Keras Deep Learning Cookbook

Getting ready

Create a class called BGAN. Import the relevant classes and initialize the variables:

from __future__ import print_function, divisionfrom keras.datasets import fashion_mnistfrom keras.layers import Input, Dense, Reshape, Flatten, Dropoutfrom keras.layers import BatchNormalization, Activation, ZeroPadding2Dfrom keras.layers.advanced_activations import LeakyReLUfrom keras.layers.convolutional import UpSampling2D, Conv2Dfrom keras.models import Sequential, Modelfrom keras.optimizers import Adamimport keras.backend as Kimport matplotlib.pyplot as pltimport sysimport numpy as npclass BGAN():....

Define the constants to be used in the program, as shown in the following listing:

self.img_rows = 28self.img_cols = 28self.channels = 1 ...