Mmpretrain

New Features

- [Feature] Support mmcls with NPU backend. ([1072](https://github.com/open-mmlab/mmclassification/pull/1072))

Bug Fixes

- [Fix] Fix performance issue in convnext DDP train. ([1098](https://github.com/open-mmlab/mmclassification/pull/1098))

Contributors
A total of 3 developers contributed to this release.

wangjiangben-hw 790475019 mzr1996

Highlights

- Support HorNet, EfficientFormerm, SwinTransformer V2, and MViT backbones.
- Support Standford Cars dataset.

New Features

- Support HorNet Backbone. ([1013](https://github.com/open-mmlab/mmclassification/pull/1013))
- Support EfficientFormer. ([954](https://github.com/open-mmlab/mmclassification/pull/954))
- Support Stanford Cars dataset. ([893](https://github.com/open-mmlab/mmclassification/pull/893))
- Support CSRA head. ([881](https://github.com/open-mmlab/mmclassification/pull/881))
- Support Swin Transform V2. ([799](https://github.com/open-mmlab/mmclassification/pull/799))
- Support MViT and add checkpoints. ([924](https://github.com/open-mmlab/mmclassification/pull/924))

Improvements

- [Improve] replace loop of progressbar in api/test. ([878](https://github.com/open-mmlab/mmclassification/pull/878))
- [Enhance] RepVGG for YOLOX-PAI. ([1025](https://github.com/open-mmlab/mmclassification/pull/1025))
- [Enhancement] Update VAN. ([1017](https://github.com/open-mmlab/mmclassification/pull/1017))
- [Refactor] Re-write `get_sinusoid_encoding` from third-party implementation. ([965](https://github.com/open-mmlab/mmclassification/pull/965))
- [Improve] Upgrade onnxsim to v0.4.0. ([915](https://github.com/open-mmlab/mmclassification/pull/915))
- [Improve] Fixed typo in `RepVGG`. ([985](https://github.com/open-mmlab/mmclassification/pull/985))
- [Imporve] Using `train_step` instead of `forward` in PreciseBNHook ([964](https://github.com/open-mmlab/mmclassification/pull/964))
- [Improve] Use `forward_dummy` to calculate FLOPS. ([953](https://github.com/open-mmlab/mmclassification/pull/953))

Bug Fixes

- Fix warning with `torch.meshgrid`. ([860](https://github.com/open-mmlab/mmclassification/pull/860))
- Add matplotlib minimum version requirements. ([909](https://github.com/open-mmlab/mmclassification/pull/909))
- val loader should not drop last by default. ([857](https://github.com/open-mmlab/mmclassification/pull/857))
- Fix config.device bug in toturial. ([1059](https://github.com/open-mmlab/mmclassification/pull/1059))
- Fix attenstion clamp max params ([1034](https://github.com/open-mmlab/mmclassification/pull/1034))
- Fix device mismatch in Swin-v2. ([976](https://github.com/open-mmlab/mmclassification/pull/976))
- Fix the output position of Swin-Transformer. ([947](https://github.com/open-mmlab/mmclassification/pull/947))

Docs Update

- Add version for torchvision to avoid error. ([903](https://github.com/open-mmlab/mmclassification/pull/903))
- Fix typo for `--out-dir` option of analyze_results.py. ([898](https://github.com/open-mmlab/mmclassification/pull/898))
- Refine the docstring of RegNet. ([935](https://github.com/open-mmlab/mmclassification/pull/935))

Contributors
A total of 19 developers contributed to this release.

a-mos Ezra-Yu Fei-Wang nijkah PeterH0323 yingfhu techmonsterwang JiayuXu0 jlim262 hukkai mzr1996 liu-mengyang twmht pallgeuer timothylimyl daquexian okotaku tpoisonooo zzc98

New Features

- Support MPS device. ([894](https://github.com/open-mmlab/mmclassification/pull/894))

Improvements

- Add test mim CI. ([879](https://github.com/open-mmlab/mmclassification/pull/879))

Bug Fixes

- [Fix] Fix Albu crash bug. ([918](https://github.com/open-mmlab/mmclassification/pull/918))
- [Fix] Add mim to extras_require in setup.py. ([872](https://github.com/open-mmlab/mmclassification/pull/872))

Contributors
A total of 2 developers contributed to this release.

mzr1996 PeterH0323

Highlights

- New WandbHook to store your training log and visualize validation results!

New Features

- [Feature] Dedicated MMClsWandbHook for MMClassification (Weights and Biases Integration) ([764](https://github.com/open-mmlab/mmclassification/pull/764))

Improvements

- [Refactor] Use mdformat instead of markdownlint to format markdown. ([844](https://github.com/open-mmlab/mmclassification/pull/844))

Bug Fixes

- [Fix] Fix wrong `--local_rank`.

Docs Update

- [Docs] Update install tutorials. ([854](https://github.com/open-mmlab/mmclassification/pull/854))
- [Docs] Fix wrong link in README. ([835](https://github.com/open-mmlab/mmclassification/pull/835))

Contributors
A total of 3 developers contributed to this release.

ayulockin mzr1996 timothylimyl

New Features

- Support DenseNet. ([750](https://github.com/open-mmlab/mmclassification/pull/750))
- Support VAN. ([739](https://github.com/open-mmlab/mmclassification/pull/739))

Improvements

- Support training on IPU and add fine-tuning configs of ViT. ([723](https://github.com/open-mmlab/mmclassification/pull/723))

Docs Update

- New style API reference, and easier to use! Welcome [view it](https://mmclassification.readthedocs.io/en/master/api/models.html). ([#774](https://github.com/open-mmlab/mmclassification/pull/774))

Contributors
A total of 4 developers contributed to this release.

mzr1996 okotaku yingfhu HuDi2018

New Features

- Support resize relative position embedding in `SwinTransformer`. ([749](https://github.com/open-mmlab/mmclassification/pull/749))
- Add PoolFormer backbone and checkpoints. ([746](https://github.com/open-mmlab/mmclassification/pull/746))

Improvements

- Improve CPE performance by reduce memory copy. ([762](https://github.com/open-mmlab/mmclassification/pull/762))
- Add extra dataloader settings in configs. ([752](https://github.com/open-mmlab/mmclassification/pull/752))

Contributors
A total of 4 developers contributed to this release.

mzr1996 yuweihao XiaobingSuper YuanLiuuuuuu