keras_mnist

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
import matplotlib.pyplot as plt

# step1
(x_train, y_train), (x_test, y_test) = mnist.load_data()

plt.figure()
plt.imshow(x_train[30], cmap='gray')
plt.show()
print(y_train.shape)
print(y_train[30])

# step2
img_rows, img_cols = 28, 28

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)

# step3
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')

# step4
num_classes = 10
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# step5
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'))

# step6
model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

# step7
model.fit(x_train, y_train,
          batch_size=128,
          epochs=12,
          verbose=1,
          validation_data=(x_test, y_test))

# step8
score = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# step9
prediction = model.predict(x_test[20].reshape(1,28,28,1))
prediction = prediction.argmax(axis=1)
plt.figure()
plt.imshow(x_test[20].reshape(28,28))
plt.text(0,-3,prediction)
plt.show()

# step10
model.save('my_model.h5')