This is an attempt to implement An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale in PyTorch
Current Support for:
- Vanilla ViT
- Hybrid ViT (with support for BiT-style resnets)
To Do:
- Axial ViT
- Training Script
-
Notifications
You must be signed in to change notification settings - Fork 34
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
License
gupta-abhay/pytorch-vit
About
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale