Mmselfsup

Highlight

- Support `PixMIM`.
- Support `DINO` in `projects/dino/`.

New Features

- Support `PixMIM` ([721](https://github.com/open-mmlab/mmselfsup/pull/721))
- Support `DINO` in `projects/dino/` ([658](https://github.com/open-mmlab/mmselfsup/pull/658))
- Support auto import modules from registry ([660](https://github.com/open-mmlab/mmselfsup/pull/660))

Bug Fixes

- Fix registry import error of MMDet ([732](https://github.com/open-mmlab/mmselfsup/pull/732))
- Fix local-rank in pytorch2.0 ([728](https://github.com/open-mmlab/mmselfsup/pull/728))
- Update MAE 300e pt results ([722](https://github.com/open-mmlab/mmselfsup/pull/722))
- Add missing data preprocessor in tsne configs ([715](https://github.com/open-mmlab/mmselfsup/pull/715))
- Fix the bug in shape bias ([717](https://github.com/open-mmlab/mmselfsup/pull/717))
- Fix T-SNE TypeError ([708](https://github.com/open-mmlab/mmselfsup/pull/708))

Improvements

- Update CI ([742](https://github.com/open-mmlab/mmselfsup/pull/742), [#739](https://github.com/open-mmlab/mmselfsup/pull/739))
- Remove file_client_args and apply new interface of fileio ([662](https://github.com/open-mmlab/mmselfsup/pull/662))

Docs

- Update doc links ([738](https://github.com/open-mmlab/mmselfsup/pull/738))
- Translate customize_runtime.md ([734](https://github.com/open-mmlab/mmselfsup/pull/734))
- Add media links and mmpretrain announcement ([730](https://github.com/open-mmlab/mmselfsup/pull/730), [#693](https://github.com/open-mmlab/mmselfsup/pull/693))
- Translate two docs ([725](https://github.com/open-mmlab/mmselfsup/pull/725))
- Translate docs ([723](https://github.com/open-mmlab/mmselfsup/pull/723))

Contributors

A total of 9 developers contributed to this release.
Thanks fangyixiao18 , tonysy , YuanLiuuuuuu , vansin , guneetmutreja , SheffieldCao , howayShi , xuan07472 , jts250

New Contributors
* vansin made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/693
* guneetmutreja made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/708
* SheffieldCao made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/723
* howayShi made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/658
* xuan07472 made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/725
* jts250 made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/734

**Full Changelog**: https://github.com/open-mmlab/mmselfsup/compare/v1.0.0rc6...v1.0.0

Highlight

- Support `MaskFeat` with video dataset in `projects/maskfeat_video/`
- Translate documentation to Chinese.

New Features

- Support `MaskFeat` with video dataset in `projects/maskfeat_video/` ([678](https://github.com/open-mmlab/mmselfsup/pull/678))

Bug Fixes

- Fix distributed setting for shape bias ([689](https://github.com/open-mmlab/mmselfsup/pull/689))
- Update link of beitv2 ([676](https://github.com/open-mmlab/mmselfsup/pull/676))
- Pass param by explicitly setting location ([654](https://github.com/open-mmlab/mmselfsup/pull/654))
- Update default_runtime.py ([681](https://github.com/open-mmlab/mmselfsup/pull/681))
- Rename metafile.yaml to metafile.yml ([680](https://github.com/open-mmlab/mmselfsup/pull/680))
- Fix bugs in configs/selfsup/eva/metafile.yaml ([669](https://github.com/open-mmlab/mmselfsup/pull/669))

Improvements

- Switch default branch to 1.x ([686](https://github.com/open-mmlab/mmselfsup/pull/686))
- Update pre-commit ([685](https://github.com/open-mmlab/mmselfsup/pull/685))
- Deprecate the support of python 3.6 ([657](https://github.com/open-mmlab/mmselfsup/pull/657))

Docs

- Translate add_transforms.md and conventions.md ([674](https://github.com/open-mmlab/mmselfsup/pull/674))
- Translate classification.md, detection.md, segmentation.md ([665](https://github.com/open-mmlab/mmselfsup/pull/665))
- Update link of knn script ([661](https://github.com/open-mmlab/mmselfsup/pull/661))
- Translate two docs ([653](https://github.com/open-mmlab/mmselfsup/pull/653))
- Translate three docs ([651](https://github.com/open-mmlab/mmselfsup/pull/651))

