Skip to content

Releases: open-mmlab/mmocr

MMOCR Release v1.0.1

04 Jul 07:11
@gaotongxiao gaotongxiao
v1.0.1
1dcd6fa
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.1 Latest
Latest

We are thrilled to announce the release of MMOCR v1.0.1! This version contains important bug fixes and feature enhancements.

🆕 New Features

🛠️ Bug Fixes

📝 Documentation Improvements

New Contributors

Full Changelog: v1.0.0...v1.0.1

Contributors

ly015, A-new-b, and 3 other contributors
Assets 2
Loading

MMOCR Release v1.0.0

06 Apr 11:05
@gaotongxiao gaotongxiao
v1.0.0
d7c59f3
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0

We are excited to announce the first official release of MMOCR 1.0, with many enhancements, bug fixes, and the introduction of new dataset support!

🌟 Highlights

  • Support for SCUT-CTW1500, SynthText, and MJSynth datasets
  • Updated FAQ and documentation
  • Deprecation of file_client_args in favor of backend_args
  • Added a new MMOCR tutorial notebook

🆕 New Features & Enhancement

📝 Docs

🛠️ Bug Fixes:

🎉 New Contributors

Thank you to all the contributors for making this release possible! We're excited about the new features and enhancements in this version, and we're looking forward to your feedback and continued support. Happy coding! 🚀

Full Changelog: v1.0.0rc6...v1.0.0

Contributors

gaotongxiao, hugotong6425, and 6 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc6

07 Mar 12:27
@gaotongxiao gaotongxiao
v1.0.0rc6
bfb36d8
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc6 Pre-release
Pre-release

Highlights

  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
  3. Users can use test-time augmentation for text recognition tasks. Docs
  4. Support batch augmentation through BatchAugSampler, 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
  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.

Dependency

This version requires MMEngine >= 0.6.0, MMCV >= 2.0.0rc4 and MMDet >= 3.0.0rc5.

New Features & Enhancements

Docs

Bug Fixes

New Contributors

Full Changelog: v1.0.0rc5...v1.0.0rc6

Contributors

double22a, gaotongxiao, and 7 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc5

06 Jan 09:35
@gaotongxiao gaotongxiao
v1.0.0rc5
27b6a68
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc5 Pre-release
Pre-release

Highlights

  1. Two models, Aster and SVTR, are added to our model zoo. The full implementation of ABCNet is also available now.
  2. Dataset Preparer supports 5 more datasets: CocoTextV2, FUNSD, TextOCR, NAF, SROIE.
  3. We have 4 more text recognition transforms, and two helper transforms. See #1646 #1632 #1645 for details.
  4. The transform, FixInvalidPolygon, is getting smarter at dealing with invalid polygons, and now capable of handling more weird annotations. As a result, a complete training cycle on TotalText dataset can be performed bug-free. The weights of DBNet and FCENet pretrained on TotalText are also released.

New Features & Enhancements

Docs

Bug Fixes

New Contributors

Full Changelog: v1.0.0rc4...v1.0.0rc5

Contributors

gaotongxiao, Harold-lkk, and 7 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc4

06 Dec 09:24
@gaotongxiao gaotongxiao
v1.0.0rc4
ebdf1cf
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc4 Pre-release
Pre-release

Highlights

  1. Dataset Preparer can automatically generate base dataset configs at the end of the preparation process, and supports 6 more datasets: IIIT5k, CUTE80, ICDAR2013, ICDAR2015, SVT, SVTP.
  2. Introducing our projects/ folder - implementing new models and features into OpenMMLab's algorithm libraries has long been complained to be troublesome due to the rigorous requirements on code quality, which could hinder the fast iteration of SOTA models and might discourage community members from sharing their latest outcome here. We now introduce projects/ folder, where some experimental features, frameworks and models can be placed, only needed to satisfy the minimum requirement on the code quality. Everyone is welcome to post their implementation of any great ideas in this folder! We also add the first example project to illustrate what we expect a good project to have (check out the raw content of README.md for more info!).
  3. Inside the projects/ folder, we are releasing the preview version of ABCNet, which is the first implementation of text spotting models in MMOCR. It's inference-only now, but the full implementation will be available very soon.

