Apache Spark Deep Learning Cookbook

How to do it...

This section walks through the steps to build a model to recognize handwritten images from MNIST.

1. Create testing and training images and labels based on the MNIST dataset from the following variables using the following script:

xtrain = data.train.imagesytrain = np.asarray(data.train.labels)xtest = data.test.images ytest = np.asarray(data.test.labels)

2. Reshape the testing and training arrays using the following script:

xtrain = xtrain.reshape( xtrain.shape[0],28,28,1)xtest = xtest.reshape(xtest.shape[0],28,28,1)ytest= ytest.reshape(ytest.shape[0],10)ytrain = ytrain.reshape(ytrain.shape[0],10)

3. Import the following from keras to build the convolutional neural network model:

import kerasimport keras.backend as Kfrom keras.models ...