timbmg/VAE-CVAE-MNIST
Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch
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.
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.
Compare
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)