Skip to content
No description, website, or topics provided.
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.

README.md

Unsupervised Discovery of Interpretable Directions in the GAN Latent Space

Official PyTorch implementation of pre-print Unsupervised Discovery of Interpretable Directions in the GAN Latent Space https://arxiv.org/abs/2002.03754 by Andrey Voynov and Artem Babenko.

This code explores interpretable latent space directions of a pretrained GAN.

An image

Here are several examples for Spectal Norm GAN (MNIST & Anime Faces), ProgGAN (CelebA-HQ) and BigGAN (ILSVRC):

An image

How to run?

Coming soon

Pretrained models

Coming soon

Credits

BigGAN code is based on the authors implementation: https://github.com/ajbrock/BigGAN-PyTorch

ProgGAN code is based on: https://github.com/ptrblck/prog_gans_pytorch_inference

U-net segmentation model code is based on: https://github.com/milesial/Pytorch-UNet

You can’t perform that action at this time.