lucidrains/vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
This project offers an accessible implementation of Vision Transformers (ViT) in PyTorch, enabling practitioners to classify images with high accuracy. It takes raw image data as input and outputs classifications, indicating what objects or features are present in the image. This is for machine learning engineers and researchers looking to apply advanced vision models to their image classification tasks.
24,988 stars. Used by 2 other packages. Actively maintained with 4 commits in the last 30 days. Available on PyPI.
Use this if you are developing computer vision systems and need a flexible, state-of-the-art approach to image classification.
Not ideal if you are a beginner with no experience in Python or deep learning frameworks, as it requires coding knowledge to implement.
Stars
24,988
Forks
3,479
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2026
Commits (30d)
4
Dependencies
3
Reverse dependents
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/lucidrains/vit-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
roflcoopter/viseron
Self-hosted, local only NVR and AI Computer Vision software. With features such as object...
blakeblackshear/frigate
NVR with realtime local object detection for IP cameras
levan92/deep_sort_realtime
A really more real-time adaptation of deep sort
notAI-tech/NudeNet
Lightweight nudity detection
blakeblackshear/frigate-hass-integration
Frigate integration for Home Assistant