Mmediting Versions Save

Highlights

We are excited to announce the release of MMEditing 1.0.0rc3. This release supports 43+ models, 170+ configs and 169+ checkpoints in MMGeneration and MMEditing. We highlight the following new features

• convert mmdet and clip to optional requirements.

New Features & Improvements

• Support try_import for mmdet. (#1408)
• Support try_import for flip. (#1420)
• Complete requirements (#1419)
• Update .gitignore. ($1416)
• Set real_feat to cpu in inception_utils. (#1415)
• Modify README and configs of StyleGAN2 and PEGAN (#1418)
• Improve the rendering of Docs-API (#1373)

Bug Fixes

• Revise config and pretrain model loading in ESRGAN (#1407)
• Revise config of LSGAN (#1409)
• Revise config of CAIN (#1404)

Contributors

A total of 5 developers contributed to this release. @Z-Fran, @zengyh1900, @plyfager, @LeoXing1996, @ruoningYu.

Highlights

We are excited to announce the release of MMEditing 1.0.0rc2. This release supports 43+ models, 170+ configs and 169+ checkpoints in MMGeneration and MMEditing. We highlight the following new features

• patch-based and slider-based image and video comparison viewer. (#1303)
• image colorization. (#1370)

We want to sincerely thank our community for continuously improving MMEditing. 🥰🥰🥰

New Features & Improvements

• Support qualitative comparison tools. (#1303)
• Support instance aware colorization. (#1370)
• Support multi-metrics with different sample-model. (#1171)
• Improve the implementation
  • refactoring evaluation metrics. (#1161)
  • Save gt images in PGGAN's forward. (#1328)
  • Improve type and change default number of preprocess_div2k_dataset.py. (#1380)
  • Support pixel value clip in visualizer. (#1365)
  • Support SinGAN Dataset and SinGAN demo. (#1363)
  • Avoid cast int and float in GenDataPreprocessor. (#1385)
• Improve the documentation
  • Update a menu switcher. (#1162)
  • Fix TTSR's README. (#1325)
  • Revise docs (change PackGenInputs and GenDataSample). (#1382)

Bug Fixes

• Fix PPL bug. (#1172)
• Fix RDN number of channels. (#1332)
• Fix types of exceptions in demos. (#1372)
• Fix realesrgan ema. (#1341)
• Improve the assertion to ensuer GenerateFacialHeatmap as np.float32. (#1310)
• Fix sampling behavior of unpaired_dataset.py and urls in cyclegan's README. (#1308)
• Fix vsr models in pytorch2onnx. (#1300)
• Fix incorrect settings in configs. (#1167,#1200,#1236,#1293,#1302,#1304,#1319,#1331,#1336,#1349,#1352,#1353,#1358,#1364,#1367,#1384,#1386,#1391,#1392,#1393)

New Contributors

• @gaoyang07 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1372

Contributors

A total of 7 developers contributed to this release. Thanks @LeoXing1996, @Z-Fran, @zengyh1900, @plyfager, @ryanxingql, @ruoningYu, @gaoyang07.

Full Changelog: https://github.com/open-mmlab/mmediting/compare/v1.0.0rc1...v1.0.0rc2

Deprecations

VisualizationHook is deprecated. Users should use MMEditVisualizationHook instead. (#1375)

visual_config = dict(  # config to register visualization hook
  type='VisualizationHook',
  output_dir='visual',
  interval=1000,
  res_name_list=[
      'gt_img', 'masked_img', 'fake_res', 'fake_img', 'fake_gt_local'
  ],
)

visual_config = dict(  # config to register visualization hook
  type='MMEditVisualizationHook',
  output_dir='visual',
  interval=1000,
  res_name_list=[
      'gt_img', 'masked_img', 'fake_res', 'fake_img', 'fake_gt_local'
  ],
)

New Features & Improvements

• Improve arguments type in preprocess_div2k_dataset.py. (#1381)
• Update docstring of RDN. (#1326)
• Update the introduction in readme. (#1387)

Bug Fixes

• Fix FLAVR register in mmedit/models/video_interpolators when importing FLAVR. (#1186)
• Fix data path processing in restoration_video_inference.py. (#1262)
• Fix the number of channels in RDB. (#1292, #1311)

Contributors

A total of 5 developers contributed to this release. Thanks @LeoXing1996, @Z-Fran, @zengyh1900, @ryanxingql, @ruoningYu.

Full Changelog: https://github.com/open-mmlab/mmediting/compare/v0.15.2...v0.16.0

v1.0.0rc1(23/9/2022)

MMEditing 1.0.0rc1 has merged MMGeneration 1.x.

