The project

Importing the right libraries is where we start. Apart from tensorflow, we will be using numpy and math for computations, scipy, matplolib for images and graphics, and warnings, random, and distutils for support in specific operations:

import numpy as np
import tensorflow as tf
import math
import warnings
import matplotlib.pyplot as plt
from scipy.misc import imresize
from random import shuffle
from distutils.version import LooseVersion

Dataset class

Our first step is to provide the data. We will rely on datasets that have already been preprocessed, but our readers could use different kinds of images for their own GAN implementation. The idea is to keep separate a Dataset class that will have the task of providing batches of normalized and reshaped images to the GANs class we will build later.

In the initialization, we will deal with both images and their labels (if available). Images are first reshaped (if their shape differs from the one defined when instantiating the class), then...