Mmpretrain

Considering more and more codebase depends on new features of MMClassification, we will release a minor version at the middle of every month. 😉

Highlights

- Support a series of CSP Network, such as CSP-ResNet, CSP-ResNeXt and CSP-DarkNet.
- A new `CustomDataset` class to help you build dataset of yourself!
- Support ConvMixer, RepMLP and new dataset - CUB dataset.

New Features

- Add CSPNet and backbone and checkpoints ([735](https://github.com/open-mmlab/mmclassification/pull/735))
- Add `CustomDataset`. ([738](https://github.com/open-mmlab/mmclassification/pull/738))
- Add diff seeds to diff ranks. ([744](https://github.com/open-mmlab/mmclassification/pull/744))
- Support ConvMixer. ([716](https://github.com/open-mmlab/mmclassification/pull/716))
- Our `dist_train` & `dist_test` tools support distributed training on multiple machines. ([734](https://github.com/open-mmlab/mmclassification/pull/734))
- Add RepMLP backbone and checkpoints. ([709](https://github.com/open-mmlab/mmclassification/pull/709))
- Support CUB dataset. ([703](https://github.com/open-mmlab/mmclassification/pull/703))
- Support ResizeMix. ([676](https://github.com/open-mmlab/mmclassification/pull/676))


Improvements

- Use `--a-b` instead of `--a_b` in arguments. ([754](https://github.com/open-mmlab/mmclassification/pull/754))
- Add `get_cat_ids` and `get_gt_labels` to KFoldDataset. ([721](https://github.com/open-mmlab/mmclassification/pull/721))
- Set torch seed in `worker_init_fn`. ([733](https://github.com/open-mmlab/mmclassification/pull/733))

Bug Fixes

- Fix the discontiguous output feature map of ConvNeXt. ([743](https://github.com/open-mmlab/mmclassification/pull/743))

Docs Update

- Add brief installation steps in README for copy&paste. ([755](https://github.com/open-mmlab/mmclassification/pull/755))
- fix logo url link from mmocr to mmcls. ([732](https://github.com/open-mmlab/mmclassification/pull/732))

Contributors
A total of 6 developers contributed to this release.

Ezra-Yu yingfhu Hydrion-Qlz mzr1996 huyu398 okotaku

Highlights

- Support ResNetV1c and Wide-ResNet, and provide pre-trained models.
- Support dynamic input shape for ViT-based algorithms. Now our ViT, DeiT, Swin-Transformer and T2T-ViT supports forwarding with any input shape.
- Reproduce training results of DeiT. And our DeiT-T and DeiT-S have higher accuracy comparing with the official weights.

New Features

- Add ResNetV1c. ([692](https://github.com/open-mmlab/mmclassification/pull/692))
- Support Wide-ResNet. ([715](https://github.com/open-mmlab/mmclassification/pull/715))
- Support gem pooling ([677](https://github.com/open-mmlab/mmclassification/pull/677))

Improvements

- Reproduce training results of DeiT. ([711](https://github.com/open-mmlab/mmclassification/pull/711))
- Add ConvNeXt pretrain models on ImageNet-1k. ([707](https://github.com/open-mmlab/mmclassification/pull/707))
- Support dynamic input shape for ViT-based algorithms. ([706](https://github.com/open-mmlab/mmclassification/pull/706))
- Add `evaluate` function for ConcatDataset. ([650](https://github.com/open-mmlab/mmclassification/pull/650))
- Enhance vis-pipeline tool. ([604](https://github.com/open-mmlab/mmclassification/pull/604))
- Return code 1 if scripts runs failed. ([694](https://github.com/open-mmlab/mmclassification/pull/694))
- Use PyTorch official `one_hot` to implement `convert_to_one_hot`. ([696](https://github.com/open-mmlab/mmclassification/pull/696))
- Add a new pre-commit-hook to automatically add a copyright. ([710](https://github.com/open-mmlab/mmclassification/pull/710))
- Add deprecation message for deploy tools. ([697](https://github.com/open-mmlab/mmclassification/pull/697))
- Upgrade isort pre-commit hooks. ([687](https://github.com/open-mmlab/mmclassification/pull/687))
- Use `--gpu-id` instead of `--gpu-ids` in non-distributed multi-gpu training/testing. ([688](https://github.com/open-mmlab/mmclassification/pull/688))
- Remove deprecation. ([633](https://github.com/open-mmlab/mmclassification/pull/633))

Bug Fixes

- Fix Conformer forward with irregular input size. ([686](https://github.com/open-mmlab/mmclassification/pull/686))
- Add `dist.barrier` to fix a bug in directory checking. ([666](https://github.com/open-mmlab/mmclassification/pull/666))

Contributors
A total of 8 developers contributed to this release.

Ezra-Yu HumberMe mzr1996 twmht RunningLeon yasu0001 okotaku yingfhu

Bug Fixes

- Fix the MMCV dependency version.

Tomorrow is the Chinese new year. Happy new year!