• Support 42+ algorithms, 169+ configs and 168+ checkpoints.
• Support 26+ loss functions, 20+ metrics.
• Support tensorboard, wandb.
• Support unconditional GANs, conditional GANs, image2image translation and internal learning.

Improvements

• [Docs] Fix typos in docs. by @Yulv-git in https://github.com/open-mmlab/mmediting/pull/1079
• [Docs] fix model_zoo and datasets docs link by @Z-Fran in https://github.com/open-mmlab/mmediting/pull/1043
• [Docs] fix typos in readme. by @arch-user-france1 in https://github.com/open-mmlab/mmediting/pull/1078
• [Improve] FLAVR demo by @Yshuo-Li in https://github.com/open-mmlab/mmediting/pull/954
• [Fix] Update MMCV_MAX to 1.7 by @wangruohui in https://github.com/open-mmlab/mmediting/pull/1001
• [Improve] Fix niqe_pris_params.npz path when installed as package by @ychfan in https://github.com/open-mmlab/mmediting/pull/995
• [CI] update github workflow, circleci and github templates by @zengyh1900 in https://github.com/open-mmlab/mmediting/pull/1087

New Contributors

• @ychfan made their first contribution in https://github.com/open-mmlab/mmediting/pull/995
• @arch-user-france1 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1078
• @Yulv-git made their first contribution in https://github.com/open-mmlab/mmediting/pull/1079

MMEditing 1.0.0rc0 is the first version of MMEditing 1.x, a part of the OpenMMLab 2.0 projects.

Built upon the new training engine, MMEditing 1.x unifies the interfaces of dataset, models, evaluation, and visualization.

And there are some BC-breaking changes. Please check the migration tutorial for more details.

v0.15.1 (04/07/2022)

Bug Fixes

• [Fix] Update cain_b5_g1b32_vimeo90k_triplet.py (#929)
• [Docs] Fix link to OST dataset (#933)

Improvements

• [Docs] Update instruction to OST dataset (#937)
• [CI] No actual execution in CUDA envs (#921)
• [Docs] Add watermark to demo video (#935)
• [Tests] Add mim ci (#928)
• [Docs] Update README.md of FLAVR (#919)
• [Improve] Update md-format in .pre-commit-config.yaml (#917)
• [Improve] Add miminstall.txt in setup.py (#916)
• [Fix] Fix clutter in dim/README.md (#913)
• [Improve] Skip problematic opencv-python versions (#833)

Contributors

@wangruohui @Yshuo-Li

v0.15.0 (01/06/2022)

Highlights

1. Support FLAVR
2. Support AOT-GAN
3. Support CAIN with ReduceLROnPlateau Scheduler

New Features

• Add configs for AOT-GAN (#681)
• Support Vimeo90k-triplet dataset (#810)
• Add default config for mm-assistant (#827)
• Support CPU demo (#848)
• Support use_cache and backend in LoadImageFromFileList (#857)
• Support VFIVimeo90K7FramesDataset (#858)
• Support ColorJitter for VFI (#859)
• Support ReduceLrUpdaterHook (#860)
• Support after_val_epoch in IterBaseRunner (#861)
• Support FLAVR Net (#866, #867, #897)
• Support MAE metric (#871)
• Use mdformat (#888)
• Support CAIN with ReduceLROnPlateau Scheduler (#906)

Bug Fixes

• Change - to _ for restoration_demo.py (#834)
• Remove recommonmark in requirements/docs.txt (#844)
• Move EDVR to VSR category in README.md (#849)
• Remove , in multi-line F-string in crop.py (#855)
• Modify double lq_path to gt_path in test_pipeline (#862)
• Fix unittest of TOF-VFI (#873)
• Fix wrong frames in VFI demo (#891)
• Fix logo & contrib guideline on README (#898)
• Normalizing trimap in indexnet_dimaug_mobv2_1x16_78k_comp1k.py (#901)

Improvements

• Add --cfg-options in train/test scripts (#826)
• Update MMCV_MAX to 1.6 (#829)
• Update TOFlow in README (#835)
• Recover beirf installation steps & merge optional requirements (#836)
• Use {MMEditing Contributors} in citation (#838)
• Add tutorial for customizing losses (#839)
• Add installation guide (wiki ver) in README (#845)
• Add a 'need help to traslate' note on Chinese documentation (#850)
• Add wechat QR code in README_zh-CN.md (#851)
• Support non-zero frame index for SRFolderVideoDataset & Fix Typos (#853)
• Create README.md for docker (#856)
• Optimize IO for flow_warp (#881)
• Move wiki/installation to docs (#883)
• Add myst_heading_anchors (#887)
• Use checkpoint link in inpainting demo (#892)

