November 2017
Intermediate to advanced
274 pages
6h 16m
English
Let's look at the NotMNIST dataset, which we explored in Chapter 2, Deep Feedforward Networks, in the Implementing feedforward networks section with images, and see how our DBN works for that dataset.
We will leverage the same pickle file, notMNIST.pickle, created in Chapter 2, Deep Feedforward Networks. The initialization parameters and imports are listed here:
import tensorflow as tfimport numpy as npimport cPickle as picklefrom common.models.boltzmann import dbnfrom common.utils import datasets, utilitiesflags = tf.app.flagsFLAGS = flags.FLAGSpickle_file = '../notMNIST.pickle'image_size = 28num_of_labels = 10RELU = 'RELU'RELU6 = 'RELU6'CRELU = 'CRELU'SIGMOID = 'SIGMOID'ELU = 'ELU'SOFTPLUS = ...
Read now
Unlock full access