shub-garg/Vision-Transformer-VIT-for-MNIST

This repository implements a Vision Transformer (ViT) to classify handwritten digits from the MNIST dataset. The project includes model definition, training scripts, and visualization of results, including correct/incorrect predictions and a confusion matrix.

27
/ 100
Experimental

This project helps machine learning practitioners classify handwritten digits. You feed it a dataset of handwritten digit images, and it outputs a trained model that can identify digits, along with visualizations of its performance, including correct and incorrect predictions and a confusion matrix. Anyone working on building or evaluating image classification models for digit recognition would use this.

No commits in the last 6 months.

Use this if you are a machine learning engineer or data scientist specifically interested in understanding or applying Vision Transformers for image classification tasks, particularly on well-known datasets like MNIST.

Not ideal if you need a pre-trained, production-ready model for digit recognition or if your task involves complex, real-world image classification beyond simple digits.

handwritten-digit-recognition image-classification machine-learning-engineering model-evaluation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

May 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/shub-garg/Vision-Transformer-VIT-for-MNIST"

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