timbmg/VAE-CVAE-MNIST

Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch

43
/ 100
Emerging

This project helps machine learning engineers and researchers understand how Variational Autoencoders (VAEs) and Conditional VAEs (CVAEs) learn to generate images. It takes a dataset of handwritten digit images as input and outputs newly generated, realistic-looking digits, demonstrating the model's ability to learn and reconstruct visual patterns. This is ideal for those exploring generative models.

658 stars. No commits in the last 6 months.

Use this if you are a machine learning practitioner looking for a clear, executable example of VAEs and CVAEs applied to image generation, particularly for educational or foundational understanding.

Not ideal if you need a production-ready solution for generating complex, high-resolution images or if you require advanced generative model architectures beyond basic VAEs/CVAEs.

generative-modeling image-synthesis deep-learning-research machine-learning-education
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 23 / 25

How are scores calculated?

Stars

658

Forks

112

Language

Python

License

Last pushed

May 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/timbmg/VAE-CVAE-MNIST"

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