apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-01 04:12:58 +08:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity
3,303 Commits 19 Branches 8 Tags
ec499a010475090dcf9147d25c4aa58aeadf49e9
Commit Graph

1010 Commits

Author SHA1 Message Date
Zheng-Bicheng
0401580264 [Bug Fix] Fixed Ppclas Bugs (#1009) 
* 更新ppclas

* 更新ppclas

* 更新ppclas

* 更新ppclas
 2022-12-29 14:13:55 +08:00
heliqi
ab0929662b [Runtime]FDTensor pybind add from_dlpack interface (#1001) 
add from_dlpack
 2022-12-28 21:58:32 +08:00
舞影凌风
973c746d06 [RKNPU2]support rknpu2 ClasModel #957 (#964) 
* [RKNPU2]support rknpu2 ClasModel #957

* [RKNPU2]support rknpu2 ClasModel #957

* [RKNPU2]support rknpu2 add Resnet50_vd example  #957

* [RKNPU2]support rknpu2 add Resnet50_vd example  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957

* [RKNPU2]support rknpu2, improve doc  #957
 2022-12-28 17:58:18 +08:00
Jack Zhou
a906ddd8ea Merge branch 'develop' into add_batch_size_for_uie 2022-12-28 10:51:40 +08:00
guxukai
866d044898 [Model] add detection model : FastestDet (#842) 
* model done, CLA fix

* remove letter_box and ConvertAndPermute, use resize hwc2chw and convert in preprocess

* remove useless values in preprocess

* remove useless values in preprocess

* fix reviewed problem

* fix reviewed problem pybind

* fix reviewed problem pybind

* postprocess fix

* add test_fastestdet.py, coco_val2017_500 fixed done, ready to review

* fix reviewed problem

* python/.../fastestdet.py

* fix infer.cc, preprocess, python/fastestdet.py

* fix examples/python/infer.py
 2022-12-28 10:49:17 +08:00
zhoushunjie
cfac517ef3 fix for 2022-12-27 15:34:18 +00:00
zhoushunjie
60f8f0e11b Add batch size argument for uie 2022-12-27 15:22:09 +00:00
Jack Zhou
3c38ba4415 [FDTensor] Add device id to output tensor (#978) 
Add device id
 2022-12-27 16:02:57 +08:00
yeliang2258
45865c8724 [Other] Change all XPU to KunlunXin (#973) 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* XPU to KunlunXin

* update

* update model link

* update doc

* update device

* update code

* useless code

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-27 10:02:02 +08:00
Zheng_Bicheng
ec67f8ee6d [Model] Refactor insightface models (#919) 
* 重构insightface代码

* 重写insightface example代码

* 重写insightface example代码

* 删除多余代码

* 修改预处理代码

* 修改文档

* 修改文档

* 恢复误删除的文件

* 修改cpp example

* 修改cpp example

* 测试python代码

* 测试python代码

* 测试python代码

* 测试python代码

* 测试python代码

* 测试python代码

* 测试python代码

* 跑通python代码

* 修复重复初始化的bug

* 更新adaface的python代码

* 修复c++重复初始化的问题

* 修复c++重复初始化的问题

* 修复Python重复初始化的问题

* 新增preprocess的几个参数的获取方式

* 修复注释的错误

* 按照要求修改

* 修改文档中的图片为图片压缩包

* 修改编译完成后程序的提示

* 更新错误include

* 删除无用文件

* 更新文档
 2022-12-26 21:01:58 +08:00
yeliang2258
1911002b90 [Backend]Add stable_diffusion and detection models support for KunlunXin XPU (#954) 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* add valid_xpu for detection

* add paddledetection model support for xpu

* support all detection model in c++ and python

* fix code

* add python stable_diffusion support

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-26 16:22:52 +08:00
yeliang2258
7b15f72516 [Backend] Add OCR、Seg、 KeypointDetection、Matting、 ernie-3.0 and adaface models for XPU Deploy (#960) 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* add seg models for XPU

* add ocr model for XPU

* add matting

* add matting python

* fix infer.cc

* add keypointdetection support for XPU

* Add adaface support for XPU

* add ernie-3.0

* fix doc

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-26 15:02:58 +08:00
yunyaoXYY
d45382e3cc [Backend] Add Huawei Ascend NPU deploy using PaddleLite CANN. (#757) 
* 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

