Summary

In this chapter, we gave the wonderful world of GANs a quick tour. We covered what GANs are and why they're so interesting – the way the generator and the discriminator play against each other and try to beat each other probably sounds appealing to most people. We then went through the detailed steps of how to train a basic GAN model and a more advanced image resolution enhancement model, and how to prepare them for mobile devices. Finally, we showed you how to build iOS and Android apps using the models. If you're excited about the whole process and the results, you'll definitely want to further explore GANs, a rapidly developing field where new types of GANs have been developed quickly to overcome the shortcomings of the previous models; for example, the same researchers who developed the pix2pix model which requires paired images for training,...