Karas 从网上下载的数据集都保存在下面的目录里

from tensorflow import keras
from tensorflow.keras import layers
cifar = keras.datasets.cifar10

(train_image, train_label), (test_image, test_label) = cifar.load_data()

从datasets中直接加载数据集

train_image.shape, test_image.shape

神经网络：最好做归一化处理（神经网络喜欢统一的，比较小的数据）

train_image = train_image/255
test_image = test_image/255

model = keras.Sequential()
model.add(layers.Conv2D(64, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D())
model.add(layers.Dropout(0.25))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.BatchNormalization())
model.add(layers.MaxPooling2D())
model.add(layers.Dropout(0.25))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.Conv2D(256, (1, 1), activation='relu'))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.25))          
model.add(layers.GlobalAveragePooling2D())
model.add(layers.Dense(128))
model.add(layers.BatchNormalization())  
model.add(layers.Dropout(0.5))         
model.add(layers.Dense(10, activation='softmax'))

model.summary()

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['acc']
)
history = model.fit(train_image, train_label, epochs=30, batch_size=128)

model.evaluate(test_image, test_label)

model.evaluate(test_image, test_label)