9bd0177cff
[GCU] Update gcu config ( #14851 )
2025-03-17 19:31:37 +08:00
6778da99e2
feat(train): use naive_sync_bn with xpu device. ( #14849 )
...
* feat(train): use naive_sync_bn with xpu device.
* feat(train): use naive_sync_bn with xpu device.
2025-03-13 19:45:02 +08:00
78ec762aac
Fix typos ( #14800 )
2025-03-04 14:20:13 +08:00
f35dfef921
Fix ( #14795 )
2025-03-04 09:38:37 +08:00
1d52a2b2e1
fix OverflowError in text_visual func ( #14758 )
2025-02-26 15:38:16 +08:00
b18b656633
remove max inplace grad ( #14596 )
...
* remove max inplace grad
* update
2025-01-26 17:19:42 +08:00
b3e3588af9
repair train bug in multi gpu ( #14576 )
2025-01-22 11:04:01 +08:00
cf4c0591ba
repair bug in latexocr cpu infer and typo ( #14552 )
2025-01-16 15:56:13 +08:00
d523388ed1
Add pp formulanet ( #14429 )
...
* add ppformulanet
* rename loss
* modify doc
* add export code
* modify yaml for global ref
2024-12-23 13:14:33 +08:00
ae67d96f3e
add slanext models ( #14374 )
...
* add slanext models
* refine codes
* refine codes
* refine codes
2024-12-13 13:39:19 +08:00
78e7184022
add unimernet model ( #14357 )
...
* add unimernet model
* add commate and single test
* repair pytest
* delete export and infer
* delete [ file
2024-12-12 14:17:24 +08:00
c8874d717f
[GCU] Support inference for GCU ( #14142 )
2024-11-21 10:10:41 +08:00
fbba2178d7
update infer/utility.py to support json format model ( #14233 )
...
* update infer/utility.py to support json format model
* merge from #13524
* fix bug
* fix bug
* Update tools/infer/utility.py
Co-authored-by: jzhang533 <jzhang533@gmail.com>
* fix codestyle
---------
Co-authored-by: jzhang533 <jzhang533@gmail.com>
2024-11-18 14:00:58 +08:00
1d4e7a80a0
rename train result ( #14217 )
2024-11-13 15:49:52 +08:00
58e876d38d
[third-party] Fix the issue of inference errors with KE models in ONNX format ( #14138 )
...
* fix inference KIE model using onnx model
* fix code style
* fix onnx inputs compatiblility with det and rec
* fix code style
2024-11-02 00:14:34 +08:00
37e177595b
Allow `create_predictor` function to accept array of ONNX Execution Providers ( #14078 )
...
* pass onnx execution providers to create_predictor function
* added ability to provide onnxruntime SessionOptions
* added argument parser for onnx_sess_options
---------
Co-authored-by: ggolda <gleb.golda@streamlabs.com>
2024-10-25 20:21:39 +08:00
cba775412a
ix gpu memory growth ( #14037 )
2024-10-18 17:06:58 +08:00
ea7ba39f52
Update program.py ( #13989 )
...
avoid ZeroDivisionError when training.
2024-10-14 07:47:26 +08:00
596328d191
[NPU] cherrypick13983 ( #13984 )
...
* support sybn for npu
* fix code style
* fix code style
2024-10-12 18:46:33 +08:00
cda3e1201e
fix hubserving run error ( #13918 )
...
* fix hubserving run error
* Update paddleocr.py
2024-09-27 15:58:49 +08:00
2b51369324
support export after save model ( #13844 )
2024-09-25 01:11:01 +08:00
3cc4ae9f37
set --image_dir to be required ( #13896 )
2024-09-23 14:17:44 +08:00
1c8233d5bc
fix SRN algorithm infer error ( #13851 )
2024-09-11 19:16:30 +08:00
30811fba3c
Repair the bug in the inference script for LaTeX OCR ( #13750 )
...
* test
* dataprocess_abspath2relpath
* repair bug in infer/predict_rec for latexocr
2024-08-26 14:21:41 +08:00
5f0b90a110
Fix some issues with LaTeXOCR in paddleX ( #13646 )
...
* repair_some_Bug_for_paddlex
* style2
* style2
* add_epilson_for groupnorm
2024-08-14 11:30:25 +08:00
b6211b936b
support benchmark for paddlepaddle3.0 ( #13574 )
2024-08-02 19:24:40 +08:00
6c12df47b2
merge release/2.6.1 to main ( #13523 )
2024-07-29 19:09:42 +08:00
cf26f2330e
Latexocr paddle ( #13401 )
...
