Changelog¶
v1.0.0rc5 (04/01/2023)¶
Highlights We are excited to announce the release of MMEditing 1.0.0rc5. This release supports 49+ models, 180+ configs and 177+ checkpoints in MMGeneration and MMEditing. We highlight the following new features
Support Restormer
Support GLIDE
Support SwinIR
Support Stable Diffusion
New Features & Improvements
Disco notebook.(#1507)
Revise test requirements and CI.(#1514)
Recursive generate summary and docstring.(#1517)
Enable projects.(#1526)
Support mscoco dataset.(#1520)
Improve Chinese documents.(#1532)
Type hints.(#1481)
Update download link.(#1554)
Update deployment guide.(#1551)
Bug Fixes
Fix documentation link checker.(#1522)
Fix ssim first channel bug.(#1515)
Fix restormer ut.(#1550)
Fix extract_gt_data of realesrgan.(#1542)
Fix model index.(#1559)
Fix config path in disco-diffusion.(#1553)
Fix text2image inferencer.(#1523)
Contributors A total of 16 developers contributed to this release. Thanks @plyfager, @LeoXing1996, @Z-Fran, @zengyh1900, @VongolaWu, @liuwenran, @AlexZou14, @lvhan028, @xiaomile, @ldr426, @austin273, @whu-lee, @willaty, @curiosity654, @Zdafeng, @Taited
New Contributors
@xiaomile made their first contribution in https://github.com/open-mmlab/mmediting/pull/1481
@ldr426 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1542
@austin273 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1553
@whu-lee made their first contribution in https://github.com/open-mmlab/mmediting/pull/1539
@willaty made their first contribution in https://github.com/open-mmlab/mmediting/pull/1541
@curiosity654 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1556
@Zdafeng made their first contribution in https://github.com/open-mmlab/mmediting/pull/1476
@Taited made their first contribution in https://github.com/open-mmlab/mmediting/pull/1534
v1.0.0rc4 (05/12/2022)¶
Highlights
We are excited to announce the release of MMEditing 1.0.0rc4. This release supports 45+ models, 176+ configs and 175+ checkpoints in MMGeneration and MMEditing. We highlight the following new features
Support High-level APIs.
Support diffusion models.
Support Text2Image Task.
Support 3D-Aware Generation.
New Features & Improvements
Refactor high-level APIs. (#1410)
Support disco-diffusion text-2-image. (#1234, #1504)
Support EG3D. (#1482, #1493, #1494, #1499)
Support NAFNet model. (#1369)
Bug Fixes
fix srgan train config. (#1441)
fix cain config. (#1404)
fix rdn and srcnn train configs. (#1392)
Revise config and pretrain model loading in esrgan. (#1407)
Contributors A total of 14 developers contributed to this release. Thanks @plyfager, @LeoXing1996, @Z-Fran, @zengyh1900, @VongolaWu, @gaoyang07, @ChangjianZhao, @zxczrx123, @jackghosts, @liuwenran, @CCODING04, @RoseZhao929, @shaocongliu, @liangzelong.
New Contributors
@gaoyang07 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1372
@ChangjianZhao made their first contribution in https://github.com/open-mmlab/mmediting/pull/1461
@zxczrx123 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1462
@jackghosts made their first contribution in https://github.com/open-mmlab/mmediting/pull/1463
@liuwenran made their first contribution in https://github.com/open-mmlab/mmediting/pull/1410
@CCODING04 made their first contribution in https://github.com/open-mmlab/mmediting/pull/783
@RoseZhao929 made their first contribution in https://github.com/open-mmlab/mmediting/pull/1474
@shaocongliu made their first contribution in https://github.com/open-mmlab/mmediting/pull/1470
@liangzelong made their first contribution in https://github.com/open-mmlab/mmediting/pull/1488
v1.0.0rc3 (03/11/2022)¶
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
andclip
to optional requirements.
New Features & Improvements
Support
try_import
formmdet
. (#1408)Support
try_import
forflip
. (#1420)Complete requirements (#1419)
Update
.gitignore
. ($1416)Set
real_feat
to cpu ininception_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.
v1.0.0rc2 (02/11/2022)¶
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.
image colorization.
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. (#1164)
Save gt images in PGGAN’s
forward
. (#1332)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
andGenDataSample
). (#1382)
Bug Fixes
Fix PPL bug. (#1172)
Fix RDN number of channels. (#1328)
Fix types of exceptions in demos. (#1372)
Fix realesrgan ema. (#1341)
Improve the assertion to ensuer
GenerateFacialHeatmap
asnp.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.
