Skip to content

Latest commit

 

History

History

vae

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

Variational AutoEncoder in PyTorch

License

This repository was designed to provide a flexible and easily adjustable framework in PyTorch for training Variational Auto Encoders (VAEs), while using powerfull tools as various neural network architectures (DenseNet, ResNet), image distributions (Discretized Logistic and Discretized Mixture of Logistics) and prior distributions (Mixture of Gaussians, VampPrior).

Features

  • Priors

    • Standard (unimodal) Gaussian
    • Mixture of Gaussians
    • VampPrior
  • Reconstruction Loss

    • MSE
    • Discretized Logistic Loss
    • Discretized Mixture of Logistics Loss
  • Neural Networks

    • DenseNet
    • ResNet
  • Datasets

    • MNIST
    • FreyFaces
    • CIFAR-10
    • CelebA

Tensorboard

  • Scalars
  • Reconstructions and Generative Samples
  • Parameters
  • Projector of latent space

Results

VAE's leanred manifold of the MNIST dataset of written digits.

Run

python main.py

Author

Ioannis Gatopoulos.