Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Growing steadily this week
25,499 → 25,572 stars since Sep 2
Maintain vit-pytorch? Show where it stands in your README — the badge updates daily.
The map refreshes every week. Follow @awesomemapdev for the week's biggest risers, or star the repo so you can find your way back.