v0.4.0 (15/12/2021)


  1. We release a new text recognition model - ABINet (CVPR 2021, Oral). With it dedicated model design and useful data augmentation transforms, ABINet can achieve the best performance on irregular text recognition tasks. Check it out!

  2. We are also working hard to fulfill the requests from our community. OpenSet KIE is one of the achievement, which extends the application of SDMGR from text node classification to node-pair relation extraction. We also provide a demo script to convert WildReceipt to open set domain, though it cannot take the full advantage of OpenSet format. For more information, please read our tutorial.

  3. APIs of models can be exposed through TorchServe. Docs

Breaking Changes & Migration Guide


Some refactoring processes are still going on. For all text detection models, we unified their decode implementations into a new module category, POSTPROCESSOR, which is responsible for decoding different raw outputs into boundary instances. In all text detection configs, the text_repr_type argument in bbox_head is deprecated and will be removed in the future release.

Migration Guide: Find a similar line from detection model’s config:


And replace it with

postprocessor=dict(type='{MODEL_NAME}Postprocessor', text_repr_type=xxx)),

Take a snippet of PANet’s config as an example. Before the change, its config for bbox_head looks like:

        in_channels=[128, 128, 128, 128],


    in_channels=[128, 128, 128, 128],
    postprocessor=dict(type='PANPostprocessor', text_repr_type='poly')),

There are other postprocessors and each takes different arguments. Interested users can find their interfaces or implementations in mmocr/models/textdet/postprocess or through our api docs.

New Config Structure

We reorganized the configs/ directory by extracting reusable sections into configs/_base_. Now the directory tree of configs/_base_ is organized as follows:

├── det_datasets
├── det_models
├── det_pipelines
├── recog_datasets
├── recog_models
├── recog_pipelines
└── schedules

Most of model configs are making full use of base configs now, which makes the overall structural clearer and facilitates fair comparison across models. Despite the seemingly significant hierarchical difference, these changes would not break the backward compatibility as the names of model configs remain the same.

New Features

  • Support openset kie by @cuhk-hbsun in

  • Add converter for the Open Images v5 text annotations by Krylov et al. by @baudm in

  • Support Chinese for kie show result by @cuhk-hbsun in

  • Add TorchServe support for text detection and recognition by @Harold-lkk in

  • Save filename in text detection test results by @cuhk-hbsun in

  • Add codespell pre-commit hook and fix typos by @gaotongxiao in

  • Avoid duplicate placeholder docs in CN by @gaotongxiao in

  • Save results to json file for kie. by @cuhk-hbsun in

  • Add SAR_CN to by @gaotongxiao in

  • mim extension for windows by @gaotongxiao in

  • Support muitiple pipelines for different datasets by @cuhk-hbsun in

  • ABINet Framework by @gaotongxiao in


  • Refactor textrecog config structure by @cuhk-hbsun in

  • Refactor text detection config by @cuhk-hbsun in

  • refactor transformer modules by @cuhk-hbsun in

  • refactor textdet postprocess by @cuhk-hbsun in


  • C++ example section by @apiaccess21 in

  • Chinese section by @A465539338 in

  • Add Chinese Translation of by @fatfishZhao in

  • Fix a model link and add the metafile for SATRN by @gaotongxiao in

  • Improve docs style by @gaotongxiao in

  • Enhancement & sync Chinese docs by @gaotongxiao in

  • TorchServe docs by @gaotongxiao in

  • Update docs menu by @gaotongxiao in

  • Docs for KIE CloseSet & OpenSet by @gaotongxiao in

  • Fix broken links by @gaotongxiao in

  • Docstring for text recognition models by @gaotongxiao in

  • Add MMFlow & MIM by @gaotongxiao in

  • Add MMFewShot by @gaotongxiao in

  • Update model readme by @gaotongxiao in

  • Add input size check to model_inference by @mpena-vina in

  • Docstring for textdet models by @gaotongxiao in

  • Add MMHuman3D in readme by @gaotongxiao in

  • Use shared menu from theme instead by @gaotongxiao in

  • Refactor docs structure by @gaotongxiao in

  • Docs fix by @gaotongxiao in


  • Use bounding box around polygon instead of within polygon by @alexander-soare in

