Description
Self-Supervised Learning Algorithms Extension to Fastai - KeremTurgutlu/self_supervised
Summary
- Algorithms Augmentations New augmentations module offers helpers for easily constructing augmentation pipelines for self supervised algorithms.
- CLIP-MoCo A custom implementation which combines CLIP with MoCo Queue implementation to reduce the requirement for using large batch sizes during training.
- Fastai Upgrade Changes are compatible with latest fastai release.
- MoCo V1 & V2 (Single and Multi GPU Support) Similar to SimCLR, it's pretty simple to switch from MoCo v1 to v2 using the parts of the library since core algorithm / loss function stays the same.