Hands-On Image Generation with TensorFlow

A practical guide to generating images and videos using deep learning

Soon Yau Cheong

• Editore: Packt Publishing
• Anno: 2020
• ISBN:
  9781838821104
• Edizione: 1
• Argomento: Computer Science
• Categoria: Computer Vision & Pattern Recognition

Implement various state-of-the-art architectures, such as GANs and autoencoders, for image generation using TensorFlow 2.x from scratch

Key Features

• Understand the different architectures for image generation, including autoencoders and GANs
• Build models that can edit an image of your face, turn photos into paintings, and generate photorealistic images
• Discover how you can build deep neural networks with advanced TensorFlow 2.x features

Book Description

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.

What you will learn

• Train on face datasets and use them to explore latent spaces for editing new faces
• Get to grips with swapping faces with deepfakes
• Perform style transfer to convert a photo into a painting
• Build and train pix2pix, CycleGAN, and BicycleGAN for image-to-image translation
• Use iGAN to understand manifold interpolation and GauGAN to turn simple images into photorealistic images
• Become well versed in attention generative models such as SAGAN and BigGAN
• Generate high-resolution photos with Progressive GAN and StyleGAN

Who this book is for

The Hands-On Image Generation with TensorFlow book is for deep learning engineers, practitioners, and researchers who have basic knowledge of convolutional neural networks and want to learn various image generation techniques using TensorFlow 2.x. You'll also find this book useful if you are an image processing professional or computer vision engineer looking to explore state-of-the-art architectures to improve and enhance images and videos. Knowledge of Python and TensorFlow will help you to get the best out of this book.

Section 1: Fundamentals of Image Generation with TensorFlow

This section will introduce you to the fundamentals of image generation using TensorFlow, including probabilistic models, autoencoders, and GANs. By the end of this section, you will have a solid understanding of the principles of image generation using deep neural networks.

This section comprises the following chapters:

• Chapter 1, Getting Started with Image Generation Using TensorFlow
• Chapter 2, Variational Autoencoder
• Chapter 3, Generative Adversarial Network

Chapter 1: Getting Started with Image Generation Using TensorFlow

This book focuses on generating images and videos using unsupervised learning with TensorFlow 2. We assume that you have prior experience in using modern machine learning frameworks, such as TensorFlow 1, to build image classifiers with Convolutional Neural Networks (CNNs). Therefore, we will not be covering the basics of deep learning and CNNs. In this book, we will mainly use high level Keras APIs in TensorFlow 2, which is easy to learn. Nevertheless, we assume that you have no prior knowledge of image generation, and we will go through all that is needed to help you get started with it. The first aspect that you need to know about is probability distribution.

Probability distribution is fundamental in machine learning and it is especially important in generative models. Don't worry, I assure you that there aren't any complex mathematical equations in this chapter. We will first learn what probability is and how to use it to generate faces without using any neural networks or complex algorithms.

That's right: with the help of only basic math and NumPy code, you'll learn how to create a probabilistic generative model. Following that, you will learn how to use TensorFlow 2 to build a PixelCNN model in order to generate handwritten digits. This chapter is packed with useful information; you will need to read this chapter before jumping to any other chapters.

In this chapter, we are going to cover the following main topics:

• Understanding probabilities
• Generating faces with a probabilistic model
• Building a PixelCNN model from scratch

Technical requirements

The code can be found here: https://github.com/PacktPublishing/Hands-On-Image-Generation-with-TensorFlow-2.0/tree/master/Chapter01.

Understanding probabilities

You can't escape the term probability in any machine learning literature, and it can be confusing as it can have different meanings in different contexts. Probability is often denoted as p in mathematical equations, and you see it everywhere in academic papers, tutorials, and blogs. Although it is a concept that is seemingly easy to understand, it can be quite confusing. This is because there are multiple different definitions and interpretations depending on the context. We will use some examples to clarify things. In this section, we will go over the use of probability in the following contexts:

• Distribution
• Belief

Probability distribution

Say we want to train a neural network to classify images of cats and dogs and that we found a dataset that contains 600 images of dogs and 400 images of cats. As you may be aware, the data will need to be shuffled before being fed into the neural network. Otherwise, if it sees only images of the same label in a minibatch, the network will get lazy and say all images have the same label without taking the effort to look hard and differentiate between them. If we sampled the dataset randomly, the probabilities could be written as follows:

pdata(dog) = 0.6

pdata(cat) = 0.4

The probabilities here refer to the data distribution. In this example, this refers to the ratio of the number of cat and dog images to the total number of images in the dataset. The probability here is static and will not change for a given dataset.

When training a deep neural network, the dataset is usually too big to fit into one batch, and we need to break it into multiple minibatches for one epoch. If the dataset is well shuffled, then the sampling distribution of the minibatches will resemble that of the data distribution. If the dataset is unbalanced, where some classes have a lot more images from one label than another, then the neural network may be biased toward predicting the images it sees more. This is a form of overfitting. We can therefore sample the data differently to give more weight to the less-represented classes. If we want to balance the classes in sampling, then the sampling probability becomes as follows:

psample(dog) = 0.5

psample(cat) = 0.5

Note

Probability distribution p(x) is the probability of the occurrence of a data point x. There are two common distributions that are used in machine learning. Uniform distribution is where every data point has the same chances of occurrence; this is what people normally imply when they say random sampling without specifying the distribution type. Gaussian distribution is another commonly used distribution. It is so common that people also call it normal distribution. The probabilities peak at the center (mean) and slowly decay on each side. Gaussian distribution also has nice mathematical properties that make it a favorite of mathemati...