TensorFlow 1.x Deep Learning Cookbook

How to do it...

We proceed with the recipe as follows:

1. We import the necessary modules:

import tensorflow as tfimport numpy as npfrom tensorflow.examples.tutorials.mnist import input_dataimport matplotlib.pyplot as plt%matplotlib inline

2. Load the MNIST dataset from TensorFlow examples:

mnist = input_data.read_data_sets("MNIST_data/")trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels

3. Define the SparseAutoEncoder class, which is very similar to the autoencoder class in the previous recipe, except for introducing the KL divergence loss:

def kl_div(self, rho, rho_hat): term2_num = tf.constant(1.)- rho term2_den = tf.constant(1.) - rho_hat kl = self.logfunc(rho,rho_hat) + self.logfunc(term2_num, ...