Skip to content
This repo contains the code for our AAAI-Workshop paper "Learning disentangled representations from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia"
Python
Branch: master
Clone or download
Latest commit 7e327e6 Dec 11, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md updated readme Dec 12, 2018
_config.yml Set theme jekyll-theme-cayman Nov 20, 2017
eval.py clean codes Nov 20, 2017
models.py clean codes Nov 20, 2017
trainContrastiveMMDVAE.py clean codes Nov 20, 2017
trainMMDVAE.py clean codes Nov 20, 2017
trainVAE.py clean codes Nov 20, 2017
utils.py clean codes Nov 20, 2017

README.md

MMD_VAE

This repo contains the code for the paper presented at Health-Intelligence Workshop, AAAI 2018 "Learning disentangled representations from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia" [Link]

As the experiments involved private dataset, the data loader are defined to take random number with same dimensions as input data.

Dependencies

  • PyTorch
  • Numpy

Description

train_{modelName}.py contains the training procedure of the model.

models.py contains the models used in the experiments.

utils.py contains utility functions.

eval.py contains the evaluation [i.e. linear classifier] to evaluate the model.

You can’t perform that action at this time.