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.
v1.0.0rc0(31/8/2022)¶
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.
v0.15.0 (01/06/2022)¶
Highlights
Support FLAVR
Support AOT-GAN
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
andbackend
in LoadImageFromFileList (#857)Support VFIVimeo90K7FramesDataset (#858)
Support ColorJitter for VFI (#859)
Support ReduceLrUpdaterHook (#860)
Support
after_val_epoch
in IterBaseRunner (#861)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
togt_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
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 seed in DistributedSampler and sync seed across ranks (#815)
Bug Fixes
Fix matting tutorial, and fix links to colab (#795)
Invert
flip_ratio
inRandomAffine
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)
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)
Update BasicVSR++ and RealBasicVSR docs (#778)
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
Support CAIN
Support EDVR-L
Support running in Windows
New Features
Add test-time ensemble for images and videos and support ensemble in BasicVSR series (#585)
Add basic interpolater (#687)
Support various scales in RRDBNet (#699)
Support Ref-SR inference (#716)
Support EDVR-L on REDS (#719)
Support CPU training (#720)
Support DCN on CPU (#735)
Bug Fixes
Fix ARG
MMCV
in Dockerfile (#708)Fix file permission of non-executable files (#718)
Fix some deprecation warning related to numpy (#728)
Delete
__init__
inTestVFIDataset
(#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
v0.12.0 (31/12/2021)¶
Highlights
Support RealBasicVSR
Support Real-ESRGAN checkpoint
New Features
Support video input and output in restoration demo (#622)
Support Real-ESRGAN checkpoint (#635)
Support conversion to y-channel when loading images (643)
Support random video compression during training (#646)
Support crop sequence (#648)
Support pixel_unshuffle (#684)
Bug Fixes
Change ‘target_size’ for RandomResize from list to tuple (#617)
Fix folder creation in preprocess_df2k_ost_dataset.py (#623)
Change TDAN config path in README (#625)
Change ‘radius’ to ‘kernel_size’ for UnsharpMasking in Real-ESRNet config (#626)
Fix bug in MATLABLikeResize (#630)
Fix ‘flow_warp’ comment (#655)
Fix the error of Model Zoo and Datasets in docs (#664)
Fix bug in ‘random_degradations’ (#673)
Limit opencv-python version (#689)
Improvements
Translate docs to Chinese (#576, #577, #578, #579, #581, #582, #584, #587, #588, #589, #590, #591, #592, #593, #594, #595, #596, #641, #647, #656, #665, #666)
Add UNetDiscriminatorWithSpectralNorm (#605)
Update mmcv (#609), mmflow (#621), mmfewshot (#634) and mmhuman3d (#649) in docs
Convert minimum GCC version to 5.4 (#612)
Add tiff in SRDataset IMG_EXTENSIONS (#614)
Update metafile and update_model_index.py (#615)
Update preprocess_df2k_ost_dataset.py (#624)
Align NIQE to MATLAB results (#631)
Add official markdown lint hook (#639)
Skip CI when some specific files were changed (#640)
Try to create a symbolic link on windows (#645)
Cancel previous runs that are not completed (#650)
Update path of configs in demo.md and getting_started.md (#658, #659)
Use mmcv root model registry (#660)
Refactor the structure of documentation (#668)
Add script to crop REDS images into sub-images for faster IO (#669)
Capitalize the first letter of the task name in the metafile (#678)
Update FixedCrop for cropping image sequence (#682)
v0.11.0 (03/11/2021)¶
Highlights
GLEAN for blind face image restoration #530
Real-ESRGAN model #546
New Features
Exponential Moving Average Hook #542
Support DF2K_OST dataset #566
Improvements
Add MATLAB-like bicubic interpolation #507
Support random degradations during training #504
Support torchserve #568
v0.10.0 (12/08/2021).¶
Highlights
Support LIIF-RDN (CVPR’2021)
Support BasicVSR++ (NTIRE’2021)
New Features
Support loading annotation from file for video SR datasets (#423)
Support persistent worker (#426)
Support mim (#455)
Bug Fixes
Fix bug in stat.py (#420)
Fix astype error in function tensor2img (#429)
Fix device error caused by torch.new_tensor when pytorch >= 1.7 (#465)
Fix _non_dist_train in .mmedit/apis/train.py (#473)
Fix multi-node distributed test (#478)
Breaking Changes
Refactor LIIF for pytorch2onnx (#425)
Improvements
Update Chinese docs (#415, #416, #418, #421, #424, #431, #442)
Add CI of pytorch 1.9.0 (#444)
Refactor README.md of configs (#452)
Avoid loading pretrained VGG in unittest (#466)
Support specifying scales in preprocessing div2k dataset (#472)
Support all formats in readthedocs (#479)
Use version_info of mmcv (#480)
Remove unnecessary codes in restoration_video_demo.py (#484)