  • Add CITATION.cff by @gaotongxiao in

  • Add py3.9 CI by @gaotongxiao in

  • update model-index.yml by @gaotongxiao in

  • Use container in CI by @gaotongxiao in

  • CircleCI Setup by @gaotongxiao in

  • Remove unnecessary custom_import from by @gaotongxiao in

  • Change the upper version of mmcv to 1.5.0 by @zhouzaida in

  • Update CircleCI by @gaotongxiao in

  • Pass custom_hooks to MMCV by @gaotongxiao in

  • Skip CI when some specific files were changed by @gaotongxiao in

  • Add markdown linter in pre-commit hook by @gaotongxiao in

  • Use shape from loaded image by @cuhk-hbsun in

  • Cancel previous runs that are not completed by @Harold-lkk in

Bug Fixes

  • Modify algorithm “sar” weights path in metafile by @ShoupingShan in

  • Fix Cuda CI by @gaotongxiao in

  • Fix image export in for KIE models by @gaotongxiao in

  • Allow invalid polygons in intersection and union by default by @gaotongxiao in

  • Update checkpoints’ links for SATRN by @gaotongxiao in

  • Fix converting to onnx bug because of changing key from img_shape to resize_shape by @Harold-lkk in

  • Fix PyTorch 1.6 incompatible checkpoints by @gaotongxiao in

  • Fix paper field in metafiles by @gaotongxiao in

  • Unify recognition task names in metafiles by @gaotongxiao in

  • Fix py3.9 CI by @gaotongxiao in

  • Always map location to cpu when loading checkpoint by @gaotongxiao in

  • Fix wrong model builder in recog_test_imgs by @gaotongxiao in

  • Improve dbnet r50 by fixing img std by @gaotongxiao in

  • Fix resource warning: unclosed file by @cuhk-hbsun in

  • Fix bug that same start_point for different texts in draw_texts_by_pil by @cuhk-hbsun in

  • Keep original texts for kie by @cuhk-hbsun in

  • Fix random seed by @gaotongxiao in

  • Fix DBNet_r50 config by @gaotongxiao in

  • Change SBC case to DBC case by @cuhk-hbsun in

  • Fix kie demo by @innerlee in

  • fix type check by @cuhk-hbsun in

  • Remove depreciated image validator in totaltext converter by @gaotongxiao in

  • Fix change locals() dict by @Fei-Wang in

  • fix #614: textsnake targets by @HolyCrap96 in

New Contributors

  • @alexander-soare made their first contribution in

  • @A465539338 made their first contribution in

  • @fatfishZhao made their first contribution in

  • @baudm made their first contribution in

  • @ShoupingShan made their first contribution in

  • @apiaccess21 made their first contribution in

  • @zhouzaida made their first contribution in

  • @mpena-vina made their first contribution in

  • @Fei-Wang made their first contribution in

Full Changelog:…0.4.0

v0.3.0 (25/8/2021)


  1. We add a new text recognition model – SATRN! Its pretrained checkpoint achieves the best performance over other provided text recognition models. A lighter version of SATRN is also released which can obtain ~98% of the performance of the original model with only 45 MB in size. (@2793145003) #405

  2. Improve the demo script,, which supports applying end-to-end text detection, text recognition and key information extraction models on images with easy-to-use commands. Users can find its full documentation in the demo section. (@samayala22, @manjrekarom) #371, #386, #400, #374, #428

  3. Our documentation is reorganized into a clearer structure. More useful contents are on the way! #409, #454

  4. The requirement of Polygon3 is removed since this project is no longer maintained or distributed. We unified all its references to equivalent substitutions in shapely instead. #448

Breaking Changes & Migration Guide

  1. Upgrade version requirement of MMDetection to 2.14.0 to avoid bugs #382

  2. MMOCR now has its own model and layer registries inherited from MMDetection’s or MMCV’s counterparts. (#436) The modified hierarchical structure of the model registries are now organized as follows.

mmcv.MODELS -> mmdet.NECKS -> NECKS
mmcv.MODELS -> mmdet.HEADS -> HEADS
mmcv.MODELS -> mmdet.LOSSES -> LOSSES

To migrate your old implementation to our new backend, you need to change the import path of any registries and their corresponding builder functions (including build_detectors) from mmdet.models.builder to mmocr.models.builder. If you have referred to any model or layer of MMDetection or MMCV in your model config, you need to add mmdet. or mmcv. prefix to its name to inform the model builder of the right namespace to work on.

Interested users may check out MMCV’s tutorial on Registry for in-depth explanations on its mechanism.

