Handwritten digit classification using TensorFlow
Putting together all the concepts we have learned so far, we will see how we can use TensorFlow to build a neural network to recognize handwritten digits. If you have been playing around with deep learning of late, then you must have come across the MNIST dataset. It has been called the hello world of deep learning. It consists of 55,000 data points of handwritten digits (0 to 9).
Importing the required libraries
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import matplotlib.pyplot as plt