一、變數初始化

batch_size = 128
nb_classes = 10
nb_epoch = 20

二、準備資料

(X_train, y_train), (X_test, y_test) = mnist.load_data()
#將3D轉化為2D
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
# 對資料進行歸一化到0-1 因為影象資料最大是255
X_train /= 255
 

X_test /= 255
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
# 將類別向量(從0到nb_classes的整數向量)對映為二值類別矩陣
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
print(Y_train.shape)
print(Y_test.shape)

三、建立模型

model = Sequential()
model.add
 
(Dense(512, input_shape=(784,)))#Dense的第一個引數是輸出維度
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.3))
model.add(Dense(10))
model.add(Activation('softmax'))

四、列印模型

print(model.summary())
plot_model(model, to_file='model.png'
 
)

五、編譯、訓練和評估模型

model.compile(loss='categorical_crossentropy',
              optimizer=RMSprop(),
              metrics=['accuracy'])
history = model.fit(X_train,Y_train,batch_size=batch_size,epochs=nb_epoch,verbose=1,validation_data=(X_test,Y_test))
score = model.evaluate(X_test, Y_test, verbose=0)
print('Test score:', score[0])
print('Test accuracy:', score[1])

六、儲存模型

model.save('mnist-mpl.h5')

原始碼地址：