Commit Graph

2282 Commits

Author SHA1 Message Date
Zeref996
c04a3a4e35 [Dev] fix dev version number (#1742) 2023-03-30 10:33:39 +08:00
Zheng-Bicheng
644a085ca2 [Bug Fix] fix yolox's bug (#1736)
fix yolox's bug

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-29 21:03:37 +08:00
guxukai
38f056d1c1 [CVCUDA] PP-OCR and PPDet preprocessor support use_cuda python API(#1734)
add cvcuda support in ppocr and ppdet
2023-03-29 20:57:36 +08:00
Zeref996
3ef48f7746 add fdbenchmark run_gpu.sh and run_x86.sh (#1741) 2023-03-29 19:36:58 +08:00
Zeref996
edbe71f68d Merge pull request #1733 from Zeref996/refresh-doc-1.0.5
Refresh doc version 1.0.5
2023-03-29 16:12:56 +08:00
CoolCola
18a39ce59d [Streamer] Add fdtracker plugin (#1668)
* add fdtracker plugin

* upload fdtracker

* delete test modle

* fix review problem

* fix code style

* fix code style

* fix copy right, delete travial annotation

* fix copy right

* fix compile error

---------

Co-authored-by: jiangjiajun <jiangjiajun@baidu.com>
2023-03-29 13:56:10 +08:00
Jason
7507003113 Update __init__.py 2023-03-29 12:57:40 +08:00
Zeref996
b00cb4223d refresh doc version 1.0.5 2023-03-29 11:05:10 +08:00
Zeref996
ea52ec9065 Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into release/1.0.5 2023-03-29 10:52:49 +08:00
wanziyu
b1d2903b93 [PaddlePaddle Hackathon4 No.186] Add PaddleDetection Models Deployment Go Examples (#1648)
* [PaddlePaddle Hackathon4 No.186] Add PaddleDetection Models Deployment Go Examples

Signed-off-by: wanziyu <ziyuwan@zju.edu.cn>

* Fix YOLOv8 Deployment Go Example

Signed-off-by: wanziyu <ziyuwan@zju.edu.cn>

---------

Signed-off-by: wanziyu <ziyuwan@zju.edu.cn>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-28 20:30:03 +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
DefTruth
7936833451 Update config.gpu.trt.fp16.h2d.txt 2023-03-28 11:54:00 +08:00
DefTruth
76936391e3 Update config.gpu.trt.fp16.e2e.txt 2023-03-28 11:53:29 +08:00
DefTruth
5f273b2541 Update config.gpu.trt.fp16.e2e.mem.txt 2023-03-28 11:53:08 +08:00
Wang Xinyu
d19b85b0e1 [Streamer] add fdinfer plugin (#1716)
fdinfer plugin
2023-03-27 19:43:09 +08:00
Jack Zhou
a3f9c1f8e3 Merge pull request #1667 from Zeref996/fix-dockerf-00
fix dockerfile paddle install url
2023-03-27 16:32:29 +08:00
wangguoya
c61a07712e fix bug for kunlunxin run sd demo for uing fp16 (#1680)
* modify sd infer.py for using paddle_kunlunxin_fp16

* Update infer.py

* [fix bug] fix bug sd in demo infer.py for kunlunxin using fp16
2023-03-27 14:04:21 +08:00
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
ChaoII
d43e9011eb [Bug Fix]fix tracking 'LetterBoxResize' (#1711) 2023-03-27 14:03:09 +08:00
WJJ1995
0c543c010e [Benchmark] Add dynamic shape for pp_trt (#1703)
* 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

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-24 23:07:10 +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
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
WJJ1995
f0235a4c4e [Benchmark]Add inlcude_h2d_d2h config for trt (#1699)
* 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

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-24 11:17:49 +08:00
Zeref996
c3410cbff7 refresh version number 1.0.5 2023-03-23 19:27:26 +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
WJJ1995
b62912ff9c [Benchmark]Add Failed Log (#1693)
* 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
2023-03-23 17:42:32 +08:00
yunyaoXYY
f36f9324de [Docs] Pick PPOCR fastdeploy docs from PaddleOCR (#1534)
* Pick PPOCR fastdeploy docs from PaddleOCR

* improve ppocr

* improve readme

* remove old PP-OCRv2 and PP-OCRv3 folfers

* rename kunlun to kunlunxin

* improve readme

* improve readme

* improve readme

---------

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-23 13:11:19 +08:00
yunyaoXYY
c91e99b5f5 [Docs] Pick paddleclas fastdeploy docs from PaddleClas (#1654)
* Adjust folders structures in paddleclas

* remove useless files

* Update sophgo

* improve readme
2023-03-23 13:06:09 +08:00
DefTruth
ab65557121 [Benchmark] fix ppdet models download urls (#1679)
* [Benchmark] fix ppdet download urls

* [Benchmark] fix ppdet download urls

* [Benchmark] fix ppdet download urls

* [Benchmark] fix ppdet download urls
2023-03-22 18:06:00 +08:00
yunyaoXYY
b672e32dae Merge pull request #1666 from yunyaoXYY/develop
[Backend] ORT support UINT8 and INT8 input and output.
2023-03-22 09:34:50 +08:00
WJJ1995
19d3b188f8 [Benchmark]Mv thread_nums from 1 to 8 in x86 (#1670)
* 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
2023-03-21 21:34:04 +08:00
yunyaoXYY
097582e468 Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into new_dev 2023-03-21 12:13:29 +00:00
guxukai
0343deb328 [Doc] add vision processor python api doc (#1655)
* add vision processor python api doc

* fix reviewed problem

* fix reviewed problem
2023-03-21 14:20:28 +08:00
Zeref996
b8f8f09e37 fix dockerfile paddle install url 2023-03-21 10:47:06 +08:00
DefTruth
2ff7b10adc [cmake] switch paddle 2.4-dev7 -> 2.4-dev6 for windows (#1660)
* [cmake] switch paddle 2.4-dev7 -> 2.4-dev6 for windows

* [cmake] remove examples from install policy

* Update CMakeLists.txt
2023-03-21 10:41:34 +08:00
yunyaoXYY
b3e16e9966 ORT support UINT8 and INT8 input and output 2023-03-21 02:23:23 +00:00
yunyaoXYY
3cc72765dd Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into new_dev 2023-03-21 02:21:35 +00:00
linyangshi
f278ed424b [benchmark] update benchmark_gpu_trt.sh (#1651)
* 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

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-20 20:55:25 +08:00
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
af18e597d0 [Docs] rename ppseg kunlun docs -> kunlunxin (#1662)
* [Docs] rename ppseg kunlun -> kunlunxin

* [Docs] rename ppseg fastdeploy kunlun docs -> kunlunxin
2023-03-20 19:46:18 +08:00
WJJ1995
d522ef28b4 [Benchmark]Add trt cache option (#1653)
* 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

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2023-03-20 18:08:28 +08:00
yunyaoXYY
f23c61328e Merge branch 'develop' of https://github.com/PaddlePaddle/FastDeploy into new_dev 2023-03-20 08:02:03 +00:00
DefTruth
d0de379d9a [Bug Fix] fix trt_shape error for PPHumanMatting 2023-03-19 13:18:41 +08:00
DefTruth
c070892fd6 [Bug Fix] fix trt_shape error in benchmark_ppmatting 2023-03-19 13:14:08 +08:00
DefTruth
e78360fdf2 [Benchmark] Update benchmark_gpu_trt.sh 2023-03-19 12:16:31 +08:00