larsmaaloee / auxiliary-deep-generative-models

Deep generative models for semi-supervised learning.

Auxiliary Deep Generatives Models

This repository is the implementation of the article on Auxiliary Deep Generative Models.

The implementation is build on the Parmesan, Lasagne and Theano libraries.

Installation

Please make sure you have installed the requirements before executing the python scripts.

Install

git clone https://github.com/casperkaae/parmesan.git
cd parmesan
python setup.py develop
pip install numpy
pip install seaborn
pip install matplotlib
pip install https://github.com/Theano/Theano/archive/master.zip
pip install https://github.com/Lasagne/Lasagne/archive/master.zip

Examples

The repository primarily includes a script running a new model on the MNIST dataset with only 100 labels - run_sdgmssl_mnist.py.

Please see the source code and code examples for further details. For some visualisations of the latent space and the half moon classification examples, see https://youtu.be/g-c-xOmA2nA, https://youtu.be/hnhkKTSdmls and https://youtu.be/O8-VYr4CxsI.