Deep Learning with TensorFlow - Second Edition

Implementing autoencoders with TensorFlow

Training an autoencoder is a simple process. It is an NN, where an output is the same as its input. There is an input layer, which is followed by a few hidden layers, and then after a certain depth, the hidden layers follow the reverse architecture until we reach a point where the final layer is the same as the input layer. We pass data into the network whose embedding we wish to learn.

In this example, we use images from the MNIST dataset as input. We begin our implementation by importing all the main libraries:

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

Then we prepare the MNIST dataset. We use the built-in input_data class from TensorFlow to load and set up the data. This ...