CycleGAN is a type of Generative Adversarial Network (GAN) for cross-domain transfer tasks, such as changing the style of an image, turning paintings into photos, and vice versa, photo enhancement, changing the season of a photo, and many more. CycleGANs were introduced by Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A. Efros in a paper entitled: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. This was produced in February 2018 at the Berkeley AI Research (BAIR) laboratory, UC Berkeley, which is available at the following link: https://arxiv.org/pdf/1703.10593.pdf. CycleGANs caused a stir in the GAN community because of their widespread use cases. In this chapter, we will be working with CycleGANs and, specifically, using them to turn paintings into photos.

In this chapter, we will cover the following topics:

• An introduction to CycleGANs
• The architecture of a CycleGAN
• Data gathering and preparation
• A Keras implementation of a CycleGAN
• The objective functions
• Training the CycleGAN
• Practical applications of CycleGANs