270ce8aa79
bugfixed: import error ( #13994 )
...
Co-authored-by: guangpin.ye <guangpin.ye@lpht.com>
2024-10-14 16:10:12 +08:00
e9fca96d4f
rename MKLDNN to OneDNN ( #13757 )
...
[Windows Inference Library (version 3.0.0-beta1) - MKL](https://www.paddlepaddle.org.cn/inference/master/guides/install/download_lib.html#windows ) renames the mkldnn folder to onednn.
2024-08-27 12:52:00 +08:00
cab3fcbcdf
fix: 'numpy' has no attribute 'astype' ( #13554 )
2024-07-31 12:36:31 +08:00
192300837f
Fix cpp_infer "--enable_mkldnn=false" not effective ( #13539 )
...
* Fix "--enable_mkldnn=false" not effective
When using the --enable_mkldnn command line option, MKLDNN should be enabled when set to true and disabled when set to false. But, using the PaddlePaddle v3.0.0-beta1 inference library, the --enable_mkldnn=false option did not work as expected, causing MKLDNN to remain enabled regardless of the setting.
This commit adds a call to `config.DisableMKLDNN()` in the else branch to explicitly disable MKLDNN when `--enable_mkldnn=false` is set.
* fix code style: clang-format
2024-07-29 17:01:40 +08:00
335c5c247f
[doc] fixing broken links and updating paddle2onnx usage descriptions ( #12749 )
...
* [docs]:添加了对于Paddle2ONNX模型转化中选项--input_shape_dict的解释说明与解决方法
* Update readme_ch.md
[docs]:使用onnxsim修改input_shape可以兼容paddlepaddle现版本
* Update readme_ch.md
修改了不恰当的相关描述
* Rename inference_ch.md to inference.md
修改了中文版模型导出说明inference_ch.md命名为inference.md
* Update readme_ch.md
修改不恰当表述
* Update readme_ch.md
修改所有python3.7为python3
* update readme
---------
Co-authored-by: Wang Xin <xinwang614@gmail.com>
2024-06-09 22:56:32 +08:00
24f06d1a1b
update common pre-commit configs and commit the results of running pre-commit run -a ( #12516 )
2024-05-29 15:26:09 +08:00
a2ad2124c7
commit fix by running pre-commit run -a ( #12165 )
2024-05-24 12:12:42 +08:00
af87691591
add ci for paddleocr test ( #12062 )
...
* add ci for paddleocr test
* fix flake8 error
* fix paddlepaddle deps
* add dep
* fix
* move flake8 to pre-commit
* update ut
* fix bug
* fix bug set paddlepaddle==2.5
* fix bug
* fix bug
* fix bug
* update test
* remove lscpu
2024-05-22 13:02:24 +08:00
045e5f6ac7
add pre-commit workflow ( #11973 )
...
* add pre-commit workflow
* run 'pre-commit run --all-files'
* setup python version
2024-04-21 21:46:20 +08:00
19144429e6
update link mentioned at #11763 ( #11764 )
2024-03-27 17:29:47 +08:00
448ee6bec1
[Feature]Complete the ppocrv4_act ( #11345 )
...
* ppocrv4_act
* update
* fix bugs when run act on ppocrv4_dedt_server
* modify act config files
* modify test code and update results
* 新增数据处理的脚本
* fix
* Add batch testing script
* fix
* fix
* fix
* update det_server inference on tesla v100
* update model urls
---------
Co-authored-by: tangshiyu <tangshiyu@baidu.com>
2024-01-19 11:12:25 +08:00
3b6f117c44
Fix ( #11448 )
2024-01-02 11:02:13 +08:00
49ef54ee3c
chore: add notes for docker gpu deploy PP-OCRv4 ( #11390 )
...
* chore: add notes for docker gpu deploy PP-OCRv4
* chore: add notes for docker gpu deploy PP-OCRv4
* Update Dockerfile
2024-01-02 10:49:32 +08:00
e3fc6393e0
[Cherry-pick] Cherry-pick from release/2.6 ( #11092 )
...
* Update recognition_en.md (#10059 )
ic15_dict.txt only have 36 digits
* Update ocr_rec.h (#9469 )
It is enough to include preprocess_op.h, we do not need to include ocr_cls.h.
