Book Image

Exploring Deepfakes

By : Bryan Lyon, Matt Tora
Book Image

Exploring Deepfakes

By: Bryan Lyon, Matt Tora

Overview of this book

Applying Deepfakes will allow you to tackle a wide range of scenarios creatively. Learning from experienced authors will help you to intuitively understand what is going on inside the model. You’ll learn what deepfakes are and what makes them different from other machine learning techniques, and understand the entire process from beginning to end, from finding faces to preparing them, training the model, and performing the final swap. We’ll discuss various uses for face replacement before we begin building our own pipeline. Spending some extra time thinking about how you collect your input data can make a huge difference to the quality of the final video. We look at the importance of this data and guide you with simple concepts to understand what your data needs to really be successful. No discussion of deepfakes can avoid discussing the controversial, unethical uses for which the technology initially became known. We’ll go over some potential issues, and talk about the value that deepfakes can bring to a variety of educational and artistic use cases, from video game avatars to filmmaking. By the end of the book, you’ll understand what deepfakes are, how they work at a fundamental level, and how to apply those techniques to your own needs.
Table of Contents (15 chapters)
1
Part 1: Understanding Deepfakes
6
Part 2: Getting Hands-On with the Deepfake Process
10
Part 3: Where to Now?

Getting hands-on with AI

The first code we’ll examine here is the actual model itself. This code defines the neural network and how it’s structured, as well as how it’s called. All of this is stored in the lib/models.py library file.

First, we load any libraries we’re using:

import torch
from torch import nn

In this case, we only import PyTorch and its nn submodule. This is because we only include the model code in this file and any other libraries will be called in the file that uses those functions.

Defining our upscaler

One of the most important parts of our model is the upscaling layers. Because this is used multiple times in both the encoder and decoder, we’ve broken it out into its own definition, and we’ll cover that here:

  1. First, we define our class:
    class Upscale(nn.Module):
      """ Upscale block to double the width/height from depth. """
      def __init__(self, size...