mnist_prediction.py

from keras import models
from keras import layers
from keras.datasets import mnist
from keras.utils import to_categorical

import keras

print(keras.__version__)

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

train_images.shape

len(train_labels)

print(train_labels)

test_images.shape

len(test_labels)

print(test_labels)

model = models.Sequential()
model.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))
model.add(layers.Dense(10, activation='softmax'))

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

train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255

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

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

model.fit(train_images, train_labels, epochs=5, batch_size=128)
test_loss, test_acc = model.evaluate(test_images, test_labels)

print('test_acc:', test_acc)

model.save('final_model.h5')

mnist_training.py

'''
brew install sox

https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-from-scratch-for-mnist-handwritten-digit-classification/
'''
from keras import models
from keras import layers
from keras.datasets import mnist
from keras.utils import to_categorical

import keras

print(keras.__version__)

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

train_images.shape

len(train_labels)

print(train_labels)

test_images.shape

len(test_labels)

print(test_labels)

model = models.Sequential()
model.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))
model.add(layers.Dense(10, activation='softmax'))

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

train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255

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

train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)

model.fit(train_images, train_labels, epochs=5, batch_size=128)
test_loss, test_acc = model.evaluate(test_images, test_labels)

print('test_acc:', test_acc)

model.save('final_model.h5')