* 补充num_classes注释说明 (#10073 )
ser_vi_layoutxlm_xfund_zh.yml中的Architecture.Backbone.num_classes所赋值会设置给Loss.num_classes，
由于采用BIO标注，假设字典中包含n个字段（包含other）时，则类别数为2n-1;假设字典中包含n个字段（不含other）时，则类别数为2n+1。
* Update algorithm_overview_en.md (#9747 )
Fix links to super-resolution algorithm docs
* 改进文档`deploy/hubserving/readme.md`和`doc/doc_ch/models_list.md` (#9110 )
* Update readme.md
* Update readme.md
* Update readme.md
* Update models_list.md
* trim trailling spaces @ `deploy/hubserving/readme_en.md`
* `s/shell/bash/` @ `deploy/hubserving/readme_en.md`
* Update `deploy/hubserving/readme_en.md` to sync with `deploy/hubserving/readme.md`
* Update deploy/hubserving/readme_en.md to sync with `deploy/hubserving/readme.md`
* Update deploy/hubserving/readme_en.md to sync with `deploy/hubserving/readme.md`
* Update `doc/doc_en/models_list_en.md` to sync with `doc/doc_ch/models_list_en.md`
* using Grammarly to weak `deploy/hubserving/readme_en.md`
* using Grammarly to tweak `doc/doc_en/models_list_en.md`
* `ocr_system` module will return with values of field `confidence`
* Update README_CN.md
* 修复测试服务中图片转Base64的引用地址错误。 (#8334 )
* Update application.md
* [Doc] Fix 404 link. (#10318 )
* Update PP-OCRv3_det_train.md
* Update knowledge_distillation.md
* Update config.md
* Fix fitz camelCase deprecation and .PDF not being recognized as pdf file (#10181 )
* Fix fitz camelCase deprecation and .PDF not being recognized as pdf file
* refactor get_image_file_list function
* Update customize.md (#10325 )
* Update FAQ.md (#10345 )
* Update FAQ.md (#10349 )
* Don't break overall processing on a bad image (#10216 )
* Add preprocessing common to OCR tasks (#10217 )
Add preprocessing to options
* [MLU] add mlu device for infer (#10249 )
* Create newfeature.md
* Update newfeature.md
* remove unused imported module, so can avoid PyInstaller packaged binary's start-time not found module error. (#10502 )
* CV套件建设专项活动 - 文字识别返回单字识别坐标 (#10515 )
* modification of return word box
* update_implements
* Update rec_postprocess.py
* Update utility.py
* Update README_ch.md
* revert README_ch.md update
* Fixed Layout recovery README file (#10493 )
Co-authored-by: Shubham Chambhare <shubhamchambhare@zoop.one>
* update_doc
* bugfix
---------
Co-authored-by: ChuongLoc <89434232+ChuongLoc@users.noreply.github.com>
Co-authored-by: Wang Xin <xinwang614@gmail.com>
Co-authored-by: tanjh <dtdhinjapan@gmail.com>
Co-authored-by: Louis Maddox <lmmx@users.noreply.github.com>
Co-authored-by: n0099 <n@n0099.net>
Co-authored-by: zhenliang li <37922155+shouyong@users.noreply.github.com>
Co-authored-by: itasli <ilyas.tasli@outlook.fr>
Co-authored-by: UserUnknownFactor <63057995+UserUnknownFactor@users.noreply.github.com>
Co-authored-by: PeiyuLau <135964669+PeiyuLau@users.noreply.github.com>
Co-authored-by: kerneltravel <kjpioo2006@gmail.com>
Co-authored-by: ToddBear <43341135+ToddBear@users.noreply.github.com>
Co-authored-by: Ligoml <39876205+Ligoml@users.noreply.github.com>
Co-authored-by: Shubham Chambhare <59397280+Shubham654@users.noreply.github.com>
Co-authored-by: Shubham Chambhare <shubhamchambhare@zoop.one>
Co-authored-by: andyj <87074272+andyjpaddle@users.noreply.github.com>
2023-10-18 17:37:23 +08:00
549376ead5
[Cherry-pick] #10441 #10512 ( #10593 )
...
* fix memory leak (#10441 )
* fix memory leak
* update: Using smart pointers instead of raw pointers
* update: Usinig intuitive initialization of duration (#10512 )
2023-08-14 10:14:43 +08:00
2d44a71b20
Toward Devkit Consistency ( #10150 )
...
* Accommodate UAPI
* Fix signal handler
* Save model.pdopt
* Change variable name
* Update vdl dir
2023-06-14 14:31:45 +08:00
c9e8ce5c24
[FastDeploy] Improve readme ( #9510 )
...
* Fix padding value in rec model, and box sort in det model
* Add FastDeploy support to deploy PaddleOCR models.
* Improve readme
* improve readme
* improve readme
* improve code
* improve readme
* improve readme and format
* improve readme and format
* improve readme and format
* improve readme
* improve readme
* improve readme
2023-03-23 10:59:08 +08:00
e1704f4613
[FastDeploy] Improve readme and code format. ( #9478 )
...
* Fix padding value in rec model, and box sort in det model
* Add FastDeploy support to deploy PaddleOCR models.
* Improve readme
* improve readme
* improve readme
* improve code
* improve readme
* improve readme and format
* improve readme and format
* improve readme and format
* improve readme
* improve readme
2023-03-21 11:13:43 +08:00
6001b1a07b
[FastDeploy] Improve Readme and API. ( #9441 )
...