* 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

* Improve Ascend

* Improve Ascend

* Move ascend python demo

* Imporve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Improve ascend

* Imporve ascend

* Imporve ascend

* Improve ascend
 2022-12-26 10:18:34 +08:00
CoolCola
2431890f73 [Model]Fit yolov7face file path (#961) 
fit yolov7face file path
 2022-12-25 16:30:03 +08:00
WJJ1995
0f28f9432f [Model] Add is_mini_pad and stride for YOLOv5 python (#949) 
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

* Add Monitor for benchmark

* update mem monitor

* Set trt_max_batch_size default 1

* fixed ocr benchmark bug

* support yolov5 in serving

* Fixed yolov5 serving

* Fixed postprocess

* update yolov5 to 7.0

* add poros runtime demos

* update readme

* Support poros abi=1

* rm useless note

* deal with comments

* support pp_trt for ppseg

* fixed symlink problem

* Add is_mini_pad and stride for yolov5

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-22 19:15:32 +08:00
huangjianhui
60b84ef315 [Other] Add comments for swap_background api (#941) 
* Update keypointdetection result docs

* Update im.copy() to im in examples

* Update new Api, fastdeploy::vision::Visualize to fastdeploy::vision

* Update SwapBackgroundSegmentation && SwapBackgroundMatting to SwapBackground

* Update README_CN.md

* Update README_CN.md

* Add comments for swap_background Api
 2022-12-22 10:14:36 +08:00
yunyaoXYY
f24bf9523e [Bug Fix] Fix PPOCR rec model bug. (#935) 
* 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
 2022-12-21 18:31:09 +08:00
huangjianhui
291db315c8 [Other]Fastdeploy supports set_model_buffer function for encrypted model (#930) 
* Update keypointdetection result docs

* Update im.copy() to im in examples

* Update new Api, fastdeploy::vision::Visualize to fastdeploy::vision

* Update SwapBackgroundSegmentation && SwapBackgroundMatting to SwapBackground

* Update README_CN.md

* Update README_CN.md

* Support set_model_buffer function
 2022-12-21 14:21:28 +08:00
yeliang2258
b42ec302e6 [Doc] Change all PaddleLite or Paddle-Lite to Paddle Lite (#929) 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* change PaddleLite or Paddle-Lite to Paddle lite

* fix docs

* fix doc

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-21 14:15:50 +08:00
DefTruth
725fe52df3 [FlyCV] Bump up FlyCV -> official release 1.0.0 (#916) 2022-12-21 10:36:07 +08:00
DefTruth
42f9d54749 [ARM] refactor VisSegmentation neon & add SwapBackground neon (#907) 
* [ARM] refactor VisSegmentation neon & add SwapBackground neon

* [ARM] refactor VisSegmentation neon & add SwapBackground neon

* [ARM] Add SwapBackground neon for matting

* [ARM] Add SwapBackground neon for seg

* [ARM] Add SwapBackground neon for seg

* [Bug Fix] Add SwapBackground neon for seg
 2022-12-19 20:30:13 +08:00
Zheng_Bicheng
218f33f8b1 [RKNPU2] Add Quantized PPHumanSeg (#905) 
* 更新rknpu2 backend核心代码

* 更新模型导出核心代码

* 删除无用的config文件

* 新增配置文件以及修改文档

* 模型转换以及文档

* 更新文档

* 更新与配置文件

* 更新PPHumanSeg全量化

* 更新文档

* 更新文档

* 更新文档
 2022-12-19 20:07:32 +08:00
Zheng_Bicheng
dc13eb7049 [RKNPU2] Update quantitative model (#879) 
* 对RKNPU2后端进行修改，当模型为非量化模型时，不在NPU执行normalize操作，当模型为量化模型时，在NUP上执行normalize操作

* 更新RKNPU2框架，输出数据的数据类型统一返回fp32类型

* 更新scrfd，拆分disable_normalize和disable_permute

* 更新scrfd代码，支持量化

* 更新scrfd python example代码

* 更新模型转换代码，支持量化模型

* 更新文档

* 按照要求修改

* 按照要求修改

* 修正模型转换文档

* 更新一下转换脚本
 2022-12-19 13:58:43 +08:00
Zheng_Bicheng
95beb2bbf6 [RKNPU2] RKYOLO Support FP32 return value (#898) 
* RKNPU2 Backend兼容其他模型的量化
fd_tensor正式移除zp和scale的量化参数

* 更新FP32返回值的RKYOLO

* 更新rkyolov5支持fp32格式

* 更新rkyolov5支持fp32格式

* 更新YOLOv5速度文档

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-19 10:03:18 +08:00
DefTruth
6060f4060b [Bug Fix] fix lite int64 datatype convert (#892) 
Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-16 13:29:56 +08:00
Jason
2d998223ac [Backend] Add KunlunXin XPU deploy support (#894) 
Revert "Revert "[Backend] Add KunlunXin XPU deploy support" (#893)"

This reverts commit 0990ab9b50.
 2022-12-16 11:22:30 +08:00
Jason
0990ab9b50 Revert "[Backend] Add KunlunXin XPU deploy support" (#893) 
Revert "[Backend] Add KunlunXin XPU deploy support (#747)"

This reverts commit 5be839b322.
 2022-12-15 21:17:59 +08:00
yeliang2258
5be839b322 [Backend] Add KunlunXin XPU deploy support (#747) 
* add xpu support

* fix docs

* update code

* update doc

* update code

* update yolov5

* update cmake

* add int64_t data support

* fix

* update download links

* add en doc

* update code

* update xpu options

* update doc

* update doc

* update doc

* update lib links

* update doc

* update code

* update lite xpu link

* update xpu lib

* update doc

* update en doc
 2022-12-15 21:17:14 +08:00
totorolin
3164af65a4 [Model] Support PaddleYOLO YOLOv5 YOLOv6 YOLOv7 RTMDet models (#857) 
* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
 2022-12-15 11:46:13 +08:00
huangjianhui
ada54bfd47 [Other]Update python && cpp multi_thread examples (#876) 
* Refactor PaddleSeg with preprocessor && postprocessor

* Fix bugs

* Delete redundancy code

* Modify by comments

* Refactor according to comments

* Add batch evaluation

* Add single test script

* Add ppliteseg single test script && fix eval(raise) error

* fix bug

* Fix evaluation segmentation.py batch predict

* Fix segmentation evaluation bug

* Fix evaluation segmentation bugs

* Update segmentation result docs

* Update old predict api and DisableNormalizeAndPermute

* Update resize segmentation label map with cv::INTER_NEAREST

* Add Model Clone function for PaddleClas && PaddleDet && PaddleSeg

* Add multi thread demo

* Add python model clone function

* Add multi thread python && C++ example

* Fix bug

* Update python && cpp multi_thread examples

* Add cpp && python directory

* Add README.md for examples

* Delete redundant code

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-14 19:18:53 +08:00
CoolCola
ce4867d14e [Model] Support YOLOv7-face Model (#651) 
* 测试

* delete test

* add yolov7-face

* fit vision.h

* add yolov7-face test

* fit: yolov7-face infer.cc

* fit

* fit Yolov7-face Cmakelist

* fit yolov7Face.cc

* add yolov7-face pybind

* add yolov7-face python infer

* feat yolov7-face pybind

* feat yolov7-face format error

* feat yolov7face_pybind error

* feat add yolov7face-pybind to facedet-pybind

* same as before

* same sa before

* feat __init__.py

* add yolov7face.py

* feat yolov7face.h ignore ","

* feat .py

* fit yolov7face.py

* add yolov7face test teadme file

* add test file

* fit postprocess

* delete remain annotation

* fit preview

* fit yolov7facepreprocessor

* fomat code

* fomat code

* fomat code

* fit format error and confthreshold and nmsthres

* fit confthreshold and nmsthres

* fit test-yolov7-face

* fit test_yolov7face

* fit review

* fit ci error

Co-authored-by: kongbohua <kongbh2022@stu.pku.edu.cn>
Co-authored-by: CoolCola <49013063+kongbohua@users.noreply.github.com>
 2022-12-14 19:14:43 +08:00
yunyaoXYY
f601d076e4 [Other] Improve some PPOCR API comments. (#875) 
* 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
 2022-12-14 10:08:31 +08:00
huangjianhui
9937b6c325 [Other] Add Model Clone function for PaddleClas && PaddleDet && PaddleSeg (#791) 
* Refactor PaddleSeg with preprocessor && postprocessor

