In this chapter, we learned about Generative Adversarial Networks. We built a simple GAN in TensorFlow and Keras and applied it to generate images from the MNIST dataset. We also learned that many different derivatives of GANs are being introduced continuously, such as DCGAN, SRGAN, StackGAN, and CycleGAN, to name a few. We also built a DCGAN where the generator and discriminator consisted of convolutional networks. You are encouraged to read and experiment with different derivatives to see which models fit the problems they are trying to solve.
In the next chapter, we shall learn how to build and deploy models in distributed clusters with TensorFlow clusters and multiple compute devices such as multiple GPUs.
