Browse Library
Sign In Start Free Trial
Close icon Search icon
Account
Browse Library Sign In Start Free Trial

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Book Overview & Buying Generative AI with Python and TensorFlow 2
  • Table Of Contents Toc
Generative AI with Python and TensorFlow 2

Generative AI with Python and TensorFlow 2

By : Joseph Babcock, Raghav Bali
4.4 (27)
Buy this Book
close
close
Generative AI with Python and TensorFlow 2

Generative AI with Python and TensorFlow 2

4.4 (27)
By: Joseph Babcock, Raghav Bali
Buy this Book

Overview of this book

Machines are excelling at creative human skills such as painting, writing, and composing music. Could you be more creative than generative AI? In this book, you’ll explore the evolution of generative models, from restricted Boltzmann machines and deep belief networks to VAEs and GANs. You’ll learn how to implement models yourself in TensorFlow and get to grips with the latest research on deep neural networks. There’s been an explosion in potential use cases for generative models. You’ll look at Open AI’s news generator, deepfakes, and training deep learning agents to navigate a simulated environment. Recreate the code that’s under the hood and uncover surprising links between text, image, and music generation.
Table of Contents (16 chapters)
close
close
close
Preface
Icon
Preface
Icon
Who this book is for
Icon
What this book covers
Icon
To get the most out of this book
Icon
Get in touch
1
An Introduction to Generative AI: "Drawing" Data from Models
Icon
An Introduction to Generative AI: "Drawing" Data from Models
Icon
Applications of AI
Icon
The rules of probability
Icon
Why use generative models?
Icon
Style transfer and image transformation
Icon
Unique challenges of generative models
Icon
Summary
Icon
References
Lock Free Chapter
2
Setting Up a TensorFlow Lab
Icon
Setting Up a TensorFlow Lab
Icon
Deep neural network development and TensorFlow
Icon
VSCode
Icon
Docker: A lightweight virtualization solution
Icon
Kubernetes: Robust management of multi-container applications
Icon
Kubeflow: an end-to-end machine learning lab
Icon
A brief tour of Kubeflow's components
Icon
Kubeflow pipelines
Icon
Using Kubeflow Katib to optimize model hyperparameters
Icon
Summary
Icon
References
3
Building Blocks of Deep Neural Networks
Icon
Building Blocks of Deep Neural Networks
Icon
Perceptrons – a brain in a function
Icon
Multi-layer perceptrons and backpropagation
Icon
Varieties of networks: Convolution and recursive
Icon
Networks for sequence data
Icon
Building a better optimizer
Icon
Summary
Icon
References
4
Teaching Networks to Generate Digits
Icon
Teaching Networks to Generate Digits
Icon
The MNIST database
Icon
Restricted Boltzmann Machines: generating pixels with statistical mechanics
Icon
Stacking Restricted Boltzmann Machines to generate images: the Deep Belief Network
Icon
Creating an RBM using the TensorFlow Keras layers API
Icon
Creating a DBN with the Keras Model API
Icon
Summary
Icon
References
5
Painting Pictures with Neural Networks Using VAEs
Icon
Painting Pictures with Neural Networks Using VAEs
Icon
Creating separable encodings of images
Icon
The variational objective
Icon
Inverse Autoregressive Flow
Icon
Importing CIFAR
Icon
Creating the network from TensorFlow 2
Icon
Summary
Icon
References
6
Image Generation with GANs
Icon
Image Generation with GANs
Icon
The taxonomy of generative models
Icon
Generative adversarial networks
Icon
Vanilla GAN
Icon
Improved GANs
Icon
Progressive GAN
Icon
Challenges
Icon
Summary
Icon
References
7
Style Transfer with GANs
Icon
Style Transfer with GANs
Icon
Paired style transfer using pix2pix GAN
Icon
Unpaired style transfer using CycleGAN
Icon
Related works
Icon
Summary
Icon
References
8
Deepfakes with GANs
chevron up
Icon
Deepfakes with GANs
Icon
Deepfakes overview
Icon
Modes of operation
Icon
Key feature set
Icon
High-level workflow
Icon
Replacement using autoencoders
Icon
Re-enactment using pix2pix
Icon
Challenges
Icon
Off-the-shelf implementations
Icon
Summary
Icon
References
9
The Rise of Methods for Text Generation
Icon
The Rise of Methods for Text Generation
Icon
Representing text
Icon
Text generation and the magic of LSTMs
Icon
LSTM variants and convolutions for text
Icon
Summary
Icon
References
10
NLP 2.0: Using Transformers to Generate Text
Icon
NLP 2.0: Using Transformers to Generate Text
Icon
Attention
Icon
GPT 1, 2, 3…
Icon
Summary
Icon
References
11
Composing Music with Generative Models
Icon
Composing Music with Generative Models
Icon
Getting started with music generation
Icon
Music generation using LSTMs
Icon
Music generation using GANs
Icon
MuseGAN – polyphonic music generation
Icon
Summary
Icon
References
12
Play Video Games with Generative AI: GAIL
Icon
Play Video Games with Generative AI: GAIL
Icon
Reinforcement learning: Actions, agents, spaces, policies, and rewards
Icon
Running GAIL on PyBullet Gym
Icon
Summary
Icon
References
13
Emerging Applications in Generative AI
Icon
Emerging Applications in Generative AI
Icon
Finding new drugs with generative models
Icon
Solving partial differential equations with generative modeling
Icon
Few shot learning for creating videos from images
Icon
Generating recipes with deep learning
Icon
Summary
Icon
References
Icon
Why subscribe?
14
Other Books You May Enjoy
Icon
Other Books You May Enjoy
15
Index
Icon
Index

High-level workflow

Fake content generation is a complex task consisting of a number of components and steps that help in generating believable content. While this space is seeing quite a lot of research and hacks that improve the overall results, the setup can largely be explained using a few common building blocks. In this section, we will discuss a common high-level flow that describes how a deepfake setup uses data to train and generate fake content. We will also touch upon a few common architectures used in a number of works as basic building blocks.

As discussed earlier, a deepfake setup requires a source identity (xs) which drives the target identity (xt) to generate fake content (xg). To understand the high-level flow, we will continue with this notation, along with the concepts related to the key feature set discussed in the previous section. The steps are as follows:

  • Input processing
    • The input image (xs or xt) is processed using a face...
CONTINUE READING
83
Tech Concepts
36
Programming languages
73
Tech Tools
Icon Unlimited access to the largest independent learning library in tech of over 8,000 expert-authored tech books and videos.
Icon Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.
Icon 50+ new titles added per month and exclusive early access to books as they are being written.
Generative AI with Python and TensorFlow 2
End of Section 8
Next Section
notes
bookmark Notes and Bookmarks search Search in title playlist Add to playlist download Download options
font-size Font size

Change the font size

margin-width Margin width

Change margin width

day-mode Day/Sepia/Night Modes

Change background colour

Close icon Search
Country selected
Close icon Your notes and bookmarks

Confirmation

Modal Close icon
claim successful
Order Page Read Now

Buy this book with your credits?

Modal Close icon
Are you sure you want to buy this book with one of your credits?
Close
YES, BUY

Submit Your Feedback

Modal Close icon
Modal Close icon
Modal Close icon