New Features & Enhancements

Docs

Bug Fixes

New Contributors

Full Changelog: v1.0.0rc3...v1.0.0rc4

Contributors

jyshee, gaotongxiao, and 6 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc3

03 Nov 11:59
@gaotongxiao gaotongxiao
v1.0.0rc3
abf5a89
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc3 Pre-release
Pre-release

Highlights

  1. We release several pretrained models using oCLIP-ResNet as the backbone, which is a ResNet variant trained with oCLIP and can significantly boost the performance of text detection models.

  2. Preparing datasets is troublesome and tedious, especially in OCR domain where multiple datasets are usually required. In order to free our users from laborious work, we designed a Dataset Preparer to help you get a bunch of datasets ready for use, with only one line of command! Dataset Preparer is also crafted to consist of a series of reusable modules, each responsible for handling one of the standardized phases throughout the preparation process, shortening the development cycle on supporting new datasets.

New Features & Enhancements

Docs

Bug Fixes

New Contributors

Full Changelog: v1.0.0rc2...v1.0.0rc3

Contributors

HannibalAPE, gaotongxiao, and 3 other contributors
Assets 2
Loading

MMOCR Release v0.6.3

03 Nov 12:01
@gaotongxiao gaotongxiao
v0.6.3
26bc471
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v0.6.3

Highlights

This release enhances the inference script and fixes a bug that might cause failure on TorchServe.

Besides, a new backbone, oCLIP-ResNet, and a dataset preparation tool, Dataset Preparer, have been released in
MMOCR 1.0.0rc3 (1.x branch). Check out the changelog for more information about the features, and maintenance plan for how we will maintain MMOCR in the future.

New Features & Enhancements

Bug Fixes

Docs

New Contributors

Full Changelog: v0.6.2...v0.6.3

Contributors

ysh329, gaotongxiao, and 2 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc2

14 Oct 06:26
@gaotongxiao gaotongxiao
v1.0.0rc2
357ccaf
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc2 Pre-release
Pre-release

This release relaxes the version requirement of MMEngine to >=0.1.0, < 1.0.0.

Full Changelog: v1.0.0rc1...v1.0.0rc2

Assets 2
Loading

MMOCR Release v0.6.2

14 Oct 06:21
@gaotongxiao gaotongxiao
v0.6.2
85f3473
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v0.6.2

Highlights

It's now possible to train/test models through Python Interface. For example, you can train a model under mmocr/ directory in this way:

# an example of how to use such modifications is shown as the following:
from mmocr.tools.train import TrainArg, parse_args, run_train_cmd
args = TrainArg(config='/path/to/config.py')
args.add_arg('--work-dir', '/path/to/dir')
args = parse_args(args.arg_list)
run_train_cmd(args)

See PR #1138 for more details.

Besides, release candidates for MMOCR 1.0 with tons of new features are available at 1.x branch now! Check out the changelog for more information about the features, and maintenance plan for how we will maintain MMOCR in the future.

New Features

  • Adding test & train API to be used directly in code by @wybryan in #1138
  • Let ResizeOCR full support mmcv.impad's pad_val parameters by @hsiehpinghan in #1437

Bug Fixes

Docs

New Contributors

Full Changelog: v0.6.1...v0.6.2

Contributors

wybryan, hsiehpinghan, and 8 other contributors
Assets 2
Loading

MMOCR Release v1.0.0rc1

09 Oct 11:21
@gaotongxiao gaotongxiao
v1.0.0rc1
f30c16c
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
Compare
Choose a tag to compare
MMOCR Release v1.0.0rc1 Pre-release
Pre-release

Highlights

This release fixes a severe bug causing inaccurate metric reports in multi-GPU training. Together with the fix, weights for all the text recognition models in MMOCR 1.0 architecture are released. The inference shorthand for them are also added back to ocr.py. Besides, more documentation chapters are available now.

New Features & Enhancements

Docs

Bug Fixes

New Contributors

Full Changelog: v1.0.0rc0...v1.0.0rc1

Contributors

gaotongxiao, Harold-lkk, and 3 other contributors
Assets 2
Loading