klab-13-3-mnist_save_restore.py

# https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py
'''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.
'''

from __future__ import print_function
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
from keras.models import model_from_json
import os

np.random.seed(1337)  # for reproducibility

batch_size = 128
nb_classes = 10
nb_epoch = 12

img_rows, img_cols = 28, 28
nb_filters = 32
pool_size = (2, 2)
kernel_size = (3, 3)


# ==============================================================================
def build_model(X_train, Y_train, X_test, Y_test):
    model = Sequential()

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

    model.add(Flatten())
    model.add(Dense(128))
    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'])

    model.fit(X_train, Y_train,
              batch_size=batch_size,
              epochs=nb_epoch,
              verbose=1,
              validation_data=(X_test, Y_test))

    return model


# ==============================================================================
# load data
(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
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')

Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)


# ==============================================================================
# build or load model
if os.path.exists('model.json'):
    with open("model.json", "r") as json_file:
        loaded_model_json = json_file.read()
        model = model_from_json(loaded_model_json)
    model.load_weights("model.h5")

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

    print('model loaded...')
else:
    model = build_model(X_train, Y_train, X_test, Y_test)

    model_json = model.to_json()
    with open("model.json", "w") as json_file:
        json_file.write(model_json)
    model.save_weights("model.h5")

    print('model saved...')


# ==============================================================================
# evaluate
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

# fix tensorflow bug.
K.clear_session()