New Features

  • Automatically replace SyncBN with BN for inference #420, #453

  • Support batch inference for CRNN and SegOCR #407

  • Support exporting documentation in pdf or epub format #406

  • Support persistent_workers option in data loader #459

Bug Fixes

  • Remove depreciated key in #381

  • Fix dimension mismatch in batch testing/inference of DBNet #383

  • Fix the problem of dice loss which stays at 1 with an empty target given #408

  • Fix a wrong link in (@naarkhoo) #417

  • Fix undesired assignment to “pretrained” in #418

  • Fix a problem in polygon generation of DBNet #421, #443

  • Skip invalid annotations in totaltext_converter #438

  • Add zero division handler in poly utils, remove Polygon3 #448


  • Replace lanms-proper with lanms-neo to support installation on Windows (with special thanks to @gen-ko who has re-distributed this package!)

  • Support MIM #394

  • Add tests for PyTorch 1.9 in CI #401

  • Enables fullscreen layout in readthedocs #413

  • General documentation enhancement #395

  • Update version checker #427

  • Add copyright info #439

  • Update citation information #440


We thank @2793145003, @samayala22, @manjrekarom, @naarkhoo, @gen-ko, @duanjiaqi, @gaotongxiao, @cuhk-hbsun, @innerlee, @wdsd641417025 for their contribution to this release!

v0.2.1 (20/7/2021)


  1. Upgrade to use MMCV-full >= 1.3.8 and MMDetection >= 2.13.0 for latest features

  2. Add ONNX and TensorRT export tool, supporting the deployment of DBNet, PSENet, PANet and CRNN (experimental) #278, #291, #300, #328

  3. Unified parameter initialization method which uses init_cfg in config files #365

New Features

  • Support TextOCR dataset #293

  • Support Total-Text dataset #266, #273, #357

  • Support grouping text detection box into lines #290, #304

  • Add benchmark_processing script that benchmarks data loading process #261

  • Add SynthText preprocessor for text recognition models #351, #361

  • Support batch inference during testing #310

  • Add user-friendly OCR inference script #366

Bug Fixes

  • Fix improper class ignorance in SDMGR Loss #221

  • Fix potential numerical zero division error in DRRG #224

  • Fix installing requirements with pip and mim #242

  • Fix dynamic input error of DBNet #269

  • Fix space parsing error in LineStrParser #285

  • Fix textsnake decode error #264

  • Correct isort setup #288

  • Fix a bug in SDMGR config #316

  • Fix kie_test_img for KIE nonvisual #319

  • Fix metafiles #342

  • Fix different device problem in FCENet #334

  • Ignore improper tailing empty characters in annotation files #358

  • Docs fixes #247, #255, #265, #267, #268, #270, #276, #287, #330, #355, #367

  • Fix NRTR config #356, #370


  • Add backend for resizeocr #244

  • Skip image processing pipelines in SDMGR novisual #260

  • Speedup DBNet #263

  • Update mmcv installation method in workflow #323

  • Add part of Chinese documentations #353, #362

  • Add support for ConcatDataset with two workflows #348

  • Add list_from_file and list_to_file utils #226

  • Speed up sort_vertex #239

  • Support distributed evaluation of KIE #234

  • Add pretrained FCENet on IC15 #258

  • Support CPU for OCR demo #227

  • Avoid extra image pre-processing steps #375

v0.2.0 (18/5/2021)


  1. Add the NER approach Bert-softmax (NAACL’2019)

  2. Add the text detection method DRRG (CVPR’2020)

  3. Add the text detection method FCENet (CVPR’2021)

  4. Increase the ease of use via adding text detection and recognition end-to-end demo, and colab online demo.

  5. Simplify the installation.

New Features

Bug Fixes

  • Fix the duplicated point bug due to transform for textsnake #130

  • Fix CTC loss NaN #159

  • Fix error raised if result is empty in demo #144

  • Fix results missing if one image has a large number of boxes #98

  • Fix package missing in dockerfile #109


  • Simplify installation procedure via removing compiling #188

  • Speed up panet post processing so that it can detect dense texts #188

  • Add zh-CN README #70 #95

  • Support windows #89

  • Add Colab #147 #199

  • Add 1-step installation using conda environment #193 #194 #195

v0.1.0 (7/4/2021)


  • MMOCR is released.

Main Features

  • Support text detection, text recognition and the corresponding downstream tasks such as key information extraction.

  • For text detection, support both single-step (PSENet, PANet, DBNet, TextSnake) and two-step (MaskRCNN) methods.

  • For text recognition, support CTC-loss based method CRNN; Encoder-decoder (with attention) based methods SAR, Robustscanner; Segmentation based method SegOCR; Transformer based method NRTR.

  • For key information extraction, support GCN based method SDMG-R.

  • Provide checkpoints and log files for all of the methods above.

Read the Docs v: v0.4.0
On Read the Docs
Project Home

Free document hosting provided by Read the Docs.