Loading the dataset

First, we load the dataset from idx3 and idx1 formats into test, train, and validation sets. We need to import TensorFlow common utilities that are defined in the common module explained here:

import tensorflow as tffrom common.models.boltzmann import dbnfrom common.utils import datasets, utilities
trainX, trainY, validX, validY, testX, testY =      datasets.load_mnist_dataset(mode='supervised')

You can find details about load_mnist_dataset() in the following code listing. As mode='supervised' is set, the train, test, and validation labels are returned:

def load_mnist_dataset(mode='supervised', one_hot=True):   mnist = input_data.read_data_sets("MNIST_data/", one_hot=one_hot)   # Training set   trX = mnist.train.images trY = mnist.train.labels ...

Get Neural Network Programming with TensorFlow now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.