tintn/vision-transformer-from-scratch

A Simplified PyTorch Implementation of Vision Transformer (ViT)

46
/ 100
Emerging

This project provides a clear and straightforward example of how a Vision Transformer (ViT) model is constructed and trained for image classification. It takes image datasets as input and outputs a trained model capable of classifying images into predefined categories. This is ideal for machine learning researchers or students who want to understand the inner workings of ViT models.

241 stars. No commits in the last 6 months.

Use this if you are a machine learning student or researcher seeking a simple, commented codebase to learn the fundamental architecture and training process of a Vision Transformer for image classification.

Not ideal if you need a high-performance, production-ready image classification solution or if you are looking for advanced features beyond a basic implementation.

deep-learning-education computer-vision-research image-classification-learning transformer-models academic-code-examples
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

241

Forks

41

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tintn/vision-transformer-from-scratch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.