 +08:00
WJJ1995
5c70db176f
[Backend]Add switch_ir_debug for Paddle Backend ( #1700 )
...
* 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
* fixed thread nums
* Add Failed log
* optimizer x86 pipeline
* Add switch_ir_debug for paddle backend
* fixed for ci
2023-03-24 17:29:31 +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
yunyaoXYY
b3e16e9966
ORT support UINT8 and INT8 input and output
2023-03-21 02:23:23 +00:00
Jack Zhou
012c7771c1
[Serving] Add collect shape and fix serving infer ( #1658 )
...
Add collect shape and fix serving infer
2023-03-20 19:55:30 +08:00
DefTruth
6af3691568
[XPU] Update Lite XPU lib and fixed some bugs ( #1647 )
2023-03-17 21:39:39 +08:00
Jason
3b1343c726
[Bug] Fix loadding big model loadding problem ( #1636 )
...
Fix loadding big model loadding problem
2023-03-17 10:25:26 +08:00
Ethan Yang
4f48d84c27
[Backend] optimize cpu usage on openvino backend ( #1531 )
...
* optimiza cpu usage on openvino backend
conver the hint varible to string
* update with affinity mode set-up
---------
Co-authored-by: Ethan <yicheng@intel.com >
Co-authored-by: Jason <jiangjiajun@baidu.com >
2023-03-17 10:24:25 +08:00
Jason
3d36e26b8a
[Backend] Remove some deprecated api ( #1574 )
...
Remove some deprecated api
2023-03-13 13:42:43 +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
Zheng-Bicheng
458523fc29
update pybind
2023-03-07 15:50:49 +08:00
Zheng-Bicheng
610b4c532b
[Bug Fix] fixed rknn bugs ( #1468 )
...
fixed rknn bugs
2023-03-01 10:21:58 +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
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
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
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
Jason
7a4b2f3177
[Other] Optimize rknpu2 backend ( #1318 )
...
* Optimize rknpu2 backend
* Fix error
* Fix comparision error
2023-02-15 11:11:37 +08:00
WJJ1995
c25d1cc1bc
[Backend]Fixed enable_paddle_to_trt() bug ( #1320 )
...
* 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
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-02-14 17:51:39 +08:00
Jack Zhou
41c5f2de5a
Merge pull request #1305 from wwbitejotunn/set_stream_infer-shareExData
...
[Backend] Set inference with extra stream and prebind output tensor with share ex data
2023-02-14 17:08:56 +08:00
Zheng-Bicheng
cd5a54cd75
[Bug Fix] Fix the bug reported by RK3568 Runtime under the latest driver ( #1311 )
...
* 更新rkyolo runtime 在rk3568最新驱动下报错的问题
* 删除debug代码
2023-02-14 15:40:15 +08:00
wwbitejotunn
f1ab47a4ef
code revine
2023-02-13 18:16:45 +00:00
wwbitejotunn
289d353d99
Merge branch 'develop' of https://github.com/paddlepaddle/fastdeploy into set_stream_infer-shareExData
2023-02-13 03:14:18 +00:00
wwbitejotunn
abfa9fd850
prebind output by shareExternalData
2023-02-13 03:11:31 +00:00
wwbitejotunn
898b063216
get cache dir
2023-02-09 20:56:55 +08:00
wwbitejotunn
c2e5f6317e
fix paddle backend
2023-02-09 20:56:55 +08:00
yeliang2258
4742f97819
[Bug Fix] Fix KunlunXin valid_places ( #1285 )
...
fix KunlunXin valid_places
2023-02-09 20:39:44 +08:00
wwbitejotunn
4b293a89de
fix paddle backend
2023-02-09 05:51:30 +00:00
DefTruth
ab5377b5fa
[Benchmark] Add PaddleYOLOv8 cpp benchmark example & lite flags option ( #1270 )
...
* [Android] Add PaddleYOLOv8 cpp benchmark example & lite flags option
* [Benchmark] add linux x86_64 gpu benchmark build script
2023-02-09 11:58:07 +08:00
Jason
b8afb0d040
[Other] Move comments for deprecated functions ( #1275 )
...
Move comments for deprecated functions
2023-02-09 10:04:18 +08:00
Jason
0fb2f26352
[Other] Optimize sophgo backend ( #1273 )
...
optimize sophgo backend
2023-02-08 19:50:37 +08:00
Jason
a4b0565b9a
[Other] Optimize paddle backend ( #1265 )
...
* Optimize paddle backend
* optimize paddle backend
* add version support
2023-02-08 19:12:03 +08:00
Jason
c5b414a774
[Other] Unify initialize api for lite/trt backend ( #1249 )
...
