GitHub · #322

lucidrains/vit-pytorch

lucidrains/vit-pytorch is #322 in this GitHub directory, with 25,552 stars. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Repository
https://github.com/lucidrains/vit-pytorch
Owner
lucidrains (User)
Stars
25,552
Forks
3,495
Open issues
144
Language
Python
License
MIT
Created
2020-10-03
Last push
2026-10-13
Topics
artificial-intelligence, attention-mechanism, computer-vision, image-classification, transformers
Snapshot
2026-10-18

Back to the GitHub directory · Methodology