Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Generative Adversarial Networks Cookbook

You're reading from   Generative Adversarial Networks Cookbook Over 100 recipes to build generative models using Python, TensorFlow, and Keras

Arrow left icon
Product type Paperback
Published in Dec 2018
Publisher Packt
ISBN-13 9781789139907
Length 268 pages
Edition 1st Edition
Languages
Tools
Arrow right icon
Author (1):
Arrow left icon
Josh Kalin Josh Kalin
Author Profile Icon Josh Kalin
Josh Kalin
Arrow right icon
View More author details
Toc

Table of Contents (10) Chapters Close

Preface 1. What Is a Generative Adversarial Network? FREE CHAPTER 2. Data First, Easy Environment, and Data Prep 3. My First GAN in Under 100 Lines 4. Dreaming of New Outdoor Structures Using DCGAN 5. Pix2Pix Image-to-Image Translation 6. Style Transfering Your Image Using CycleGAN 7. Using Simulated Images To Create Photo-Realistic Eyeballs with SimGAN 8. From Image to 3D Models Using GANs 9. Other Books You May Enjoy

Parsing the data – is our data unique?


Data is the lifeblood of these algorithms. If you take nothing else away from this book, please learn this lesson. In this recipe, we'll read each of the files in an array, resize them for learning, and save them into an easy-to-access compressed format.

 

 

Getting ready

First, let's perform a sanity check on our directory structure to make sure that we have all the right pieces; it should look as follows:

DCGAN
├── data
│   └── README.md
├── docker
│   ├── build.sh
│   ├── clean.sh
│   └── Dockerfile
├── README.md
├── scripts
│   └── create_data.sh
└── src
    ├── save_to_npy.py

You should notice the new folder, src, along with a new file, save_to_npy.py. The following recipe will focus on this Python file and how to run it to save data.

How to do it...

  1. First, create the save_to_npy.py file and add the following lines to import the necessary dependencies and point to the python3 interpreter:
#!/usr/bin/env python3
from PIL import Image
import numpy as np
import...
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 $19.99/month. Cancel anytime
Banner background image