Python module for training unsupervised deep, generative models on images.
Python module for training unsupervised deep, generative models on images. It uses Chainer for the Neural Network framework and implements several methods, including Variational Auto-encoders, Generative Adversarial Networks, and their combination. These methods are built with reference to personal notes and the following papers: 1) Diederik P Kingma, Max Welling; “Auto-Encoding Variational Bayes”; (2013). 2) Alec Radford et. al.; “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks”; (2015). 3) Anders Boesen et. al.; “Autoencoding Beyond Pixels Using a Learned Similarity Metric”; (2015).