ganspace | Discovering Interpretable GAN Controls | Machine Learning library

ganspace is a Jupyter Notebook library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Generative adversarial networks applications. ganspace has no bugs, it has no vulnerabilities, it has a Permissive License and it has medium support. You can download it from GitHub.

Figure 1: Sequences of image edits performed using control discovered with our method, applied to three different GANs. The white insets specify the particular edits using notation explained in Section 3.4 ('Layer-wise Edits'). GANSpace: Discovering Interpretable GAN Controls Erik Härkönen1,2, Aaron Hertzmann2, Jaakko Lehtinen1,3, Sylvain Paris2 1Aalto University, 2Adobe Research, 3NVIDIA Abstract: This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis, such as change of viewpoint, aging, lighting, and time of day. We identify important latent directions based on Principal Components Analysis (PCA) applied in activation space. Then, we show that interpretable edits can be defined based on layer-wise application of these edit directions. Moreover, we show that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner. A user may identify a large number of interpretable controls with these mechanisms. We demonstrate results on GANs from various datasets. Video: