vit-rope topic
List
vit-rope repositories
2D-Positional-Encoding-Vision-Transformer
36
Stars
4
Forks
36
Watchers
PyTorch implementation of 2D Positional Encodings for Vision Transformers (ViT). Positional Encodings/Embeddings: Sinusoidal (Absolute), Learnable, Relative and Rotation (Rope).
