Keras Deep Learning Cookbook

Train the model

1. Once the network is compiled, it is trained on the test data as follows:

# train LSTMfor i in range(n_epoch):model.fit(seq1X, seq1Y, epochs=1, batch_size=n_batch, verbose=1, shuffle=False)model.reset_states()model.fit(seq2X, seq2Y, epochs=1, batch_size=n_batch, verbose=0, shuffle=False)model.reset_states() 

2. The last step is to test against sequences one and two, shown as follows:

# test LSTM on sequence 1print('Sequence 1')result = model.predict_classes(seq1X, batch_size=n_batch, verbose=0)model.reset_states()for i in range(len(result)):    print('X=%s y=%s, yhat=%s' % (seq1[i], seq1[i+1], chr(result[i])))# test LSTM on sequence 2print('Sequence 2')result = model.predict_classes(seq2X, batch_size=n_batch, verbose=0)model.reset_states() ...