Part 2. Image generation

Part II dives deep into image generation.

In chapter 4, you’ll learn to build and train generative adversarial networks to generate high-resolution color images. In particular, you’ll learn to use convolutional neural networks to capture spatial features in images. You’ll also learn to use transposed convolutional layers to upsample and generate high-resolution feature maps in images. In chapter 5, you’ll learn two ways to select characteristics in the generated images. In chapter 6, you’ll learn to build and train a CycleGAN to translate images between two domains such as images with black hair and images with blond hair or horse images and zebra images. In chapter 7, you’ll learn to create images using another generative model: autoencoders and their variant, variational autoencoders.