Contributors

A total of 7 developers contributed to this release.
Thanks fangyixiao18 , YuanLiuuuuuu , GeoffreyChen777 , okotaku , Caczhtus , 123456789asdfjkl , JetstramSam

New Contributors
* JetstramSam made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/651
* 123456789asdfjkl made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/665
* Caczhtus made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/674
* okotaku made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/680
* GeoffreyChen777 made their first contribution in https://github.com/open-mmlab/mmselfsup/pull/681

**Full Changelog**: https://github.com/open-mmlab/mmselfsup/compare/v1.0.0rc5...v1.0.0rc6

Highlight

- Support `BEiT v2`, `MixMIM`, `EVA`
- Support `ShapeBias` for model analysis
- Add Solution of FGIA ACCV 2022 (1st Place)
- Refactor t-SNE

New Features

- Support `BEiT v2` ([627](https://github.com/open-mmlab/mmselfsup/pull/627))
- Support `MixMIM` ([626](https://github.com/open-mmlab/mmselfsup/pull/626))
- Support `EVA` ([632](https://github.com/open-mmlab/mmselfsup/pull/632))
- Support `ShapeBias` for model analysis ([635](https://github.com/open-mmlab/mmselfsup/pull/635))
- Add convert scripts and instructions on seg and det ([621](https://github.com/open-mmlab/mmselfsup/pull/621))
- Add pretraining for FGIA ([607](https://github.com/open-mmlab/mmselfsup/pull/607))

Bug Fixes

- Change `pseudo_collect` to `default_collect` ([616](https://github.com/open-mmlab/mmselfsup/pull/616))
- Fix the link of SimMIM 800pt 100ft ([622](https://github.com/open-mmlab/mmselfsup/pull/622))
- Change `map_location` to `cpu` ([623](https://github.com/open-mmlab/mmselfsup/pull/623))
- Fix import error ([631](https://github.com/open-mmlab/mmselfsup/pull/631))
- Fix key error in configs ([630](https://github.com/open-mmlab/mmselfsup/pull/630))
- Change `np.int` to `int` ([636](https://github.com/open-mmlab/mmselfsup/pull/636))
- Fix knn multi-gpu bug ([634](https://github.com/open-mmlab/mmselfsup/pull/634))

Improvements

- Refactor `projects/` folder ([620](https://github.com/open-mmlab/mmselfsup/pull/620))
- Refactor `t-SNE` ([629](https://github.com/open-mmlab/mmselfsup/pull/629))
- Refactor `CAE` ([645](https://github.com/open-mmlab/mmselfsup/pull/645))
- Refactor benchmark script and update files ([637](https://github.com/open-mmlab/mmselfsup/pull/637))

Docs

- Update data_flow.md ([612](https://github.com/open-mmlab/mmselfsup/pull/612))
- Update datasets.md ([633](https://github.com/open-mmlab/mmselfsup/pull/633))

Contributors
A total of 6 developers contributed to this release.
Thanks fangyixiao18 , YuanLiuuuuuu , tonysy , wangbo-zhao , WasedaMagina , ZhaoQiiii

The `master` branch is still 0.x version and we will checkout a new `1.x` branch to release 1.x version. The two versions will be maintained simultaneously in the future.

We briefly list the major breaking changes here. Please refer to the [migration guide](https://mmselfsup.readthedocs.io/en/dev-1.x/migration.html) for details and migration instructions.

Highlight

- Support `BEiT` and `MILAN`
- Support low-level reconstruction visualization

New Features

- Support `BEiT` ([425](https://github.com/open-mmlab/mmselfsup/pull/425))
- Support `MILAN` ([600](https://github.com/open-mmlab/mmselfsup/pull/600))
- Support low-level reconstruction visualization ([570](https://github.com/open-mmlab/mmselfsup/pull/570))

Bug Fixes

- Fix registry of data preprocessor ([603](https://github.com/open-mmlab/mmselfsup/pull/603))
- Fix dependence and key bug ([611](https://github.com/open-mmlab/mmselfsup/pull/611))

Improvements

- Refactor file io ([582](https://github.com/open-mmlab/mmselfsup/pull/582)))
- Add './projects' folder and an example ([586](https://github.com/open-mmlab/mmselfsup/pull/586)))
- Update CI and UT ([601](https://github.com/open-mmlab/mmselfsup/pull/601)))

Docs

- Update readthedocs rst and menu button ([572](https://github.com/open-mmlab/mmselfsup/pull/572))
- Add readthedocs algorithm pages and fix some displaying error ([599](https://github.com/open-mmlab/mmselfsup/pull/599))

Contibutors
A total of 3 developers contributed to this release.
Thanks fangyixiao18 , YuanLiuuuuuu , soonera

The `master` branch is still 0.x version and we will checkout a new `1.x` branch to release 1.x version. The two versions will be maintained simultaneously in the future.

We briefly list the major breaking changes here. Please refer to the [migration guide](../migration.md) for details and migration instructions.

Highlight

- Support `MaskFeat`

New Features

- Support `MaskFeat` ([494](https://github.com/open-mmlab/mmselfsup/pull/494))
- Add Hog generator ([518](https://github.com/open-mmlab/mmselfsup/pull/518))

Bug Fixes

- Fix fine-tuning config of MAE-H-448 ([509](https://github.com/open-mmlab/mmselfsup/pull/509))

Improvements

- Refactor evaluation folder and related configs ([538](https://github.com/open-mmlab/mmselfsup/pull/538)))
- Refine configs ([547](https://github.com/open-mmlab/mmselfsup/pull/547)))

Docs

- Add custom dataset tutorial ([522](https://github.com/open-mmlab/mmselfsup/pull/522))
- Refactor add_modules.md ([524](https://github.com/open-mmlab/mmselfsup/pull/524))
- Translate some documentation to Chinese

Contributors
A total of 6 developers contributed to this release.
Thanks fangyixiao18 , YuanLiuuuuuu , tonysy , Jiahao000 , wangbo-zhao , soonera

The `master` branch is still 0.x version and we will checkout a new `1.x` branch to release 1.x version. The two versions will be maintained simultaneously in the future.

We briefly list the major breaking changes here. Please refer to the [migration guide](../migration.md) for details and migration instructions.

Highlight

- Full support of `MAE`, `SimMIM`, `MoCoV3`.

New Features

- Full support of `MAE` ([483](https://github.com/open-mmlab/mmselfsup/pull/483))
- Full support of `SimMIM` ([487](https://github.com/open-mmlab/mmselfsup/pull/487))
- Full support of `MoCoV3` ([496](https://github.com/open-mmlab/mmselfsup/pull/496))

Bug Fixes

- Fix classification configs ([488](https://github.com/open-mmlab/mmselfsup/pull/488))
- Fix MAE config name error ([498](https://github.com/open-mmlab/mmselfsup/pull/498))

Improvements

- Refactor colab tutorial ([470](https://github.com/open-mmlab/mmselfsup/pull/470)))
- Update readthedocs requirements ([472](https://github.com/open-mmlab/mmselfsup/pull/472))
- Update CI ([476](https://github.com/open-mmlab/mmselfsup/pull/476))
- Refine `mim_slurm_test.sh` and `mim_dist_test.sh` for benchmarks ([477](https://github.com/open-mmlab/mmselfsup/pull/477))
- Update Metafile format and content ([478](https://github.com/open-mmlab/mmselfsup/pull/478))

Docs

- Add advanced_guides/engine.md ([454](https://github.com/open-mmlab/mmselfsup/pull/454))
- Add advanced_guides/evaluation.md ([456](https://github.com/open-mmlab/mmselfsup/pull/456))
- add advanced_guides/transforms.md ([463](https://github.com/open-mmlab/mmselfsup/pull/463))
- Add dataset docs ([437](https://github.com/open-mmlab/mmselfsup/pull/437))
- Refine contribution guide ([492](https://github.com/open-mmlab/mmselfsup/pull/492))
- update convention ([475](https://github.com/open-mmlab/mmselfsup/pull/475))

Contributors

fangyixiao18 , YuanLiuuuuuu , wangbo-zhao , soonera