04_modern_net.py

from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.optimizers import RMSprop
from keras.datasets import mnist
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epoch = 100

# Load MNIST dataset
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

# Deep Multilayer Perceptron model
model = Sequential()
model.add(Dense(output_dim=625, input_dim=784, init='normal'))
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(output_dim=625, input_dim=625, init='normal'))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(output_dim=10, input_dim=625, init='normal'))
model.add(Activation('softmax'))

model.compile(optimizer=RMSprop(lr=0.001, rho=0.9), loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()

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

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