人工智能教程：Spring Boot+OAuth2，一個註解搞定單點登錄！

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

<code>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

 
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)

 
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()

 
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)


 
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,   
       samplewise_center=False,   
       featurewise_std_normalization=False,   
       samplewise_std_normalization=False,   
       zca_whitening=False,   
       rotation_range=
10
,   
       width_shift_range=
0.2
,   
       height_shift_range=
0.2
,   
       horizontal_flip=True,   
       vertical_flip=False)   

   datagen.fit(x_train)
   model.fit_generator(datagen.flow(x_train,y_train,batch_size=batch_size),                                   
                       steps_per_epoch=x_train.shape[
0
]  
                       epochs=epochs,
                       validation_data=(x_test, y_test), callbacks=[tbCallBack])/<code>