Building Machine Learning Systems with Python - Third Edition

LSTM for image processing

Let's imagine we want to perform handwriting recognition. From time to time, we get a new column of data. Is it the end of a letter? If yes, which one? Is it the end of a word? Is it punctuation? All these questions can be answered with a recurrent network.

For our test example, we will go back to our 10-digit dataset and use LSTMs instead of convolution layers.

We use similar hyperparameters:

import tensorflow as tffrom tensorflow.contrib import rnn# rows of 28 pixelsn_input=28# unrolled through 28 time steps (our images are (28,28))time_steps=28# hidden LSTM unitsnum_units=128# learning rate for adamlearning_rate=0.001n_classes=10batch_size=128n_epochs = 10step = 100

Setting up training and testing data is almost ...