mnist_double_cnn.py

Go to the documentation of this file.

'''Trains a simple convnet on the MNIST dataset.

Gets to 99.25% test accuracy after 12 epochs
(there is still a lot of margin for parameter tuning).
16 seconds per epoch on a GRID K520 GPU.
'''
# Taken from
# https://raw.githubusercontent.com/keras-team/keras/master/examples/

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

batch_size = 128
num_classes = 10
epochs = 100

# input image dimensions
img_rows, img_cols = 28, 28

# the data, 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_test /= 255
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)

# kernel_init = 'glorot_uniform'
kernel_init = 'he_uniform'
model = Sequential()
model.add(Conv2D(16, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape, use_bias=False,
                 kernel_initializer=kernel_init))
model.add(Conv2D(16, (3, 3), activation='relu', use_bias=False,
                 kernel_initializer=kernel_init))
# model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu', use_bias=False,
                kernel_initializer=kernel_init))
# model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax', use_bias=False))
# model.add(Dense(num_classes, activation='relu'))

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


model.save_weights('double_cnn_he_100.h5')
json_string = model.to_json()
with open('double_cnn_he_100.json', 'w') as file:
    file.write(json_string)