lucidrains/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch. Significance is further explained in Yannic Kilcher's video. There's really not much to code here, but may as well lay it out for everyone so we expedite the attention revolution. For a Pytorch implementation with pretrained models, please see Ross Wightman's repository here. The official Jax repository is here. A tensorflow2 translation also exists here, created by research scientist Junho Kim! 🙏 Flax translation by Enrico Shippole! Image size. If you have rectangular images, make sure your image size is the maximum of the width and height Size of patches. imagesize must be divisible by patchsize. The number of patches is: n = (imagesize // patchsize) 2 and n must be greater than 16. Number of classes to classify. Last dimension of output tensor after linear transformation nn.Linear(..., dim).…
Read the full README ↗ · Preview checked 2026-11-01T17:05:10.639Z
Inside the original README — Document outline
- Table of Contents
- Vision Transformer - Pytorch
- Install
- Usage
- Parameters
- Simple ViT
- NaViT
- Distillation
- Deep ViT
- CaiT
- Token-to-Token ViT
- CCT
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Repository facts
- Owner
- lucidrains
- Primary language
- Python
- Stars
- 25,554
- Forks
- 3,496
- Open issues + pull requests
- 151
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2020-10-03T22:47:24.000Z
- Last push
- 2026-11-01T03:52:46.000Z
Topics and intended use
Owner-supplied topics: artificial-intelligence, attention-mechanism, computer-vision, image-classification, transformers
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-01T13:20:54.848Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer