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.

Related Content you might be interested in

Current Title:

Small book image
Hands-On Image Generation with TensorFlow
Soon Yau Cheong
Dec, 2020 | 306 pages
Small book image
Generative AI with Python and TensorFlow 2
Raghav Bali | Joseph Babcock
Apr, 2021 | 488 pages
Small book image
Hands-On Generative Adversarial Networks with Keras
Rafael Valle
May, 2019 | 272 pages
Small book image
Generative Adversarial Networks Projects
Kailash Ahirwar
Jan, 2019 | 316 pages
Table of Contents (15 chapters)
Preface
Preface
Who this book is for
How to use this book
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Reviews
1
Section 1: Fundamentals of Image Generation with TensorFlow
Section 1: Fundamentals of Image Generation with TensorFlow
Free Chapter
2
Chapter 1: Getting Started with Image Generation Using TensorFlow
Chapter 1: Getting Started with Image Generation Using TensorFlow
Technical requirements
Understanding probabilities
Generating faces with a probabilistic model
Building a PixelCNN model from scratch
Summary
3
Chapter 2: Variational Autoencoder
Chapter 2: Variational Autoencoder
Technical requirements
Learning latent variables with autoencoders
Variational autoencoders
Generating faces with VAEs
Controlling face attributes
Summary
4
Chapter 3: Generative Adversarial Network
Chapter 3: Generative Adversarial Network
Technical requirements
Understanding the fundamentals of GANs
Building a Deep Convolutional GAN (DCGAN)
Challenges in training GANs
Building a Wasserstein GAN
Summary
5
Section 2: Applications of Deep Generative Models
Section 2: Applications of Deep Generative Models
6
Chapter 4: Image-to-Image Translation
Chapter 4: Image-to-Image Translation
Technical requirements
Conditional GANs
Image translation with pix2pix
Unpaired image translation with CycleGAN
Diversifying translation with BicyleGAN
Summary
7
Chapter 5: Style Transfer
Chapter 5: Style Transfer
Technical requirements
Neural style transfer
Improving style transfer
Arbitrary style transfer in real time
Introduction to style-based GANs
Summary
8
Chapter 6: AI Painter
Chapter 6: AI Painter
Technical requirements
Introduction to iGAN
Segmentation map-to-image translation with GauGAN
Summary
9
Section 3: Advanced Deep Generative Techniques
Section 3: Advanced Deep Generative Techniques
10
Chapter 7: High Fidelity Face Generation
Chapter 7: High Fidelity Face Generation
Technical requirements
ProGAN overview
Building a ProGAN
Implementing StyleGAN
Summary
11
Chapter 8: Self-Attention for Image Generation
Chapter 8: Self-Attention for Image Generation
Technical requirements
Spectral normalization
Self-attention modules
Building a SAGAN
Implementing BigGAN
Summary
12
Chapter 9: Video Synthesis
Chapter 9: Video Synthesis
Technical requirements
Video synthesis overview
Implementing face image processing
Building a DeepFake model
Swapping faces
Improving DeepFakes with GANs
Summary
13
Chapter 10: Road Ahead
Chapter 10: Road Ahead
Reviewing GANs
Putting your skills into practice
Image processing
Text to image
Video retargeting
Neural rendering
Summary
14
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Swapping faces

Here comes the last step of the deepfake pipeline, but let's first recap the pipeline. The deepfake production pipeline involves three main stages:

  1. Extract a face from an image using dlib and OpenCV.
  2. Translate the face using the trained encoder and decoders.
  3. Swap the new face back into the original image.

The new face generated by the autoencoder is an aligned face of size 64×64, so we will need to warp it to the position, size, and angle of the face in the original image. We'll use the affine matrix obtained from step 1 in the face extraction stage. We'll use cv2.warpAffine like before, but this time, the cv2.WARP_INVERSE_MAP flag is used to reverse the direction of image transformation as follows:

h, w, _ = image.shape
size = 64
new_image = np.zeros_like(image, dtype=np.uint8)
new_image = cv2.warpAffine(np.array(new_face, 						   dtype=np.uint8)
           ...
Previous Section
End of Section 6
Next Section