Search icon CANCEL
Subscription
0
Cart icon
Cart
Close icon
You have no products in your basket yet
Save more on your purchases!
Savings automatically calculated. No voucher code required
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Generative AI with Python and TensorFlow 2

You're reading from  Generative AI with Python and TensorFlow 2

Product type Book
Published in Apr 2021
Publisher Packt
ISBN-13 9781800200883
Pages 488 pages
Edition 1st Edition
Languages
Authors (2):
Joseph Babcock Joseph Babcock
Profile icon Joseph Babcock
Raghav Bali Raghav Bali
Profile icon Raghav Bali
View More author details
Toc

Table of Contents (16) Chapters close

Preface 1. An Introduction to Generative AI: "Drawing" Data from Models 2. Setting Up a TensorFlow Lab 3. Building Blocks of Deep Neural Networks 4. Teaching Networks to Generate Digits 5. Painting Pictures with Neural Networks Using VAEs 6. Image Generation with GANs 7. Style Transfer with GANs 8. Deepfakes with GANs 9. The Rise of Methods for Text Generation 10. NLP 2.0: Using Transformers to Generate Text 11. Composing Music with Generative Models 12. Play Video Games with Generative AI: GAIL 13. Emerging Applications in Generative AI 14. Other Books You May Enjoy
15. Index

Replacement using autoencoders

Deepfakes are an interesting and powerful use of technology that is both useful and dangerous. In previous sections, we discussed different modes of operations and key features that can be leveraged, as well as common architectures. We also briefly touched upon the high-level flow of different tasks required to achieve the end results. In this section, we will focus on developing a face swapping setup using an autoencoder as our backbone architecture. Let's get started.

Task definition

The aim of this exercise is to develop a face swapping setup. As discussed earlier, face swapping is a type of replacement mode operation in the context of deepfake terminology. In this setup, we will focus on transforming Nicolas Cage (a Hollywood actor) into Donald J. Trump (former US president). In the upcoming sections, we will present each sub-task necessary for the preparation of data, training our models, and finally, the generation of swapped fake...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €14.99/month. Cancel anytime}