Python Deep Learning Cookbook

How to do it...

1. We start by importing the necessary libraries, as follows:

import numpy as npfrom keras.models import Sequential, Modelfrom keras.layers import Input, Dense, Activation, Flatten, Reshapefrom keras.layers import Conv2D, Conv2DTranspose, UpSampling2Dfrom keras.layers import LeakyReLU, Dropoutfrom keras.layers import BatchNormalizationfrom keras.optimizers import Adamfrom keras import initializersfrom keras.datasets import mnistimport matplotlib.pyplot as plt

2. By using Keras, we can easily import both datasets with the following lines of code:

(X_train, y_train), (X_test, y_test) = mnist.load_data()img_rows, img_cols = X_train.shape[1:]X_train = X_train.reshape(-1, img_rows*img_cols, 1).astype(np.float32)/255.

3. For our GAN, ...