Before we jump into building our awesome neural network, let's first have a look at the famous MNIST dataset. So let's visualize the MNIST dataset in this section.
Words of wisdom: You must know your data and how it has been preprocessed, in order to know why the models you build perform the way they do. This section reviews the significant work that has been done in preparation on the dataset, to make our current job of building the MLP easier. Always remember: data science begins with DATA!
Let's start therefore by downloading the data, using the following commands:
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
If we examine the mnist variable content, we can see that it is structured in a specific format, with three major components—TRAIN, TEST...