The MNSIT dataset is a database of handwritten digits, and contains 60,000 training examples and 10,000 testing examples:

from tensorflow.examples.tutorials.mnist import input_data

 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

We will load the image database from MNIST:

import matplotlib.pyplot as plt 

im = mnist.train.images[0,:] 

label = mnist.train.labels[0,:] 

im = im.reshape([28,28])

We can construct a fully connected feed-forward neural network that is one layer deep to complete the example.