You are reading the documentation for MMSelfSup 0.x, which will soon be deprecated by the end of 2022. We recommend you upgrade to MMSelfSup 1.0.0rc versions to enjoy fruitful new features and better performance brought by OpenMMLab 2.0. Check out the changelog, code and documentation of MMSelfSup 1.0.0rc for more details.
Cancel previous runs that are not completed in CI (#145)
Enhance MIM function (#152)
Skip CI when some specific files were changed (#154)
drop_lastwhen building eval optimizer (#158)
Deprecate the support for “python setup.py test” (#174)
Speed up training and start time (#181)
isortto 5.10.1 (#184)
Refactor the directory structure of docs (#146)
Update algorithm README with the new format (#177)
Released with code refactor.
Add 3 new self-supervised learning algorithms.
Support benchmarks with MMDet and MMSeg.
Add comprehensive documents.
Merge redundant dataset files.
Adapt to new version of MMCV and remove old version related codes.
Inherit MMCV BaseModule.
Rename all config files.
Add SwAV, SimSiam, DenseCL algorithms.
Add t-SNE visualization tools.
Support MMCV version fp16.
More benchmarking results, including classification, detection and segmentation.
Support some new datasets in downstream tasks.
Launch MMDet and MMSeg training with MIM.
Refactor README, getting_started, install, model_zoo files.
Add data_prepare file.
Add comprehensive tutorials.
Support Mixed Precision Training
Improvement of GaussianBlur doubles the training speed
More benchmarking results
Fix bugs in moco v2, now the results are reproducible.
Fix bugs in byol.
Mixed Precision Training
Improvement of GaussianBlur doubles the training speed of MoCo V2, SimCLR, BYOL
More benchmarking results, including Places, VOC, COCO
Support semi-supervised benchmarks
Fix hash id in publish_model.py
Separate train and test scripts in linear/semi evaluation.
Support semi-supevised benchmarks: benchmarks/dist_train_semi.sh.
Move benchmarks related configs into configs/benchmarks/.
Provide benchmarking results and model download links.
Support updating network every several iterations.
Support LARS optimizer with nesterov.
Support excluding specific parameters from LARS adaptation and weight decay required in SimCLR and BYOL.