Tutorial_2.2_MNIST_cnn.py

from __future__ import print_function

import os
import numpy as np
import tensorflow as tf

# prevent a single instance from claiming all memory

import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
session = tf.Session(config=config)

# start

np.random.seed(5005)
tf.set_random_seed(5005)

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

from keras.backend.tensorflow_backend import set_session
from keras.layers.normalization import BatchNormalization

## GPU OPTIONS
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
set_session(tf.Session(config=config))

## PREPARE MNIST

batch_size = 128
num_classes = 10
epochs = 12

# 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_test /= 255

# 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)


## BUILD MODEL
cnn = Sequential()
cnn.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=input_shape))
cnn.add(Conv2D(64, (3, 3), activation='relu'))
cnn.add(MaxPooling2D(pool_size=(2, 2)))
cnn.add(Dropout(0.25))
cnn.add(Flatten())
cnn.add(Dense(128, activation='relu'))
cnn.add(Dropout(0.5))
cnn.add(Dense(num_classes, activation='softmax'))

cnn.compile(loss=keras.losses.categorical_crossentropy,
              optimizer='adam',
              metrics=['accuracy'])

## TRAIN

cnn.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=5,
          verbose=1,
          validation_data=(x_test, y_test))