Mindocr

2. Add New Models
LayoutXLM SER
TableMaster
4. Bug fixes
[PR632] fix PP-OCRv3 DBNet and SVTR param maps
[PR633] improve training speed of LayoutXLM and VI-LayoutXLM
[PR634] revise homepage readme for r0.3
[PR638] partial refactoring of py_infer & OCRServer
[PR642] Fix bugs of kie loss
[PR645] fix log print with loss inf

2. Add New Models
YOLOv8 nano-based layout analysis algorithm
LayoutXLM SER
VI-LayoutXLM SER
PP-OCRv3 DBNet and SVTR
3. Offline Inference
Support YOLOv8 nano-based layout analysis on Ascend 310
Support PP-OCRv4 (third-party model) text detection and recognition on Ascend 310
4. Support Multi-specification Ascend 910
DBNet ResNet-50
DBNet++ ResNet-50
CRNN VGG7
SVTR-Tiny
FCENet
ABINet
5. Bug fixes
[PR587] Fix the performance degradation issues on PyNative mode
[PR601] Fix the layout issues of visualization results when the text is vertical
[PR618] Avoid loading ckpt abundantly by revise yaml file of DBNet
[PR620] Fix the precision issues of PP-OCRv3 offline inference
[PR622] Fix some error URL address on the readme
[PR627] Fix the bug that CPU usage is too high in some offline inference scenarios

What's Changed
* tools for model exporting and converting by horcham in https://github.com/mindspore-lab/mindocr/pull/639
* add SVTR-Tiny 8p training by tonytonglt in https://github.com/mindspore-lab/mindocr/pull/660
* add DBNet++ ResNet50 icdar2015 8p training by tonytonglt in https://github.com/mindspore-lab/mindocr/pull/661
* Fix problems of psenet-ctw1500 training and others by horcham in https://github.com/mindspore-lab/mindocr/pull/664
* revise whl deploy setting and version info by panshaowu in https://github.com/mindspore-lab/mindocr/pull/658
* add minddata functions by chengtianwu in https://github.com/mindspore-lab/mindocr/pull/667
* Remove dependency of mindformers by horcham in https://github.com/mindspore-lab/mindocr/pull/666
* revise the readme of CRNN by panshaowu in https://github.com/mindspore-lab/mindocr/pull/672
* fix data bug by chengtianwu in https://github.com/mindspore-lab/mindocr/pull/673
* Bugfix of modelarts by Bourn3z in https://github.com/mindspore-lab/mindocr/pull/671
* update readme of SVTR by tonytonglt in https://github.com/mindspore-lab/mindocr/pull/681
* support Vary Toy infer by panshaowu in https://github.com/mindspore-lab/mindocr/pull/680
* Bugfix of svtr when the input is FP16 or FP32 for MindSpore r2.3rc1 by Bourn3z in https://github.com/mindspore-lab/mindocr/pull/686
* Update FAQ & Add paddle2mindir & Update ppocrv4 config file by horcham in https://github.com/mindspore-lab/mindocr/pull/685
* Bugfix for crnn when amp_level is O0 by Bourn3z in https://github.com/mindspore-lab/mindocr/pull/688
* Bugfix crnn by Bourn3z in https://github.com/mindspore-lab/mindocr/pull/689
* Add LayoutLMv3 backbone by Bourn3z in https://github.com/mindspore-lab/mindocr/pull/656
* Add docker to readme by horcham in https://github.com/mindspore-lab/mindocr/pull/695
* 310p export bug fix by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/699
* fix deprecated numpy int and bool by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/704
* set jit_level to O2 under graph mode by Mark-ZhouWX in https://github.com/mindspore-lab/mindocr/pull/705
* Revert "set jit_level to O2 under graph mode (705)" by Mark-ZhouWX in https://github.com/mindspore-lab/mindocr/pull/706
* abinet set context by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/709
* fix svtr_tiny 8p loss except by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/715
* update readme about device description by Mark-ZhouWX in https://github.com/mindspore-lab/mindocr/pull/720
* add 910* test result by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/719
* change ci config by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/722
* add jit config level O2 for training scripts to support ms 2.3.0 version by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/721
* remove device type from version table by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/723
* set svtr config drop_overflow_update True by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/724
* fix ops masked_fill by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/725
* fix bug litmit_side_len to master by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/729
* update github.io docs by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/730
* remove required package lanms for Windows by Hsiayukoo in https://github.com/mindspore-lab/mindocr/pull/732
* 修改 lanms 包安装的判定条件 by Hsiayukoo in https://github.com/mindspore-lab/mindocr/pull/740
* fix check_cpplint by hongziqi in https://github.com/mindspore-lab/mindocr/pull/747
* update tablemasterhead network by hongziqi in https://github.com/mindspore-lab/mindocr/pull/746
* fix bug in ops.masked_fill by updating finfo func by hongziqi in https://github.com/mindspore-lab/mindocr/pull/748
