Book Image

Hands-On Image Generation with TensorFlow

By : Soon Yau Cheong
Book Image

Hands-On Image Generation with TensorFlow

By: Soon Yau Cheong

Overview of this book

The emerging field of Generative Adversarial Networks (GANs) has made it possible to generate indistinguishable images from existing datasets. With this hands-on book, you’ll not only develop image generation skills but also gain a solid understanding of the underlying principles. Starting with an introduction to the fundamentals of image generation using TensorFlow, this book covers Variational Autoencoders (VAEs) and GANs. You’ll discover how to build models for different applications as you get to grips with performing face swaps using deepfakes, neural style transfer, image-to-image translation, turning simple images into photorealistic images, and much more. You’ll also understand how and why to construct state-of-the-art deep neural networks using advanced techniques such as spectral normalization and self-attention layer before working with advanced models for face generation and editing. You'll also be introduced to photo restoration, text-to-image synthesis, video retargeting, and neural rendering. Throughout the book, you’ll learn to implement models from scratch in TensorFlow 2.x, including PixelCNN, VAE, DCGAN, WGAN, pix2pix, CycleGAN, StyleGAN, GauGAN, and BigGAN. By the end of this book, you'll be well versed in TensorFlow and be able to implement image generative technologies confidently.
Table of Contents (15 chapters)
Section 1: Fundamentals of Image Generation with TensorFlow
Section 2: Applications of Deep Generative Models
Section 3: Advanced Deep Generative Techniques

Implementing StyleGAN

ProGAN is great at generating high-resolution images by growing the network progressively, but the network architecture is quite primitive. The simple architecture resembles earlier GANs such as DCGAN that generate images from random noise but without fine control over the images to be generated.

As we have seen in previous chapters, many innovations happened in image-to-image translation to allow better manipulation of the generator outputs. One of them is the use of the AdaIN layer (Chapter 5, Style Transfer) to allow style transfer, mixing the content and style features from two different images. StyleGAN adopts this concept of style-mixing to come out with a style-based generator architecture for generative adversarial networks – this is the title of the paper written for FaceBid. The following figure shows that StyleGAN can mix the style features from two different images to generate a new one:

Figure 7.5 – Mixing styles...