人工智能教程：Spring Boot+OAuth2，一個注解搞定單點登錄！

神經網絡比較深…下面的代碼最好運行在GPU上

環境參數：Keras == 2.1.2
Tensorflow = 1.4.0

import keras

from keras.datasets import cifar10

from keras.preprocessing.image import ImageDataGenerator

from keras.models import Sequential

from keras.layers import Dense,Dropout,Flatten,Activation

from keras.layers import Conv2D,MaxPooling2D,ZeroPadding2D,GlobalMaxPooling2D



#加載數據集

batch_size = 32

num_classes = 10

epochs = 1600

data_augmentation = True



(x_train,y_train),(x_test,y_test) = cifar10.load_data()

print('x_train shape:',x_train.shape)

print(x_train.shape[0],'train samples')

print(x_test.shape[0],'test samples')

x_train = x_train.astype('float32')

x_test  = x_test.astype('float32')

x_train /= 255

x_test  /= 255



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

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



#搭建網絡 

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(48, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(48, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))

model.add(Conv2D(80, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(80, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(80, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(80, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(80, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))

model.add(Conv2D(128, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(128, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(128, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(128, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(128, (3, 3), padding='same',input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(GlobalMaxPooling2D())

model.add(Dropout(0.25))

model.add(Dense(500))

model.add(Activation('relu'))

model.add(Dropout(0.25))

model.add(Dense(num_classes))

model.add(Activation('softmax'))

model.summary()



#模型編譯訓練

opt = keras.optimizers.Adam(lr = 0.0001)

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

print("---------train---------")

model.fit(x_train,y_train,epochs = 600,batch_size = 128,)

print("---------test---------")

loss,acc = model.evaluate(x_test,y_test)

print("loss=",loss)

print("accuracy=",acc)
#基于數據增強的訓練方法

if not data_augmentation:

   print('Not using data augmentation.')

   model.fit(x_train, y_train,

             batch_size=batch_size,

             epochs=epochs,

             validation_data=(x_test, y_test),

             shuffle=True, callbacks=[tbCallBack])

else:

   print('Using real-time data augmentation.')

   datagen = ImageDataGenerator(

       featurewise_center=False,  # set input mean to 0 over the dataset

       samplewise_center=False,  # set each sample mean to 0

       featurewise_std_normalization=False,  # divide inputs by std of the dataset

       samplewise_std_normalization=False,  # divide each input by its std

       zca_whitening=False,  # apply ZCA whitening

       rotation_range=10,  # randomly rotate images in the range (degrees, 0 to 180)

       width_shift_range=0.2,  # randomly shift images horizontally (fraction of total width)

       height_shift_range=0.2,  # randomly shift images vertically (fraction of total height)

       horizontal_flip=True,  # randomly flip images

       vertical_flip=False)  # randomly flip images



   datagen.fit(x_train)

   model.fit_generator(datagen.flow(x_train,y_train,batch_size=batch_size),                                   

                       steps_per_epoch=x_train.shape[0] // batch_size,

                       epochs=epochs,

                       validation_data=(x_test, y_test), callbacks=[tbCallBack])