Practical Convolutional Neural Networks

GAN – code example

In the following example, we build and train a GAN model using an MNIST dataset and using TensorFlow. Here, we will use a special version of the ReLU activation function known as Leaky ReLU. The output is a new type of handwritten digit:

Leaky ReLU is a variation of the ReLU activation function given by the formula f(x) = max(α∗x, x). So the output for the negative value for x is alpha * x and the output for positive x is x.

#import all necessary libraries and load data set%matplotlib inlineimport pickle as pklimport numpy as npimport tensorflow as tfimport matplotlib.pyplot as pltfrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets('MNIST_data')

In order to build this network, we ...