PASSL is a Paddle based vision library for state-of-the-art Self-Supervised Learning research with PaddlePaddle. PASSL aims to accelerate research cycle in self-supervised learning: from designing a new self-supervised task to evaluating the learned representations.

• Reproducible implementation of SOTA in Self-Supervision: Existing SOTA in Self-Supervision are implemented - SimCLR, MoCo(v1),MoCo(v2), MoCo-BYOL, CLIP. BYOL is coming soon. Also supports supervised trainings.
• Modular: Easy to build new tasks and reuse the existing components from other tasks (Trainer, models and heads, data transforms, etc.).

• See INSTALL.md.

Benchmark Linear Image Classification on ImageNet-1K

Please see GETTING_STARTED.md for the basic usage of PASSL.

• Train SimCLR model
• Train MoCo(v1,v2) model
• Train MoCo-BYOL model
• Train BYOL model
• Train CLIP model