V
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Project.
Catalog snapshot
- License
- MIT
- Platforms
- Linux
- Docker
- No
- Commercial use
- Allowed
- Stars
- 25.5k
- Language
- Python
- Last commit
Repository health snapshot: 3,493 forks and 141 open issues at review time. Platform support is inferred conservatively from repository topics.
About.
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch Fossfits includes vit-pytorch as an actively maintained image ai option: its public repository was updated on 2026-09-05, uses the MIT license, and had 25,503 stars when reviewed. Check its documentation and release notes before production adoption.
artificial intelligence · attention mechanism · computer vision · image classification · transformers
