cheng6076 / Variational-Recurrent-Autoencoder

Implementation of the VRAE

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

This is the main model class file used for the ICLR 2015 workshop paper

For preprocessing the MIDI files into numpy ndarrays, we used code from the RNN-RBM model by Boulanger-Lewandowski et al. found here. Direct download via here, see specifically the util.py file.

For some example code on how to use this class refer to Variational-Autoencoder, which uses largely the same structure.

Feel free to contact the authors (see paper for email addresses) for any questions regarding use of code, dataset etc.

The code is MIT licensed.

About

Implementation of the VRAE

License:MIT License


Languages

Language:Python 100.0%