sssingh/mnist-digit-generation-gan

A Generative Adversarial Network (GAN) trained on the MNIST dataset, capable of creating fake but realistic looking MNIST digit images that appear to be drawn from the original dataset.

24
/ 100
Experimental

This project helps machine learning practitioners or researchers generate new, realistic handwritten digit images. It takes the characteristics of existing MNIST digit images and creates brand new examples that look authentic, even though they were never drawn by a human. The output is synthetic handwritten digit images, useful for expanding datasets.

No commits in the last 6 months.

Use this if you need to create additional, artificial examples of handwritten digits that closely resemble the standard MNIST dataset for training or testing purposes.

Not ideal if you need to generate images beyond simple handwritten digits, or if you require diverse image content like landscapes, faces, or specific objects.

synthetic-data-generation image-synthesis dataset-augmentation machine-learning-research computer-vision-prototyping
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Jupyter Notebook

License

Last pushed

Aug 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sssingh/mnist-digit-generation-gan"

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