* Fix bugs

* Delete redundancy code

* Modify by comments

* Refactor according to comments

* Add batch evaluation

* Add single test script

* Add ppliteseg single test script && fix eval(raise) error

* fix bug

* Fix evaluation segmentation.py batch predict

* Fix segmentation evaluation bug

* Fix evaluation segmentation bugs

* Update segmentation result docs

* Update old predict api and DisableNormalizeAndPermute

* Update resize segmentation label map with cv::INTER_NEAREST

* Add Model Clone function for PaddleClas && PaddleDet && PaddleSeg

* Add multi thread demo

* Add python model clone function

* Add multi thread python && C++ example

* Fix bug

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-13 15:19:47 +08:00
yeliang2258
6a1a3d001f [Backend] A311D support (#825) 
* add A311D support

* update code

* update toolchain

* update opencv_armhf lib

* update libs

* update code

* add install script

* update bos link

* update toolchain
 2022-12-13 11:53:36 +08:00
Zheng_Bicheng
188dcedc02 [RKNN2] Fix bugs (#851) 
* 修复picodet格式

* * 修正错误文档
* 修复rknpu2 backend后端的部分错误
* 更新pphumanseg example格式

* * 更新pphumanseg example格式

* * 更新picodet example格式

* * 更新scrfd example格式

* * 更新ppseg rknpu2 python example中的错误

* * 修复代码格式问题

* * 修复代码格式问题

* * 修复代码格式问题

* * 修复代码格式问题

* * 修复代码格式问题

* * 修复代码格式问题

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-12 15:37:31 +08:00
DefTruth
5b54bcfb48 [ARM] fix VisSegmentation background error with bit ops (#852) 
* [NEON] fix visseg background error with bit ops

* [Bug Fix] fix build_android_aar.sh ci scripts

* [Bug Fix] fix VisSegmentationCommonCpu
 2022-12-12 09:54:08 +08:00
WJJ1995
8e13a38bf5 [Backend] Modify trt_max_batch_size the default value to 1 (#817) 
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

* Add Monitor for benchmark

* update mem monitor

* Set trt_max_batch_size default 1

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-11 14:16:37 +08:00
Zheng_Bicheng
c7dc7d5eee Add RKYOLOv5 RKYOLOX RKYOLOV7 (#709) 
* 更正代码格式

* 更正代码格式

* 修复语法错误

* fix rk error

* update

* update

* update

* update

* update

* update

* update

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-10 15:44:00 +08:00
shentanyue
3c05c74513 [Paddle Lite] Support stable-diffusion model (#830) 
* support stable-diffusion model for paddlelite

* update code
 2022-12-09 13:20:33 +08:00
MistEO
22325d23ed [Other] Add const modifier to some OCR interface parameters (#836) 
* [Other] Add const modifier to some OCR interface parameters

* [Other] Add a Predict interface to PPOCR with const parameters

For interface compatibility, I chose to add rather than modify
 2022-12-09 09:20:55 +08:00
yunyaoXYY
07833b7d79 [Bug Fix] Fix SortBoxes function for PPOCR det model (#814) 
* Imporve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Improve OCR Readme

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Add Initialize function to PP-OCR

* Make all the model links come from PaddleOCR

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Improve OCR readme

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add Readme for vision results

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add check for label file in postprocess of Rec model

* Add comments to create API docs

* Improve OCR comments

* Rename OCR and add comments

* Make sure previous python example works

* Make sure previous python example works

* Fix Rec model bug

* Fix Rec model bug

* Fix rec model bug

* Add SetTrtMaxBatchSize function for TensorRT

* Add SetTrtMaxBatchSize Pybind

* Add set_trt_max_batch_size python function

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Set TRT dynamic shape in PPOCR examples

* Fix PPOCRv2 python example

* Fix PPOCR dynamic input shape bug

* Remove useless code

* Fix PPOCR bug

* Remove useless comments  in PaddleSeg example

* Fix quantize docs readme

* Fix PP-OCRv2 readme

* Modify dynamic shape in PP-OCRv2 example

* Modify TRT dynamic shape for PP-OCRv2

* Fix sort box for det model

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-07 21:17:53 +08:00
Thomas Young
5df62485c3 [Bug Fix] add ocr new feature and fix codestyle (#764) 
* fix ocr bug and add new feature

