Classifying handwritten digits

In the previous section, we covered a lot of the theory around neural networks, which can be a little overwhelming if you are new to this topic. In this section, we will use the famous MNIST dataset, which contains 60,000 samples of handwritten digits along with their labels.

We will train two different networks on it:

• An MLP using OpenCV
• A deep neural network using Keras

Loading the MNIST dataset

The easiest way to obtain the MNIST dataset is by using Keras:

In [1]: from keras.datasets import mnist
...     (X_train, y_train), (X_test, y_test) = mnist.load_data()
Out[1]: Using TensorFlow backend.
        Downloading data from
        https://s3.amazonaws.com/img-datasets/mnist.npz

This will download...