* update lite inference doc by CaitinZhao in https://github.com/mindspore-lab/mindocr/pull/751
* update Lite thirdparty_models_list by iugoood in https://github.com/mindspore-lab/mindocr/pull/752
* 基于CCPD的车牌号检测和识别案例 by Xv-M-S in https://github.com/mindspore-lab/mindocr/pull/744
* 修正ch_pp_det_OCRv4 config.txt 链接 by iugoood in https://github.com/mindspore-lab/mindocr/pull/754
* update Lite mindocr_models_list by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/753
* Support rectangle in draw_boxes and relocate draw_ser_results by hongziqi in https://github.com/mindspore-lab/mindocr/pull/755
* fix links in doc by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/759
* support table structure model inference by hongziqi in https://github.com/mindspore-lab/mindocr/pull/764
* update doc about table model by hongziqi in https://github.com/mindspore-lab/mindocr/pull/766
* Add online layout model prediction by can-gaa-hou in https://github.com/mindspore-lab/mindocr/pull/765
* 基于MindOCR的车牌识别 by Xv-M-S in https://github.com/mindspore-lab/mindocr/pull/760
* fix dbnet eval on ctw1500 by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/771
* Adding end-to-end prediction by can-gaa-hou in https://github.com/mindspore-lab/mindocr/pull/772
* Revert "Adding end-to-end prediction" by CaitinZhao in https://github.com/mindspore-lab/mindocr/pull/774
* Add end-to-end prediction(layout-table/ocr-recovery) by hongziqi in https://github.com/mindspore-lab/mindocr/pull/775
* Update readme by ChongWei905 in https://github.com/mindspore-lab/mindocr/pull/768
* docs: add missed form in README_CN by ChongWei905 in https://github.com/mindspore-lab/mindocr/pull/779
* 新增Layoutlmv3 on publaynet by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/773
* support cls predict module by zhangjunlongtech in https://github.com/mindspore-lab/mindocr/pull/769
* revise document of license plate demo by panshaowu in https://github.com/mindspore-lab/mindocr/pull/776
* Add 2.4.0 information to the LayoutLMv3 readme by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/783
* update config to add argument:ser_class_dict_path by hongziqi in https://github.com/mindspore-lab/mindocr/pull/786
* use default ser ckpt in vi_layoutxlm_ser by hongziqi in https://github.com/mindspore-lab/mindocr/pull/789
* fix docs by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/793
* update rec models Readme and fix master_resnet31 bug by iugoood in https://github.com/mindspore-lab/mindocr/pull/794
* update readme by kk928290341 in https://github.com/mindspore-lab/mindocr/pull/790
* Delete det FCENet and update det 910* results. by Bruce-py in https://github.com/mindspore-lab/mindocr/pull/796
* Update lanms to lanms-nova by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/805
* Update det dbnet README by Bruce-py in https://github.com/mindspore-lab/mindocr/pull/803
* change repeat to repeat_interleave by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/792
* fix pse_ctw1500 training error by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/806
* fix synthText dataset convert by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/807
* Fix docs by Bruce-py in https://github.com/mindspore-lab/mindocr/pull/811
* svtr_tiny 性能优化 和 修改多卡启动方式为msrun by iugoood in https://github.com/mindspore-lab/mindocr/pull/810
* v0.5.0 adaption by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/813
* v0.5.0 link adaption by alien-0119 in https://github.com/mindspore-lab/mindocr/pull/814
* update set_context API for ms2.5 version by Ash-Lee233 in https://github.com/mindspore-lab/mindocr/pull/816
* fix set_device twice bug by Ash-Lee233 in https://github.com/mindspore-lab/mindocr/pull/818