* commit_test
* modified: configs/rec/rec_latex_ocr.yml
deleted: ppocr/modeling/backbones/rec_resnetv2.py
* ntuple_solve
* style
* style
* style
* style
* style
* style
* style
* style
* style
* delete comment
* cla_email
2024-07-22 11:50:23 +08:00
5347be75f9
Update program.py ( #13389 )
...
refering to-https://www.paddlepaddle.org.cn/documentation/docs/en/api/paddle/incubate/ModelAverage_en.html
it should be paddle.incunate.ModelAverage and paddle.incubate.optimizer.ModelAverage
2024-07-15 21:48:26 +08:00
db0ad17cf6
fix slice op parameters not being passed correctly ( #13319 )
2024-07-09 17:13:41 +08:00
c95f6b2de7
optimize func: get_infer_gpuid ( #13275 )
...
* optimize func: get_infer_gpuid
* apply code review suggestion
2024-07-09 10:01:16 +08:00
6d5f998fe1
solve the onnxruntime inference issue ( #13154 )
2024-06-21 17:20:40 +08:00
86a447de9f
fix wrong function name ( #12826 )
...
AttributeError: module 'ntpath' has no attribute 'is_dir'. Did you mean: 'isdir'?
2024-06-09 10:23:24 +08:00
a764c560ba
Save recognition inference logs to file ( #12542 )
...
* Save recognition inference logs to file
* Formatted code with black
2024-05-31 09:36:34 +08:00
6e7a1b871d
Save detection inference logs to file ( #12042 )
...
* Save detection inference logs to file
* Minor fix on save_log_path
* Formatted with black
* If logger is None: get_logger()
2024-05-29 11:19:47 +08:00
ea29b423d5
fix and enable flake8 E721 ( #12258 )
2024-05-27 11:12:05 +08:00
965f569e81
added sliding window for large image inference ( #12152 )
...
added sliding window for large image inference
2024-05-24 16:16:37 +08:00
502e1675e4
Error with pyclipper inhomogeneous expanded array ( #12108 )
...
* pyclipper inhomogeneous expanded array solved
For some images, `np.array(offset.Execute(distance))` can result in inhomogeneous part of the detection box list, which cannot be casted into numpy array directly.
* corrected box reshape position
- box reshape was mistakenly done at line 145 which is now correctly done at line 92 of `db_postprocess.py`
- if box is empty then continue
* reverted mistakenly changed line 147
- reverted mistakenly changed `box.array(box)` to `np.array(box)`
* expanded array fix for `det_box_type=quad`
* polygons padding
For `--det_box_type = poly`, pad the detected polygon arrays if they have different shapes to ensure even shapes of polygon arrays
* fix codestyle
---------
Co-authored-by: Wang Xin <xinwang614@gmail.com>
2024-05-18 09:19:06 +08:00
a730065e7b
【OCR Issue No.9】以可选形式支持Visualdl ( #11947 )
...
* delete visual dl
* totally delete visual
* delete vdl file
* fix codestyle
2024-04-25 17:37:27 +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
3b6f117c44
Fix ( #11448 )
2024-01-02 11:02:13 +08:00
0382bfb02d
Optimize prediction on long image and deduplicate similar boxes with multiple lables ( #11366 )
...
* Handle conflict where a box is simultaneously recognized as multiple labels
* Split large height image recursively and process each with overlap to enhance performance
* Fix error when dt_box result is empty
* Add split operation on horizon side
* Slide on horizon may suffer line completeness, so that add more strict condition.
* Optimize recognition of overlap boxes.
2023-12-21 10:32:42 +08:00
317eac13b5
Add device check in check_gpu ( #11293 )
2023-12-06 11:12:58 +08:00
856ce76be3
Dygraph fix max_mem_reserved for benchmark ( #11341 )
...
* fix profile
* fix python3.10
* add max_mem_reserved for benchmark
* fix benchmark
2023-12-05 14:55:38 +08:00
317f56a3f4
Refine according to comment ( #11301 )
2023-11-24 16:50:34 +08:00
c8544d04ec
Fix bug when running on XPU ( #11299 )
2023-11-23 16:58:48 +08:00
a0901d2175
Dygraph【benchmark】add max_mem_reserved for benchmark ( #11284 )
...
* fix profile
* fix python3.10
* add max_mem_reserved for benchmark
2023-11-22 20:11:14 +08:00
fb38d0be18
fix SAR inference, when batch size>1, norm_img_batch and valid_ratios shapes do not match ( #11238 )
2023-11-15 10:02:03 +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
d0d77fe273
Fixed a bug where changing "max_text_length" for VisionLAN did not change the length of the output text ( #11025 )
2023-10-12 11:07:07 +08:00
EnflameGCU
Jonathans575
co63oc
Wang Xin
hong
liuhongen1234567
Liu Jiaxuan
zhangyubo0722
Alex
Salmondx
lona-cn
wangna11BD
changdazhou
Manik Singh Sarmaal
CaiRan
enximi
Alex Pasquali
aspaul20
Sanjay Rijal
张春乔
marswen
TracebaK
gmm
RuohengMa
Alexnet
shiyutang
Viktor Bordiuzha