Generative adversarial networks<\/a>, or GANs, are effective at generating high-quality synthetic images.<\/p>\n A limitation of GANs is that the are only capable of generating relatively small images, such as 64\u00d764 pixels.<\/p>\n 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\u00d74, and incrementally increasing the size of the generated images to 8\u00d78, 16\u00d716, until the desired output size is met. This has allowed the progressive GAN to generate photorealistic synthetic faces with 1024\u00d71024 pixel resolution.<\/p>\n 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.<\/p>\n In this tutorial, you will discover how to implement and train a progressive growing generative adversarial network for generating celebrity faces.<\/p>\n After completing this tutorial, you will know:<\/p>\n Discover how to develop DCGANs, conditional GANs, Pix2Pix, CycleGANs, and more with Keras in my new GANs book<\/a>, with 29 step-by-step tutorials and full source code.<\/p>\n Let\u2019s get started.<\/p>\n How to Train a Progressive Growing GAN in Keras for Synthesizing Faces. This tutorial is divided into five parts; they are:<\/p>\n GANs are effective at generating crisp synthetic images, although are typically limited in the size of the images that can be generated.<\/p>\n 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\u00d71024 pixels. It was described in the 2017 paper by Tero Karras<\/a>, et al. from Nvidia titled \u201cProgressive Growing of GANs for Improved Quality, Stability, and Variation<\/a>.\u201d<\/p>\n The key innovation of the Progressive Growing GAN is the incremental increase in the size of images output by the generator, starting with a 4\u00d74 pixel image and doubling to 8\u00d78, 16\u00d716, and so on until the desired output resolution.<\/p>\n This is achieved by a training procedure that involves periods of fine-tuning the model with a given output resolution, and periods of slowly phasing in a new model with a larger resolution. All layers remain trainable during the training process, including existing layers when new layers are added.<\/p>\n Progressive Growing GAN involves using a generator and discriminator model with the same general structure and starting with very small images. During training, new blocks of convolutional layers are systematically added to both the generator model and the discriminator models.<\/p>\n The incremental addition of the layers allows the models to effectively learn coarse-level detail and later learn ever-finer detail, both on the generator and discriminator sides.<\/p>\n This incremental nature allows the training to first discover large-scale structure of the image distribution and then shift attention to increasingly finer-scale detail, instead of having to learn all scales simultaneously.<\/p>\n The next step is to select a dataset to use for developing a Progressive Growing GAN.<\/p>\n Take my free 7-day email crash course now (with sample code).<\/p>\n Click to sign-up and also get a free PDF Ebook version of the course.<\/p>\n\n
![\"How](\"https:\/\/machinelearningmastery.com\/wp-content\/uploads\/2019\/08\/How-to-Train-a-Progressive-Growing-GAN-in-Keras-for-Synthesizing-Faces.jpg\")
<\/p>\n
Photo by Alessandro Caproni<\/a>, some rights reserved.<\/p>\n<\/div>\nTutorial Overview<\/h2>\n
\n
What Is the Progressive Growing GAN<\/h2>\n
Want to Develop GANs from Scratch?<\/h3>\n