guilherme-pombo / 3DPixelCNN

code for Bayesian 3DPixelCN

Bayesian 3DPixelCNN

This repository contains the code used for the Bayesian 3DPixelCNN model used in Bayesian Volumetric Autoregressive generative models for better semisupervised learning paper. If you use this code or our results in your research, we'd appreciate if you cite our paper as following:

@article{pombo3DPixelCNN,
  title={Bayesian Volumetric Autoregressive generative models for better semisupervised learning},
  author={Pombo, Guilherme and Gray, Robert and Varsavsky, Thomas and Ashburner, John and Nachev, Parashkev},
  journal={arXiv preprint arXiv:1907.11559},
  year={2019}
}

Software Requirements

Python 3.6, Keras 2.2.4 and Tensorflow 1.12.0

Notes

This has been only tested on a single modality of brain imaging. No promises made with regards to multiple channel 3D data