Let us start with the recipe:
- Import tensorflow, matplotlib, random, and numpy. Then, import the minst data and perform one-hot encoding. Note the TensorFlow has some built-in libraries to deal with MNIST and we are going to use them:
from __future__ import division, print_function
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
- Introspect some data to understand what MNIST is. This gives us an idea of how many images are in the training dataset and how many are in the test dataset. We are also going to visualize a few numbers just to understand how they ...
