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 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
import numpy as np
import tensorflow as tf

from helpers import make_tmp


def cnn(combination, learning_rate, epochs, batches, seed):
    np.random.seed(seed)
    tf.random.set_random_seed(seed)

    make_tmp()

    num_classes = 10

    # 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)

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

    model.compile(loss=keras.losses.categorical_crossentropy,
                  optimizer=keras.optimizers.Adadelta(lr=learning_rate),  # 1
                  metrics=['accuracy'])

    from datetime import datetime
    now = datetime.utcnow().strftime("%Y%m%d%H%M%S")
    save_string = "mnist-" + str(combination) + "-" + str(learning_rate) + "-" + str(epochs) + "-" + str(
        batches) + "-" + str(seed)
    root_logdir = "logs"
    logdir = "{}/{}-{}".format(root_logdir, save_string, now)
    tensorboard = keras.callbacks.TensorBoard(log_dir=logdir)

    model.fit(x_train, y_train,
              batch_size=batches,  # 128
              epochs=epochs,  # 12
              verbose=1,
              callbacks=[tensorboard],
              validation_data=(x_test, y_test))

    model.save('logs/' + save_string + '.ckpt')

    # new_model = keras.models.load_model('mnist-cnn-0-1-1-128-420.ckpt')

    score = model.evaluate(x_test, y_test, verbose=0)
    # score = new_model.evaluate(x_test, y_test, verbose=0)
    print('Test loss:', score[0])
    print('Test accuracy:', score[1])

    score = model.evaluate(x_train, y_train, verbose=0)
    # score = new_model.evaluate(x_test, y_test, verbose=0)
    print('Test loss:', score[0])
    print('Test accuracy:', score[1])


if __name__ == "__main__":
    cnn(0, 1, 0, 128, 420)