'''Trains a simple ConvNet on the MNIST dataset. It gets more than 99% test accuracy after 12 epochs
(but there is still a lot of margin for parameter tuning). Training can take a few minutes!'''

# Import libraries
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

# Define hyperparameters
batch_size = 128
num_classes = 10
epochs = 12

# Input image dimensions
img_rows, img_cols = 28, 28

# Split the data 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)

# Define the sequential Keras model composed of a few layers
model = Sequential()
model.add(Conv2D(64, kernel_size=(4, 3),activation='relu', input_shape=input_shape))
model.add(Conv2D(64, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Dropout(0.10))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.15))
model.add(Dense(num_classes, activation='softmax'))

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

# Train the model, validate, evaluate, and present scores
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])