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?

Exploring the training code

Now that we have defined our models, we can go ahead with the process of training a neural network on our data. This is the part where we actually have AI learn the different faces so that it can later swap between them.

  1. First, we import our libraries:
    from glob import glob
    import os
    import random
    from argparse import ArgumentParser
    import cv2
    import numpy as np
    from tqdm import tqdm
    import torch
    from lib.models import OriginalEncoder, OriginalDecoder

Like all Python programs, we import our libraries. We also import our encoder and decoders from our model file. This loads the AI model code from earlier in this chapter and lets us use those to define our models in this code. Python really makes it easy to import code we’ve already written, as every Python file can be called directly or imported into another file.

Note that Python uses a strange syntax for folder paths. Python treats this syntax exactly the same as a module, so you...