Highlights

- Support K-fold cross-validation. The tutorial will be released later.
- Support HRNet, ConvNeXt, Twins, and EfficientNet.
- Support model conversion from PyTorch to Core-ML by a tool.

New Features

- Support K-fold cross-validation. ([563](https://github.com/open-mmlab/mmclassification/pull/563))
- Support HRNet and add pre-trained models. ([660](https://github.com/open-mmlab/mmclassification/pull/660))
- Support ConvNeXt and add pre-trained models. ([670](https://github.com/open-mmlab/mmclassification/pull/670))
- Support Twins and add pre-trained models. ([642](https://github.com/open-mmlab/mmclassification/pull/642))
- Support EfficientNet and add pre-trained models.([649](https://github.com/open-mmlab/mmclassification/pull/649))
- Support `features_only` option in `TIMMBackbone`. ([668](https://github.com/open-mmlab/mmclassification/pull/668))
- Add conversion script from pytorch to Core-ML model. ([597](https://github.com/open-mmlab/mmclassification/pull/597))

Improvements

- New-style CPU training and inference. ([674](https://github.com/open-mmlab/mmclassification/pull/674))
- Add setup multi-processing both in train and test. ([671](https://github.com/open-mmlab/mmclassification/pull/671))
- Rewrite channel split operation in ShufflenetV2. ([632](https://github.com/open-mmlab/mmclassification/pull/632))
- Deprecate the support for "python setup.py test". ([646](https://github.com/open-mmlab/mmclassification/pull/646))
- Support single-label, softmax, custom eps by asymmetric loss. ([609](https://github.com/open-mmlab/mmclassification/pull/609))
- Save class names in best checkpoint created by evaluation hook. ([641](https://github.com/open-mmlab/mmclassification/pull/641))

Bug Fixes

- Fix potential unexcepted behaviors if `metric_options` is not specified in multi-label evaluation. ([647](https://github.com/open-mmlab/mmclassification/pull/647))
- Fix API changes in `pytorch-grad-cam>=1.3.7`. ([656](https://github.com/open-mmlab/mmclassification/pull/656))
- Fix bug which breaks `cal_train_time` in `analyze_logs.py`. ([662](https://github.com/open-mmlab/mmclassification/pull/662))

Docs Update

- Update README in configs according to OpenMMLab standard. ([672](https://github.com/open-mmlab/mmclassification/pull/672))
- Update installation guide and README. ([624](https://github.com/open-mmlab/mmclassification/pull/624))

Contributors
A total of 10 developers contributed to this release.

Ezra-Yu mzr1996 rlleshi WINDSKY45 shinya7y Minyus 0x4f5da2 imyhxy dreamer121121 xiefeifeihu

Highlights

- The feature extraction function has been enhanced. See [593](https://github.com/open-mmlab/mmclassification/pull/593) for more details.
- Provide the high-acc ResNet-50 training settings from [*ResNet strikes back*](https://arxiv.org/abs/2110.00476).
- Reproduce the training accuracy of T2T-ViT & RegNetX, and provide self-training checkpoints.
- Support DeiT & Conformer backbone and checkpoints.
- Provide a CAM visualization tool based on [pytorch-grad-cam](https://github.com/jacobgil/pytorch-grad-cam), and detailed [user guide](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#class-activation-map-visualization)!

New Features

- Support Precise BN. ([401](https://github.com/open-mmlab/mmclassification/pull/401))
- Add CAM visualization tool. ([577](https://github.com/open-mmlab/mmclassification/pull/577))
- Repeated Aug and Sampler Registry. ([588](https://github.com/open-mmlab/mmclassification/pull/588))
- Add DeiT backbone and checkpoints. ([576](https://github.com/open-mmlab/mmclassification/pull/576))
- Support LAMB optimizer. ([591](https://github.com/open-mmlab/mmclassification/pull/591))
- Implement the conformer backbone. ([494](https://github.com/open-mmlab/mmclassification/pull/494))
- Add the frozen function for Swin Transformer model. ([574](https://github.com/open-mmlab/mmclassification/pull/574))
- Support using checkpoint in Swin Transformer to save memory. ([557](https://github.com/open-mmlab/mmclassification/pull/557))

Improvements

- [Reproduction] Reproduce RegNetX training accuracy. ([587](https://github.com/open-mmlab/mmclassification/pull/587))
- [Reproduction] Reproduce training results of T2T-ViT. ([610](https://github.com/open-mmlab/mmclassification/pull/610))
- [Enhance] Provide high-acc training settings of ResNet. ([572](https://github.com/open-mmlab/mmclassification/pull/572))
- [Enhance] Set a random seed when the user does not set a seed. ([554](https://github.com/open-mmlab/mmclassification/pull/554))
- [Enhance] Added `NumClassCheckHook` and unit tests. ([559](https://github.com/open-mmlab/mmclassification/pull/559))
- [Enhance] Enhance feature extraction function. ([593](https://github.com/open-mmlab/mmclassification/pull/593))
- [Enhance] Imporve efficiency of precision, recall, f1_score and support. ([595](https://github.com/open-mmlab/mmclassification/pull/595))
- [Enhance] Improve accuracy calculation performance. ([592](https://github.com/open-mmlab/mmclassification/pull/592))
- [Refactor] Refactor `analysis_log.py`. ([529](https://github.com/open-mmlab/mmclassification/pull/529))
- [Refactor] Use new API of matplotlib to handle blocking input in visualization. ([568](https://github.com/open-mmlab/mmclassification/pull/568))
- [CI] Cancel previous runs that are not completed. ([583](https://github.com/open-mmlab/mmclassification/pull/583))
- [CI] Skip build CI if only configs or docs modification. ([575](https://github.com/open-mmlab/mmclassification/pull/575))

