Study
Transformers · Vision Transformer (ViT)
ViT treats an image as a sequence of 16×16 patches with a [CLS] token and position embeddings; patch arithmetic, and a pretrained ViT classifying a photo.
- An image becomes a sequence: cut it into fixed-size patches, flatten each, and project it to a token.
- A 224×224 image with 16×16 patches gives 196 patch tokens plus one [CLS] token.