* Fix padding value in rec model, and box sort in det model
* Add FastDeploy support to deploy PaddleOCR models.
* Improve readme
* improve readme
* improve readme
* improve code
* improve readme
2023-03-17 13:22:36 +08:00
08c8da5352
[FastDeploy] Improve fastdeploy code and readme ( #9379 )
...
* Fix padding value in rec model, and box sort in det model
* Add FastDeploy support to deploy PaddleOCR models.
* Improve readme
* improve readme
* improve readme
* improve code
2023-03-13 14:03:59 +08:00
a27bb180cf
[FastDeploy] Add FastDeploy support to deploy PaddleOCR models. ( #9260 )
...
* Fix padding value in rec model, and box sort in det model
* Add FastDeploy support to deploy PaddleOCR models.
* Improve readme
* improve readme
2023-03-03 14:51:09 +08:00
6cbd7d1ece
[doc] fix doc ( #8935 )
...
* support min_area_rect crop
* add check_install
* fix requirement.txt
* fix check_install
* add lanms-neo for drrg
* fix
* fix doc
* fix
* support set gpu_id when inference
* fix #8855
* fix #8855
* opt slim doc
* fix doc bug
2023-02-01 09:53:47 +08:00
9059f747e6
support new version of numpy ( #8921 )
...
* add finetune en doc & test=document_fix
* fix dead link & test=document_fix
* fix dead link & test=document_fix
* update check img
* fix det res dtype
* update args default type & test=document_fix
* fix numpy version
* support numpy1.24.0
2023-01-30 16:05:14 +08:00
5aff7e6362
Fix padding value in rec model, and box sort in det model ( #8552 )
2022-12-26 10:51:22 +08:00
414bf18a20
fix issue 9659 and doc ( #8690 )
2022-12-23 10:02:45 +08:00
5cac747656
[bug] fix issues about sort_function and DB Head ( #8580 )
...
* support min_area_rect crop
* add check_install
* fix requirement.txt
* fix check_install
* add lanms-neo for drrg
* fix
* fix doc
* fix
2022-12-13 16:26:42 +08:00
70987157a6
Update requirements.txt
2022-11-15 19:11:27 +08:00
f283516850
Merge pull request #8030 from LDOUBLEV/dygraph
...
[doc] fix typo and refine doc for paddle.js deploy
2022-10-26 10:40:15 +08:00
54d102add6
refine doc for paddle.js
2022-10-26 10:25:56 +08:00
b3241534db
Merge pull request #8091 from WenmuZhou/cpp_infer2
...
fix cls diff with python
2022-10-25 17:56:50 +08:00
2c1747b638
fix cls diff with python
2022-10-25 08:38:42 +00:00
32b6ca4f4a
Update readme.md
2022-10-10 13:08:27 +08:00
46d639a1b5
updata paddle2onnx en doc
2022-10-10 12:08:10 +08:00
8cbb4fce6a
updata paddle2onnx en doc
2022-10-10 10:55:53 +08:00
c9ab4e6647
updata paddle2onnx en doc
2022-10-10 10:54:00 +08:00
60559a7ec1
add ser+re hub serving ( #7844 )
...
* add ser+re hub serving
* fix
2022-10-09 13:28:12 +08:00
dd9f48da2e
fix bug
2022-09-20 03:40:05 +00:00
b913f66403
update docs
2022-09-19 13:29:57 +00:00
43838e3e9f
add trt shape file to table and layout model
2022-09-19 11:39:22 +00:00
a166e54aca
add default value
2022-09-19 11:00:42 +00:00
bb0955dd95
Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into cpp_infer
2022-09-19 10:58:31 +00:00
603f234bcc
add layout
2022-09-19 09:37:41 +00:00
1b07e42912
fix trt
2022-09-16 20:11:18 +08:00
31a84a33d8
support dynamic trt
2022-09-16 15:01:32 +08:00
50e3bacd32
fix slim doc
2022-09-16 12:05:42 +08:00
bc324341d6
add ppocrv3 for lite deploy readme
2022-09-16 11:54:15 +08:00
b6c0db3b82
Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into kl_pact
2022-09-14 17:01:45 +08:00
541954da52
add layoutxml kl he pact
2022-09-14 15:30:30 +08:00
4589f51b5c
fix ( #7587 )
2022-09-14 10:26:27 +08:00
2cfb23cf05
fix table cpp infer bug ( #7550 )
...
* fix table cpp infer bug
* change default tale dict to ch
* update doc
* update vis
2022-09-10 22:45:35 +08:00
Yes
achieve_dream
laolitou
hiroi-sora
Xu Jiakang
jzhang533
Wang Xin
Ran chongzhi
co63oc
sheiy
shiyutang
moehuster
Lin Manhui
yunyaoXYY
Double_V
andyj
Evezerest
LDOUBLEV
WenmuZhou
tink2123
littletomatodonkey
zhoujun