Bug Fixes

- Fix test sampler bug. ([611](https://github.com/open-mmlab/mmclassification/pull/611))
- Try to create a symbolic link, otherwise copy. ([580](https://github.com/open-mmlab/mmclassification/pull/580))
- Fix a bug for multiple output in swin transformer. ([571](https://github.com/open-mmlab/mmclassification/pull/571))

Docs Update

- Update mmcv, torch, cuda version in Dockerfile and docs. ([594](https://github.com/open-mmlab/mmclassification/pull/594))
- Add analysis&misc docs. ([525](https://github.com/open-mmlab/mmclassification/pull/525))
- Fix docs build dependency. ([584](https://github.com/open-mmlab/mmclassification/pull/584))

Contributors
A total of 6 developers contributed to this release.

elopezz Ezra-Yu mzr1996 0x4f5da2 fangxu622 okotaku

Highlights

- Support MLP-Mixer backbone and provide pre-trained checkpoints.
- Add a tool to visualize the learning rate curve of the training phase. Welcome to use with the [tutorial](https://mmclassification.readthedocs.io/en/latest/tools/visualization.html#learning-rate-schedule-visualization)!

New Features

- Add MLP Mixer Backbone. ([528](https://github.com/open-mmlab/mmclassification/pull/528), [#539](https://github.com/open-mmlab/mmclassification/pull/539))
- Support positive weights in BCE. ([516](https://github.com/open-mmlab/mmclassification/pull/516))
- Add a tool to visualize learning rate in each iterations. ([498](https://github.com/open-mmlab/mmclassification/pull/498))

Improvements

- Use CircleCI to do unit tests. ([567](https://github.com/open-mmlab/mmclassification/pull/567))
- Focal loss for single label tasks. ([548](https://github.com/open-mmlab/mmclassification/pull/548))
- Remove useless `import_modules_from_string`. ([544](https://github.com/open-mmlab/mmclassification/pull/544))
- Rename config files according to the config name standard. ([508](https://github.com/open-mmlab/mmclassification/pull/508))
- Use `reset_classifier` to remove head of timm backbones. ([534](https://github.com/open-mmlab/mmclassification/pull/534))
- Support passing arguments to loss from head. ([523](https://github.com/open-mmlab/mmclassification/pull/523))
- Refactor `Resize` transform and add `Pad` transform. ([506](https://github.com/open-mmlab/mmclassification/pull/506))
- Update mmcv dependency version. ([509](https://github.com/open-mmlab/mmclassification/pull/509))

Bug Fixes

- Fix bug when using `ClassBalancedDataset`. ([555](https://github.com/open-mmlab/mmclassification/pull/555))
- Fix a bug when using iter-based runner with 'val' workflow. ([542](https://github.com/open-mmlab/mmclassification/pull/542))
- Fix interpolation method checking in `Resize`. ([547](https://github.com/open-mmlab/mmclassification/pull/547))
- Fix a bug when load checkpoints in mulit-GPUs environment. ([527](https://github.com/open-mmlab/mmclassification/pull/527))
- Fix an error on indexing scalar metrics in `analyze_result.py`. ([518](https://github.com/open-mmlab/mmclassification/pull/518))
- Fix wrong condition judgment in `analyze_logs.py` and prevent empty curve. ([510](https://github.com/open-mmlab/mmclassification/pull/510))

Docs Update

- Fix vit config and model broken links. ([564](https://github.com/open-mmlab/mmclassification/pull/564))
- Add abstract and image for every paper. ([546](https://github.com/open-mmlab/mmclassification/pull/546))
- Add mmflow and mim in banner and readme. ([543](https://github.com/open-mmlab/mmclassification/pull/543))
- Add schedule and runtime tutorial docs. ([499](https://github.com/open-mmlab/mmclassification/pull/499))
- Add the top-5 acc in ResNet-CIFAR README. ([531](https://github.com/open-mmlab/mmclassification/pull/531))
- Fix TOC of `visualization.md` and add example images. ([513](https://github.com/open-mmlab/mmclassification/pull/513))
- Use docs link of other projects and add MMCV docs. ([511](https://github.com/open-mmlab/mmclassification/pull/511))

Contributors
A total of 9 developers contributed to this release.

Ezra-Yu LeoXing1996 mzr1996 0x4f5da2 huoshuai-dot imyhxy juanjompz okotaku xcnick