mnist.py

import os, sys
import numpy as np

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.utils import np_utils
from keras import backend as K


batch_size = 128
nb_classes = 10
nb_epoch = 20

img_rows, img_cols = 28, 28
nb_filters = 64
pool_size = (2, 2)
kernel_size = (3, 3)

(X_train, y_train), (X_test, y_test) = mnist.load_data()

if K.image_dim_ordering() == 'th':
    X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
    X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
    X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

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)



model = Sequential()

model.add(Conv2D(nb_filters,
                 kernel_size=kernel_size,
                 padding='same',
                 input_shape=input_shape))
model.add(Activation('relu'))
model.add(Conv2D(nb_filters, kernel_size=kernel_size))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))

model.add(Conv2D(nb_filters*2, kernel_size=kernel_size, padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(nb_filters*2, kernel_size=kernel_size))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))

model.add(Conv2D(nb_filters*4, kernel_size=kernel_size, padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(nb_filters*4, kernel_size=kernel_size))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=pool_size))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adadelta',
              metrics=['accuracy'])

print('Starting fit...', file=sys.stderr)
history = model.fit(X_train, Y_train, batch_size=batch_size, epochs=nb_epoch,
                    verbose=2, validation_data=(X_test, Y_test))
print('Fit complete.', file=sys.stderr)