07_lstm.py

from keras.models import Sequential
from keras.layers import LSTM, Dense
from keras.datasets import mnist
from keras.utils import np_utils
from keras import initializations

def init_weights(shape, name=None):
    return initializations.normal(shape, scale=0.01, name=name)

# Hyper parameters
batch_size = 128
nb_epoch = 50

# Parameters for MNIST dataset
img_rows, img_cols = 28, 28
nb_classes = 10

# Parameters for LSTM network
nb_lstm_outputs = 30
nb_time_steps = img_rows
dim_input_vector = img_cols


# Load MNIST dataset
(X_train, y_train), (X_test, y_test) = mnist.load_data()
print('X_train original shape:', X_train.shape)
input_shape = (nb_time_steps, dim_input_vector)

X_train = X_train.astype('float32') / 255.
X_test = X_test.astype('float32') / 255.
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

# Build LSTM network
model = Sequential()
model.add(LSTM(nb_lstm_outputs, input_shape=input_shape))
model.add(Dense(nb_classes, activation='softmax', init=init_weights))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()

# Train
history = model.fit(X_train, Y_train, nb_epoch=nb_epoch, batch_size=batch_size, shuffle=True, verbose=1)

# Evaluate
evaluation = model.evaluate(X_test, Y_test, batch_size=batch_size, verbose=1)
print('Summary: Loss over the test dataset: %.2f, Accuracy: %.2f' % (evaluation[0], evaluation[1]))