Contributors

@wangruohui @quincylin1 @nijkah @jayagami @ckkelvinchan @ryanxingql @NK-CS-ZZL @Yshuo-Li

v0.14.0 (01/04/2022)

Highlights

1. Support TOFlow in video frame interpolation

New Features

• Support AOT-GAN (#677)
• Use --diff-seed to set different torch seed on different rank (#781)
• Support streaming reading of frames in video interpolation demo (#790)
• Support dist_train without slurm (#791)
• Put LQ into CPU for restoration_video_demo (#792)
• Support gray normalization constant in EDSR (#793)
• Support TOFlow in video frame interpolation (#806, #811)
• Support seed in DistributedSampler and sync seed across ranks (#815)

Bug Fixes

• Update link in README files (#782, #786, #819, #820)
• Fix matting tutorial, and fix links to colab (#795)
• Invert flip_ratio in RandomAffine pipeline (#799)
• Update preprocess_div2k_dataset.py (#801)
• Update SR Colab Demo Installation Method and Set5 link (#807)
• Fix Y/GRB mistake in EDSR README (#812)
• Replace pytorch install command to conda in README(_zh-CN).md (#816)

Improvements

• Update CI (#650)
• Update requirements.txt (#725, #817)
• Add Tutorial of dataset (#758), pipeline (#779), model (#766)
• Update index and TOC tree (#767)
• Make update_model_index.py compatible on windows (#768)
• Update doc build system (#769)
• Update keyword and classifier for setuptools (#773)
• Renovate installation (#776, #800)
• Update BasicVSR++ and RealBasicVSR docs (#778)
• Update citation (#785, #787)
• Regroup docs (#788)
• Use full name of config as 'Name' in metafile (#798)
• Update figure and video demo in README (#802)
• Add clamp(0, 1) in test of video frame interpolation (#805)
• Use hyphen for command line args in demo & tools (#808), and keep underline for required arguments in python files (#822)
• Make dataset.pipeline a dedicated section in doc (#813)
• Update mmcv-full>=1.3.13 to support DCN on CPU (#823)

Contributors

@wangruohui @ckkelvinchan @Yshuo-Li @nijkah @wdmwhh @freepoet @quincylin1

v0.13.0 (01/03/2022)

Highlights

1. Support CAIN
2. Support EDVR-L
3. Support running in Windows

New Features

• Add test-time ensemble for images and videos and support ensemble in BasicVSR series (#585)
• Support AOT-GAN (work in progress) (#674, #675, #676)
• Support CAIN (#683, #691, #709, #713)
• Add basic interpolater (#687)
• Add BaseVFIDataset and VFIVimeo90KDataset (#695, #697)
• Add video interpolation demo (#688, #717)
• Support various scales in RRDBNet (#699)
• Support Ref-SR inference (#716)
• Support EDVR-L on REDS (#719)
• Support CPU training (#720)
• Support running in Windows (#732, #738)
• Support DCN on CPU (#735)

Bug Fixes

• Fix link address in docs (#703, #704)
• Fix ARG MMCV in Dockerfile (#708)
• Fix file permission of non-executable files (#718)
• Fix some deprecation warning related to numpy (#728)
• Delete __init__ in TestVFIDataset (#731)
• Fix data type in docstring of several Datasets (#739)
• Fix math notation in docstring (#741)
• Fix missing folders in copyright commit hook (#754)
• Delete duplicate test in loading (#756)

Improvements

• Update Pillow from 6.2.2 to 8.4 in CI (#693)
• Add argument 'repeat' to SRREDSMultipleGTDataset (#672)
• Deprecate the support for "python setup.py test" (#701)
• Add setup multi-processing both in train and test (#707)
• Add OpenMMLab website and platform links (#710)
• Refact README files of all methods (#712)
• Replace string version comparison with package.version.parse (#723)
• Add docs of Ref-SR demo and video frame interpolation demo (#724)
• Add interpolation and refact README.md (#726)
• Update isort version in pre-commit hook (#727)
• Redesign CI for Linux (#734)
• Update install.md (#763)
• Reorganizing OpenMMLab projects in readme (#764)
• Add deprecation message for deploy tools (#765)

Contributors

@wangruohui @ckkelvinchan @Yshuo-Li @quincylin1 @Juggernaut93 @anse3832 @nijkah