train.py

# Getting Data
from keras.datasets import mnist
from keras.utils import to_categorical

(train_images, train_labels), (test_images, test_labels) = mnist.load_data()


train_images = train_images.reshape((60000,28,28,1)) # (n_imgs, h, w, channels)
train_images = train_images.astype('float32')/ 255. 

test_images = test_images.reshape((10000,28,28,1))
test_images = test_images.astype('float32') / 255. 

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

model.fit(train_images, train_labels, epochs = 5, batch_size = 64)

# Testing
test_loss, test_acc = model.evaluate(test_images, test_labels)

print('{}% accurate'.format(test_acc*100))