######################################################################
# MNIST using keras
# checked 10-14-2019 (tensorflow version 2.0.0)
######################################################################

import tensorflow.keras as keras
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.optimizers import RMSprop

import matplotlib.pyplot as plt

batch_size = 128
num_classes = 10
epochs = 20

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(60000, 28 * 28)
x_train = x_train.astype('float32') / 255.0
x_train.shape

x_test = x_test.reshape(10000, 28 * 28)
x_test = x_test.astype('float32') / 255.0
x_test.shape

# convert class vectors to binary class matrices

y_train = keras.utils.to_categorical(y_train, num_classes)
y_train.shape
y_test = keras.utils.to_categorical(y_test, num_classes)
y_test.shape

# define the model

model = Sequential()
model.add(Dense(512, activation = 'relu', input_shape = (784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation = 'relu'))
model.add(Dropout(0.2))
model.add(Dense(num_classes, activation = 'softmax'))

model.summary()

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

history = model.fit(x_train, y_train,
                    batch_size = batch_size,
                    epochs = epochs,
                    verbose = 1,
                    validation_data = (x_test, y_test))

history.history.keys()
history.history.get('val_loss')

plt.plot(history.epoch, history.history.get('accuracy'), 'bs')
plt.plot(history.epoch, history.history.get('val_accuracy'), 'r^')
plt.show()

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


######################################################################
# THE END
######################################################################