AIPython★ 276⑂ 14 forksMIT
kyegomez/NaViT
NAVIT Any‑Format Vision Transformer
Implementation of the Patch n’ Pack paper: NaViT – a Vision Transformer that works with any aspect ratio and resolution without padding.
// KEY FEATURES
- Supports arbitrary image aspect ratios
- Eliminates the need for padding and resizing
- Implemented in PyTorch, easy to integrate
#attention-mechanism#clip#gpt4#multimodal#multimodal-deep-learning#multimodal-learning#multimodality#vit
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram