Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling
This is a PyTorch implementation of a new prior ("Variational Mixture of Posteriors" prior, or VampPrior for short) for the variational auto-encoder framework with one layer and two layers of stochastic hidden units as described in the following paper:
The code is compatible with:
pytorch 0.2.0
The experiments can be run on the following datasets:
experiment.py
.python experiment.py
You can run a vanilla VAE, a one-layered VAE or a two-layered HVAE with the standard prior or the VampPrior by setting model_name
argument to either: (i) vae
or hvae_2level
for MLP, (ii) convvae_2level
for convnets, (iii) pixelhvae_2level
for (ii) with a PixelCNN-based decoder, and specifying prior
argument to either standard
or vampprior
.
Please cite our paper if you use this code in your research:
@article{TW:2017,
title={{VAE with a VampPrior}},
author={Tomczak, Jakub M and Welling, Max},
journal={arXiv},
year={2017}
}
The research conducted by Jakub M. Tomczak was funded by the European Commission within the Marie Skłodowska-Curie Individual Fellowship (Grant No. 702666, ”Deep learning and Bayesian inference for medical imaging”).