Plain-AyI
← All projects
AI models & research

vit-pytorch

Code versions of the Vision Transformer and many related image-recognition AI designs, for researchers to experiment with.

Research-backed

What it does

The Vision Transformer (ViT) is an AI design that recognises what's in a picture by cutting it into small patches and processing them the way language models process words. This project provides a clean version of it written with PyTorch, a popular AI programming toolkit.

Beyond the original, it includes many later variations from research papers, each with a short summary of the idea and example code. Some aim to train faster, handle images of different sizes, work with video or 3D data, or learn without labelled examples.

It contains model code only, not trained models; the README points to other projects for ready-trained versions.

Who it's for

AI researchers, students and engineers working on image recognition.

Can I use it without coding?

Developers only. A Python library; you need to write code and train or load models yourself. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it