Handwritten Digit Recognition

Objective: Classify handwritten digits from the MNIST dataset by training a convolutional neural network (CNN) using the Keras deep learning library.

Data Preparation

We begin by downloading the data and creating training & validation sets. Keras has inbuilt helper functions to do this.

from keras.datasets import mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

Using TensorFlow backend.

import jovian

jovian.log_dataset('data/mnist')

jovian.log_dataset({
    'path': 'data/mnist',
    'hash': 'sfsfsfasdfsdf23423',
    'size': '100MB'
})

Each sample is a 28px x 28 px image, flattened out a vector of length 784 i.e. 28x28.