MNIST-Conv-SELU.py

# Adapted KERAS tutorial 

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, AlphaDropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 30

# input image dimensions
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
    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_train = (x_train - np.mean(x_train))/np.std(x_train)

x_test /= 255
# x_test = (x_test - np.mean(x_train))/np.std(x_train)

print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='selu', input_shape=input_shape, kernel_initializer='lecun_normal',
                 bias_initializer='zeros'))
model.add(Conv2D(64, (3, 3), activation='selu', kernel_initializer='lecun_normal', bias_initializer='zeros'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(AlphaDropout(0.25))
model.add(Flatten())
model.add(Dense(512, activation='selu', kernel_initializer='lecun_normal', bias_initializer='zeros'))
model.add(AlphaDropout(0.5))
model.add(Dense(num_classes, activation='softmax', kernel_initializer='lecun_normal', bias_initializer='zeros'))

model.compile(loss=keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adadelta(), metrics=['accuracy'])

model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

f = open('MNIST_SELU_results.txt', 'a')
f.write('Test loss:' + str(score[0]) + ' Test accuracy:' + str(score[1]) + '\n')  # python will convert \n to os.linesep
f.close()