Home Projects vit-pytorch
vit-pytorch

vit-pytorch

by lucidrains · GitHub

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

# artificial-intelligence# attention-mechanism# computer-vision# image-classification
View on GitHub
⭐ Stars
25.4k
🍴 Forks
3.5k
📜 License
MIT
Commercial use OK
📅 Created
2020
🔄 Last commit
29 days ago
🏷️ Category
artificial-intelligence
💻 Language
You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
vit-pytorch — GitHub preview card
📈 Star history
25.42k25.36k
2026-06-272026-07-22
📄 About

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Frequently asked questions

What is vit-pytorch?

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Is vit-pytorch open source?

vit-pytorch is an open-source project. It is released under the MIT license.

Is vit-pytorch free?

Yes. vit-pytorch is free and open source — you can use, modify and self-host it.

🏅 Maintainer of this project?
olud.ai badge — vit-pytorch

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=lucidrains-vit-pytorch)](https://olud.ai/project/lucidrains-vit-pytorch.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.