Hands-On Deep Learning Algorithms with Python

Implementing DCGAN to generate CIFAR images

Now we will see how to implement DCGAN in TensorFlow. We will learn how to use DCGAN with images from the Canadian Institute For Advanced Research (CIFAR)-10 dataset. CIFAR-10 consists of 60,000 images from 10 different classes that include airplanes, cars, birds, cats, deer, dogs, frogs, horses, ships, and trucks. We will examine how we can use DCGAN to generate such images.

First, import the required libraries:

import warningswarnings.filterwarnings('ignore')import numpy as npimport tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datatf.logging.set_verbosity(tf.logging.ERROR)from keras.datasets import cifar10import matplotlib.pyplot as plt%matplotlib inlinefrom IPython import ...