* Unify initialize api for lite/trt backend
* Unify initialize api for lite/trt backend
2023-02-08 11:16:39 +08:00
Jason
c25aa71fa9
Revert "[Benchmark]Benchmark cpp for YOLOv5" ( #1250 )
...
Revert "[Benchmark]Benchmark cpp for YOLOv5 (#1224 )"
This reverts commit c487359e33
2023-02-07 22:14:48 +08:00
WJJ1995
c487359e33
[Benchmark]Benchmark cpp for YOLOv5 ( #1224 )
...
* 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
2023-02-07 21:26:04 +08:00
Jason
713afe7f1c
[Other] Deprecate some option api and parameters ( #1243 )
...
* Optimize Poros backend
* fix error
* Add more pybind
* fix conflicts
* add some deprecate notices
* [Other] Deprecate some apis in RuntimeOption (#1240 )
* Deprecate more options
* modify serving
* Update option.h
* fix tensorrt error
* Update option_pybind.cc
* Update option_pybind.cc
* Fix error in serving
* fix word spell error
2023-02-07 17:57:46 +08:00
Jason
7c9bf11c44
[Other] Optimize Poros backend ( #1232 )
...
* Optimize Poros backend
* fix error
* Add more pybind
* fix conflicts
* add some deprecate notices
2023-02-07 10:18:03 +08:00
DefTruth
f73a538f61
[Backend] support bechmark mode for runtime and backend ( #1201 )
...
* [backend] support bechmark mode for runtime and backend
* [backend] support bechmark mode for runtime and backend
* [pybind11] add benchmark methods pybind
* [pybind11] add benchmark methods pybind
* [Other] Update build scripts
* [Other] Update cmake/summary.cmake
* [Other] update build scripts
* [Other] add ENABLE_BENCHMARK option -> setup.py
* optimize backend time recording
* optimize backend time recording
* optimize trt backend time record
* [backend] optimze backend_time recording for trt
* [benchmark] remove redundant logs
* fixed ov_backend confilct
* [benchmark] fixed paddle_backend conflicts
* [benchmark] fixed paddle_backend conflicts
* [benchmark] fixed paddle_backend conflicts
* [benchmark] remove use_gpu option from ort backend option
* [benchmark] update benchmark_ppdet.py
* [benchmark] update benchmark_ppcls.py
* fixed lite backend conflicts
* [Lite] fixed lite xpu
* add benchmark macro
* add RUNTIME_PROFILE_LOOP macros
* add comments for RUNTIME_PROFILE macros
* add comments for new apis
* add comments for new apis
* update benchmark_ppdet.py
* afixed bugs
* remove unused codes
* optimize RUNTIME_PROFILE_LOOP macros
* optimize RUNTIME_PROFILE_LOOP macros
* add comments for benchmark option and result
* add docs for benchmark namespace
2023-02-06 14:29:35 +08:00
Jason
5033000f41
[Other] Optimize OpenVINO backend ( #1228 )
...
* Optimize OpenVINO backend
* Update ov_backend.cc
2023-02-03 14:18:30 +08:00
Jason
3c5824c862
[Other] Refine Paddle Lite backend ( #1202 )
...
* Refine Paddle Lite backend
* fix error
* Fix compile error
* Fix build error
* modify cpu configure
* fix error
* Fix comment
* Fix error
2023-02-02 17:40:03 +08:00
huangjianhui
ba6d75f526
Delete redundant code ( #1222 )
...
Update paddle_backend.cc
Delete redundant code
Co-authored-by: Jason <jiangjiajun@baidu.com >
2023-02-02 15:44:52 +08:00
Jason
a711f99c69
[Other] Optimize runtime module ( #1211 )
...
* modify ort option
* update code
* Unify backend
2023-02-02 13:10:40 +08:00
Jason
b4e322af63
[Other] Optimize load model from memory function ( #1205 )
...
Optimize option for runtime
2023-02-01 15:50:38 +08:00
huangjianhui
76df90afc3
[Other] FastDeploy TensorRT && ONNX backend support to load model form memory ( #1130 )
...
* Update all backends load model from buffer
* Delete redundant code
* Format code style
* Format code style
* Delete redundant code
* Delete redundant code
* Add some FDASSERTs
* Update load model form memory when cloning engine
* Update clone engine code
* Update set_model_buffer api parameters with char pointer
* Release memory buffer variables after finish init backends
* Fix conflict
* Fix bug
2023-02-01 11:36:09 +08:00
Jason
54ceb93670
[Other] Optimize runtime module ( #1195 )
...
* Optimize code
* optimize code
* fix bug
2023-01-31 10:11:16 +08:00
