How to Train a Progressive Growing GAN in Keras for Synthesizing Faces

Generative adversarial networks, or GANs, are effective at generating high-quality synthetic images. A limitation of GANs is that the are only capable of generating relatively small images, such as 64 64 pixels. The Progressive Growing GAN is an extension to the GAN training procedure that involves training a GAN to generate very small images, such as 4 4, and incrementally increasing the size of the generated images to 8 8, 16 16, until the desired output size is met. This has allowed the progressive GAN to generate photorealistic synthetic faces with 1024 1024 pixel resolution. The key innovation of the progressive growing GAN is the two-phase training procedure that involves the fading-in of new blocks to support higher-resolution images followed by fine-tuning. In this tutorial, you will discover how to implement and train a progressive growing generative adversarial network for generating celebrity faces. Discover how to develop DCGANs, conditional GANs, Pix2Pix, CycleGANs, and more with Keras in my new GANs book, with 29 step-by-step tutorials and full source code. Photo by Alessandro Caproni, some rights reserved. GANs are effective at generating crisp synthetic images, although are typically limited in the size of the images that can be generated. The Progressive Growing GAN is an extension to the GAN that allows the training generator models to be capable of generating large high-quality images, such as photorealistic faces with the size 1024 1024 pixels. It was described in the 2017 paper by Tero Karras, et al. from Nvidia titled "Progressive Growing of GANs for Improved Quality, Stability, and Variation."