lucidrains/vit-pytorch

Health v2 · maintenance only

Adoption not part of the score

25488 stars · 3492 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch library implementing the Vision Transformer (ViT) and dozens of ViT variants (NaViT, MaxViT, MobileViT, Dino, masked autoencoders, and more) for image classification and vision research. It provides clean, minimal model definitions without pretrained weights.

Use cases

• implement vision transformer in pytorch
• train an image classifier with a transformer encoder
• experiment with ViT variants like NaViT or MaxViT
• research attention mechanisms for images
• build a masked autoencoder for images
• apply transformers to video classification

When to choose

• you want readable, hackable PyTorch ViT implementations for research or experimentation
• you need many transformer vision architectures in one pip-installable package
• you are learning how vision transformers work from clean code

When to avoid

• you need pretrained weights for production use - use timm instead
• you need a full training pipeline, data loading, or deployment tooling
• you work in TensorFlow, JAX, or a non-PyTorch stack

Facets

library · maturity active

machine-learning deep-learning image-processing computer-vision deep-learning machine-learning artificial-intelligence python vision-transformer pytorch image-classification attention transformer-architectures research-code

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lucidrains/vit-pytorch")