OpenMMLab Self-Supervised Learning Toolbox and Benchmark
We are excited to announce the release of MMSelfSup v1.0.0rc0.
MMSelfSup v1.0.0rc0 is the first version of MMSelfSup 1.x, a part of the OpenMMLab 2.x projects.
The master
branch is still 0.x version and we will checkout a new 1.x
branch to release 1.x version. The two versions will be maintained simultaneously in the future.
We briefly list the major breaking changes here. Please refer to the migration guide for details and migration instructions.
SelfSupDataSample
to unify the components' interface.SelfSupVisualizer
for visualization.SelfSupDataPreprocessor
for data preprocess in model.dict
.A total of 4 developers contributed to this release. Thanks @fangyixiao18 , @YuanLiuuuuuu , @soonera , @doem97
A total of 5 developers contributed to this release. Thanks @Jiahao000 , @fangyixiao18 , @YuanLiuuuuuu , @luuuyi , @soonera
imgs_per_gpu
to samples_per_gpu
in MAE config (#278)A total of 5 developers contributed to this release. Thanks @Jiahao000 , @fangyixiao18 , @YuanLiuuuuuu , @mitming , @xcnick
A total of 5 developers contributed to this release. Thanks @Jiahao000 , @fangyixiao18 , @YuanLiuuuuuu , @soonera , @mitming
Fix MMClassification version dependency
imgs_per_gpu
and use samples_per_gpu
(#204)A total of 6 developers contributed to this release. Thanks @Jiahao000 , @fangyixiao18 , @YuanLiuuuuuu , @wang11wang , @c-liangyu , @mitming
RandomAppliedTrans
(#173)dataset.evaluate
args bug (#192)drop_last
when building eval optimizer (#158)isort
to 5.10.1 (#184)A total of 10 developers contributed to this release. Thanks @Jiahao000, @fangyixiao18, @YuanLiuuuuuu, @soonera, @Kaminyou, @mitming, @RangeKing, @xcnick, @st9007a, @Muyun99