New Contributors
* Mark-ZhouWX made their first contribution in https://github.com/mindspore-lab/mindocr/pull/705
* hongziqi made their first contribution in https://github.com/mindspore-lab/mindocr/pull/747
* Xv-M-S made their first contribution in https://github.com/mindspore-lab/mindocr/pull/744
* can-gaa-hou made their first contribution in https://github.com/mindspore-lab/mindocr/pull/765
* zhangjunlongtech made their first contribution in https://github.com/mindspore-lab/mindocr/pull/769

**Full Changelog**: https://github.com/mindspore-lab/mindocr/compare/v0.3.1...v0.5.0

What's Changed
* detection tutorials [WIP] by wtomin in https://github.com/mindspore-lab/mindocr/pull/398
* [fix] Update README_CN.md by heepengpeng in https://github.com/mindspore-lab/mindocr/pull/423
* [fix] bug fix by heepengpeng in https://github.com/mindspore-lab/mindocr/pull/424
* Accelerate ppocr PSENet and add modify onnx script by VictorHe-1 in https://github.com/mindspore-lab/mindocr/pull/392
* Modify device_id setting way to avoid ambiguity while setting device_id by env variable or yaml by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/425
* Add DBNet and DBNet++ API docs by hadipash in https://github.com/mindspore-lab/mindocr/pull/421
* update tutorials by Songyuanwei in https://github.com/mindspore-lab/mindocr/pull/420
* update infer readme by liangxhao in https://github.com/mindspore-lab/mindocr/pull/426
* update infer readme url by liangxhao in https://github.com/mindspore-lab/mindocr/pull/427
* add MindSpore compile related to git ignore list by zhtmike in https://github.com/mindspore-lab/mindocr/pull/431
* modify print to logger by Songyuanwei in https://github.com/mindspore-lab/mindocr/pull/429
* ppocr psenet modify script update by VictorHe-1 in https://github.com/mindspore-lab/mindocr/pull/432
* allow to run inference on images located in multiple subdirectories by hadipash in https://github.com/mindspore-lab/mindocr/pull/433
* Build mindocr online doc webpage by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/393
* Add API docstring for psenet by VictorHe-1 in https://github.com/mindspore-lab/mindocr/pull/434
* fix the logging in construct part and clean content expression by zhtmike in https://github.com/mindspore-lab/mindocr/pull/437
* fix infer readme by liangxhao in https://github.com/mindspore-lab/mindocr/pull/439
* update inference model list in online docs by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/441
* add fcenet by colawyee in https://github.com/mindspore-lab/mindocr/pull/412
* callbacks revision: allow group lr and correct the logging for resuming training by wtomin in https://github.com/mindspore-lab/mindocr/pull/386
* [feat] change visual to ppocr by heepengpeng in https://github.com/mindspore-lab/mindocr/pull/436
* remove axes and white margins around images in the inference mode by hadipash in https://github.com/mindspore-lab/mindocr/pull/440
* fix infer postprocess init by liangxhao in https://github.com/mindspore-lab/mindocr/pull/442
* update modelzoo by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/449
* fix infer model list readme by liangxhao in https://github.com/mindspore-lab/mindocr/pull/445
* fix bugs in aicc and docs by SamitHuang in https://github.com/mindspore-lab/mindocr/pull/451
* optim some infer yaml, readme and parallel by liangxhao in https://github.com/mindspore-lab/mindocr/pull/450
* update modelzoo by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/454
* update distributed training docs by wtomin in https://github.com/mindspore-lab/mindocr/pull/443
* Fix infer det bug for PSENet ic15 by VictorHe-1 in https://github.com/mindspore-lab/mindocr/pull/463
* [fix] fix style error by heepengpeng in https://github.com/mindspore-lab/mindocr/pull/464
* 规范变量名称 by colawyee in https://github.com/mindspore-lab/mindocr/pull/455
* Add Master Model by zhtmike in https://github.com/mindspore-lab/mindocr/pull/446
* Add RARE MindIR by zhtmike in https://github.com/mindspore-lab/mindocr/pull/448
* fix logger in callback by zhtmike in https://github.com/mindspore-lab/mindocr/pull/457
* update infer models list by liangxhao in https://github.com/mindspore-lab/mindocr/pull/456
* update readme fps by Songyuanwei in https://github.com/mindspore-lab/mindocr/pull/452
* Update readme by SamitHuang in https://github.com/mindspore-lab/mindocr/pull/465
* Fix error during loss reduce in callback by zhtmike in https://github.com/mindspore-lab/mindocr/pull/469
* Remove and Replace Unnecessary Augmentations by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/461
* update fcenet readme by colawyee in https://github.com/mindspore-lab/mindocr/pull/472
* modify logger, add logger_set level by Songyuanwei in https://github.com/mindspore-lab/mindocr/pull/467
* Fix empty images eval by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/460
* DBNet: follow loss naming convention by hadipash in https://github.com/mindspore-lab/mindocr/pull/466
* update fps log printing to avoid ambiguity by HaoyangLee in https://github.com/mindspore-lab/mindocr/pull/471
* add 13 new dataset converters by hadipash in https://github.com/mindspore-lab/mindocr/pull/376
* linting fix by hadipash in https://github.com/mindspore-lab/mindocr/pull/473
* RARE and SVTR docstring by zhtmike in https://github.com/mindspore-lab/mindocr/pull/400
* Fix dataset docs by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/474
* fix datasets docs by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/476
* Add size limits to RandomScale transform by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/462
* visionlan gpu updates by wtomin in https://github.com/mindspore-lab/mindocr/pull/459
* Replace deprecated ResizeBilinear for EAST by VictorHe-1 in https://github.com/mindspore-lab/mindocr/pull/479
* Move save config before training start log by zhtmike in https://github.com/mindspore-lab/mindocr/pull/478
* update Fcenet readme by colawyee in https://github.com/mindspore-lab/mindocr/pull/475
* Add RobustScanner rec model by tonytonglt in https://github.com/mindspore-lab/mindocr/pull/444
* Fix docs links by ShahJahanIshaq in https://github.com/mindspore-lab/mindocr/pull/477
* optim performance and cls/rec batchsize for inference by liangxhao in https://github.com/mindspore-lab/mindocr/pull/480
* update readme for supporting RobustScanner by tonytonglt in https://github.com/mindspore-lab/mindocr/pull/487
* add ABINet [WIP, don't merge yet] by safeandnewYH in https://github.com/mindspore-lab/mindocr/pull/385
* update version to 0.2.0 by jianyunchao in https://github.com/mindspore-lab/mindocr/pull/490

New Contributors
* ShahJahanIshaq made their first contribution in https://github.com/mindspore-lab/mindocr/pull/461
* safeandnewYH made their first contribution in https://github.com/mindspore-lab/mindocr/pull/385

**Full Changelog**: https://github.com/mindspore-lab/mindocr/compare/v0.1.1...v0.2.0