Change priority of DistEvalIterHook to ‘LOW’ (#489)
Reset resource limit (#491)
Update QQ QR code in README_CN.md (#494)
Add
myst_parser
(#495)Add license header (#496)
Fix typo of StyleGAN modules (#427)
Fix typo in tools/data/super-resolution/reds/README.md (#469)
v0.9.0 (30/06/2021).¶
Highlights
Support DIC and DIC-GAN (CVPR’2020)
Support GLEAN Cat 8x (CVPR’2021)
Support TTSR-GAN (CVPR’2020)
Add colab tutorial for super-resolution
New Features
Add DIC (#342, #345, #348, #350, #351, #357, #363, #365, #366)
Add SRFolderMultipleGTDataset (#355)
Add GLEAN Cat 8x (#367)
Add SRFolderVideoDataset (#370)
Add colab tutorial for super-resolution (#380)
Bug Fixes
Fix bug in restoration_video_inference.py (#379)
Fix Config of LIIF (#368)
Change the path to pre-trained EDVR-M (#396)
Fix normalization in restoration_video_inference (#406)
Fix [brush_stroke_mask] error in unittest (#409)
Breaking Changes
Change mmcv minimum version to v1.3 (#378)
Improvements
v0.8.0 (31/05/2021).¶
Highlights
Support GLEAN (CVPR’2021)
Support TTSR (CVPR’2020)
Support TDAN (CVPR’2020)
New Features
Support PWD metafile (#298)
Support CropLike in pipeline (#299)
Add TTSR (#301, #304, #307, #311, #311, #312, #313, #314, #321, #326, #327)
Add onnx2tensorrt (#317)
Add tensorrt evaluation (#328)
Add SRFacicalLandmarkDataset (#329)
Add demo for video super-resolution methods (#275)
Add SR Folder Ref Dataset (#292)
Support FLOPs calculation of video SR models (#309)
Bug Fixes
Fix find_unused_parameters in PyTorch 1.8 for BasicVSR (#290)
Fix error in publish_model.py for pt>=1.6 (#291)
Fix PSNR when input is uint8 (#294)
Improvements
Update
metric_average_mode
of video SR dataset (#319)Add error message in restoration_demo.py (324)
Minor correction in getting_started.md (#339)
Update description for Vimeo90K (#349)
Support start_index in GenerateSegmentIndices (#338)
Support different filename templates in GenerateSegmentIndices (#325)
v0.7.0 (30/04/2021).¶
Highlights
Support BasicVSR (CVPR’2021)
Support IconVSR (CVPR’2021)
Support RDN (CVPR’2018)
Add onnx evaluation tool
New Features
Add MultipleGT datasets (#238)
Add BasicVSR and IconVSR (#245, #252, #253, #254, #264, #274, #258, #252, #264)
Add onnx evaluation tool (#279)
Bug Fixes
Fix onnx conversion of maxunpool2d (#243)
Fix inpainting in
demo.md
(#248)Tiny fix of config file of EDSR (#251)
Fix link in README (#256)
Fix restoration_inference key missing bug (#270)
Fix the usage of channel_order in
loading.py
(#271)Fix the command of inpainting (#278)
Fix
preprocess_vimeo90k_dataset.py
args name (#281)
Improvements
v0.6.0 (08/04/2021).¶
Highlights
Support Local Implicit Image Function (LIIF)
Support exporting DIM and GCA from Pytorch to ONNX
New Features
Add readthedocs config files and fix docstring (#92)
Add github action file (#94)
Support exporting DIM and GCA from Pytorch to ONNX (#105)
Support concatenating datasets (#106)
Support
non_dist_train
validation (#110)Add matting colab tutorial (#111)
Support niqe metric (#114)
Support PoolDataLoader for parrots (#134)
Support pt1.6 cpu/gpu in CI (#138)
Support publishing to pypi (#149)
Add doc of datasets (194)
Support extended foreground option. (#195, #199, #200, #210)
Support nn.MaxUnpool2d (#196)
Support random down sampling in pipeline (#222)
Support SR folder GT Dataset (#223)
Support Local Implicit Image Function (LIIF) (#224, #226, #227, #234, #239)
Bug Fixes
Fix
_non_dist_train
in train api (#104)Fix setup and CI (#109)
Fix redundant loop bug in Normalize (#121)
Fix
get_hash
insetup.py
(#124)Fix
tool/preprocess_reds_dataset.py
(#148)Fix slurm train tutorial in
getting_started.md
(#162)Fix pip install bug (#173)
Fix bug in config file (#185)
Fix broken links of datasets (#236)
Fix broken links of model zoo (#242)
Breaking Changes
Refactor data loader configs (#201)
Improvements
Update teaser (#96)
Updata model_zoo (#101)
Adopt adjust_gamma from skimage and reduce dependencies (#112)
remove
.gitlab-ci.yml
(#113)Update import of first party (#115)
Remove citation and contact (#122)
Update version file (#136)
Update download url (#141)
Update
setup.py
(#150)modify
Crop
to handle a sequence of video frames (#164)Add config type (#181)
Refactor docs (#184)
Add config link (#187)
Update file structure (#192)
Update config doc (#202)
Update
slurm_train.md
script (#204)Use
file_client
in CompositeFg (#212)Replace
random
withnumpy.random
(#213)Refactor
loader_cfg
(#214)
v0.5.0 (09/07/2020).¶
Note that MMSR has been merged into this repo, as a part of MMEditing. With elaborate designs of the new framework and careful implementations, hope MMEditing could provide better experience.