* fix bug

* fix bug

* fix bug

* fix bug

* fix bug

* fix bug

* add property

* add test

* fix code style

* fix bug

* fix bug

* fix bug

* fix port

* fix ocr

* fix_ocr

* fix ocr

* fix ocr

* fix ocr

* fix ocr

* Update paddle2onnx.cmake

* Update paddle2onnx.cmake

* Update paddle2onnx.cmake

Co-authored-by: Jason <jiangjiajun@baidu.com>
Co-authored-by: Jason <928090362@qq.com>
 2022-12-07 19:31:54 +08:00
DefTruth
ffea55e038 [Bug Fix] add __aarch64__ to limit int64 in armv8 (#794) 2022-12-05 18:19:11 +08:00
yeliang2258
104d965b38 [Backend] Add YOLOv5、PPYOLOE and PP-Liteseg for RV1126 (#647) 
* add yolov5 and ppyoloe for rk1126

* update code, rename rk1126 to rv1126

* add PP-Liteseg

* update lite lib

* updade doc for PPYOLOE

* update doc

* fix docs

* fix doc and examples

* update code

* uodate doc

* update doc

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-05 16:48:00 +08:00
DefTruth
65f270df29 [FastTokenizer] Support FastTokenizer on Android (#783) 
* [FastTokenizer] Support FastTokenizer on Android

* [OMP] Add OMP bind_proc(close) policy

* [Android] Add Lite support for UIE

* [Android] Add VIS_SEG_OMP_NUM_THREADS
 2022-12-05 14:12:54 +08:00
WJJ1995
ea0bac4061 [Benchmark] Add GPU OpenVIVO Option in benchmark (#786) 
* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&&reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

* refactor yolov7

* add yolov7 testcase

* rm resize_after_load and add is_scale_up

* fixed bug

* set multi_label true

* optimize rvm preprocess

* optimizer rvm postprocess

* fixed bug

* deal with comments

* fixed bugs

* add gpu ov for benchmark

Co-authored-by: Jason <928090362@qq.com>
Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-05 10:51:13 +08:00
huangjianhui
a0caf9fbb7 [Doc] Update PaddleSeg comments (#785) 
* Update docs for wrong path

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update segmentation_result.md

* Update README.md

* Update README.md

* Update README.md

* Update PaddleSeg comments

Co-authored-by: Jason <928090362@qq.com>
 2022-12-05 10:14:35 +08:00
Jack Zhou
8c2d582925 [Backend]Add DisablePaddleTrtOPs (#788) 
* Add DisablePaddleTrtOPs

* Add delete_paddle_backend_pass disable_paddle_trt_ops pybind
 2022-12-05 10:03:52 +08:00
huangjianhui
6c31198342 [Other] Update deprecated segmentation apis && segmentation label map resize interinterpolation (#790) 
* Refactor PaddleSeg with preprocessor && postprocessor

* Fix bugs

* Delete redundancy code

* Modify by comments

* Refactor according to comments

* Add batch evaluation

* Add single test script

* Add ppliteseg single test script && fix eval(raise) error

* fix bug

* Fix evaluation segmentation.py batch predict

* Fix segmentation evaluation bug

* Fix evaluation segmentation bugs

* Update segmentation result docs

* Update old predict api and DisableNormalizeAndPermute

* Update resize segmentation label map with cv::INTER_NEAREST

Co-authored-by: Jason <jiangjiajun@baidu.com>
 2022-12-05 09:57:54 +08:00
Jack Zhou
d74e1209ae [Diffusion] Add StableDiffusionInpaint pipeline (#760) 
* Update Inpaint pipeline

* Update concat

* Add GaussianRandomKernel

* Update GaussianRandom

* Add vae endoder

* Add unet infer

* Add vae decoder predict

* add PrepareMaskAndMaskedImage

* Add imwrite

* Add time counter

* Fix pipeline

* use FDTensor move

* Fix scaled_linear dpm solver

* Add RGB2BGR
 2022-12-02 19:30:32 +08:00