**The default branch is now `main` and the code on the branch has been switched to v1.0.0. The old `main` branch (v0.6.3) code now exists on the `0.x` branch.** If you have been using the `main` branch and encounter upgrade issues, please read the [Migration Guide](https://mmocr.readthedocs.io/en/dev-1.x/migration/overview.html) and notes on [Branches](https://mmocr.readthedocs.io/en/dev-1.x/migration/branches.html) .
1. Two new models, ABCNet v2 (inference only) and SPTS are added to `projects/` folder.
2. Announcing `Inferencer`, a unified inference interface in OpenMMLab for everyone's easy access and quick inference with all the pre-trained weights. [Docs](https://mmocr.readthedocs.io/en/dev-1.x/user_guides/inference.html)
3. Users can use test-time augmentation for text recognition tasks. [Docs](https://mmocr.readthedocs.io/en/dev-1.x/user_guides/train_test.html#test-time-augmentation)
4. Support [batch augmentation](https://openaccess.thecvf.com/content_CVPR_2020/papers/Hoffer_Augment_Your_Batch_Improving_Generalization_Through_Instance_Repetition_CVPR_2020_paper.pdf) through [`BatchAugSampler`](https://github.com/open-mmlab/mmocr/pull/1757), which is a technique used in SPTS.
5. Dataset Preparer has been refactored to allow more flexible configurations. Besides, users are now able to prepare text recognition datasets in LMDB formats. [Docs](https://mmocr.readthedocs.io/en/dev-1.x/user_guides/data_prepare/dataset_preparer.html#lmdb-format)
6. Some textspotting datasets have been revised to enhance the correctness and consistency with the common practice.
7. Potential spurious warnings from `shapely` have been eliminated.
Read [Changelog](https://mmocr.readthedocs.io/en/dev-1.x/notes/changelog.html) for more details!
MMOCR is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction. It is part of the [OpenMMLab](https://openmmlab.com/) project.
The modular design of MMOCR enables users to define their own optimizers, data preprocessors, and model components such as backbones, necks and heads as well as losses. Please refer to [Overview](https://mmocr.readthedocs.io/en/dev-1.x/get_started/overview.html) for how to construct a customized model.
The toolbox provides a comprehensive set of utilities which can help users assess the performance of models. It includes visualizers which allow visualization of images, ground truths as well as predicted bounding boxes, and a validation tool for evaluating checkpoints during training. It also includes data converters to demonstrate how to convert your own data to the annotation files which the toolbox supports.
MMOCR depends on [PyTorch](https://pytorch.org/), [MMEngine](https://github.com/open-mmlab/mmengine), [MMCV](https://github.com/open-mmlab/mmcv) and [MMDetection](https://github.com/open-mmlab/mmdetection).
[Here](projects/README.md) are some implementations of SOTA models and solutions built on MMOCR, which are supported and maintained by community users. These projects demonstrate the best practices based on MMOCR for research and product development. We welcome and appreciate all the contributions to OpenMMLab ecosystem.
We appreciate all contributions to improve MMOCR. Please refer to [CONTRIBUTING.md](.github/CONTRIBUTING.md) for the contributing guidelines.
## Acknowledgement
MMOCR is an open-source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks.
We hope the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new OCR methods.
author={Kuang, Zhanghui and Sun, Hongbin and Li, Zhizhong and Yue, Xiaoyu and Lin, Tsui Hin and Chen, Jianyong and Wei, Huaqiang and Zhu, Yiqin and Gao, Tong and Zhang, Wenwei and Chen, Kai and Zhang, Wayne and Lin, Dahua},
Scan the QR code below to follow the OpenMMLab team's [**Zhihu Official Account**](https://www.zhihu.com/people/openmmlab) and join the OpenMMLab team's [**QQ Group**](https://jq.qq.com/?_wv=1027&k=aCvMxdr3), or join the official communication WeChat group by adding the WeChat, or join our [**Slack**](https://join.slack.com/t/mmocrworkspace/shared_invite/zt-1ifqhfla8-yKnLO_aKhVA2h71OrK8GZw)
