MMClassification Release V0.20.0

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)
• Support HRNet and add pre-trained models. (#660)
• Support ConvNeXt and add pre-trained models. (#670)
• Support Twins and add pre-trained models. (#642)
• Support EfficientNet and add pre-trained models.(#649)
• Support features_only option in TIMMBackbone. (#668)
• Add conversion script from pytorch to Core-ML model. (#597)

Improvements

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

Bug Fixes

• Fix potential unexcepted behaviors if metric_options is not specified in multi-label evaluation. (#647)
• Fix API changes in pytorch-grad-cam>=1.3.7. (#656)
• Fix bug which breaks cal_train_time in analyze_logs.py. (#662)

Docs Update

• Update README in configs according to OpenMMLab standard. (#672)
• Update installation guide and README. (#624)

Contributors

A total of 10 developers contributed to this release.

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