Skip to content

integraledelebesgue/conditional-vae

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Conditional Convolutional Variational Autoencoder

This repository contains a simple variational autoencoder used to generate handwritten digits based on the MNIST dataset.
The architecture of a simple CNN-based VAE has been modified according to the idea of conditioning, based on the paper Learning Structured Output Representations from Attributes using Deep Conditional Generative Models. This allows generating arbitrary digits by providing class labels to the decoder.

Installation:

Important

The project is managed by uv. I strongly recommend using it for installation and usage, not only for this project but for all your Python software.

To run the notebook:

  1. Clone the repository:
git clone https://github.com/integraledelebesgue/conditional-vae.git
cd conditional-vae
  1. Install the dependencies and create the virtual environment:
uv sync

About

A PyTorch implementation of a Conditional Convolutional VAE for controlled MNIST digit generation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors