Skip to content

zenlm/vjepa2

 
 

Repository files navigation

VJEPA2

Self-supervised visual representation learning from video. Part of the Zen LM ecosystem.

License

Overview

VJEPA2 implements Video Joint-Embedding Predictive Architecture for learning visual representations from unlabeled video data without relying on hand-crafted augmentations.

Features

  • Self-supervised learning from video
  • No hand-crafted augmentations required
  • Pre-trained visual encoder for downstream tasks
  • Efficient training with masking strategies

Related

  • jin — Multimodal understanding framework
  • Zen LM — Full model family

License

See LICENSE file.

Part of the Zen LM ecosystem by Hanzo AI

About

PyTorch code and models for VJEPA2 self-supervised learning from video.

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 95.5%
  • Jupyter Notebook 4.5%