gogobd / cyclevqgan Goto Github PK

This Notebook implements a pair of Vector Quantized Variational Autoencoders and Adversarial Discriminators to perform cycle-consistent image transformations of a domain "A" to a domain "B" with unpaired training data. The goal is to learn a mapping G:X→Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F:Y→X and introduce a cycle consistency loss to push F(G(X))≈X (and vice versa).

License: GNU General Public License v3.0