3.2tensorflow2.0中几个简单常用的图片数据集介绍及加载方式

代码会检查有没有数据集在本地，没有数据集的话代码会自动下载，注意科学上网提高下载速度

MNIST数据集

• 一个手写数字数据集，共10类

from tensorflow import keras

(x_train,y_train),(x_test,y_test)=keras.datasets.mnist.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (60000, 28, 28) (60000,) (10000, 28, 28) (10000,)      

Fashion_MNIST

• 一个服装数据集，共10类

(x_train,y_train),(x_test,y_test)=keras.datasets.fashion_mnist.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (60000, 28, 28) (60000,) (10000, 28, 28) (10000,)      

Cifar10/100

• 一个各类东西的数据集，cifar10和cifar100数据集图片是一样的，只是cifar100在cifar10上的10个类别的基础上，在每个小类别里又划分成了新的10类，共10*10=100类

(x_train,y_train),(x_test,y_test)=keras.datasets.cifar10.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (50000, 32, 32, 3) (50000, 1) (10000, 32, 32, 3) (10000, 1)

(x_train,y_train),(x_test,y_test)=keras.datasets.cifar100.load_data()
print(x_train.shape,y_train.shape,x_test.shape,y_test.shape)
# (50000, 32, 32, 3) (50000, 1) (10000, 32, 32, 3) (10000, 1)