MMClassification Release V0.18.0
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!
New Features
- Add MLP Mixer Backbone. (#528, #539)
- Support positive weights in BCE. (#516)
- Add a tool to visualize learning rate in each iterations. (#498)
Improvements
- Use CircleCI to do unit tests. (#567)
- Focal loss for single label tasks. (#548)
- Remove useless
import_modules_from_string
. (#544) - Rename config files according to the config name standard. (#508)
- Use
reset_classifier
to remove head of timm backbones. (#534) - Support passing arguments to loss from head. (#523)
- Refactor
Resize
transform and addPad
transform. (#506) - Update mmcv dependency version. (#509)
Bug Fixes
- Fix bug when using
ClassBalancedDataset
. (#555) - Fix a bug when using iter-based runner with 'val' workflow. (#542)
- Fix interpolation method checking in
Resize
. (#547) - Fix a bug when load checkpoints in mulit-GPUs environment. (#527)
- Fix an error on indexing scalar metrics in
analyze_result.py
. (#518) - Fix wrong condition judgment in
analyze_logs.py
and prevent empty curve. (#510)
Docs Update
- Fix vit config and model broken links. (#564)
- Add abstract and image for every paper. (#546)
- Add mmflow and mim in banner and readme. (#543)
- Add schedule and runtime tutorial docs. (#499)
- Add the top-5 acc in ResNet-CIFAR README. (#531)
- Fix TOC of
visualization.md
and add example images. (#513) - Use docs link of other projects and add MMCV docs. (#511)
Contributors
A total of 9 developers contributed to this release.
@Ezra-Yu @LeoXing1996 @mzr1996 @0x4f5da2 @huoshuai-dot @imyhxy @juanjompz @okotaku @xcnick