cifar10数据读取

 数据读取

需要提前配置有keras的环境

下载CIFAR-10 and CIFAR-100 datasets的python版本并解压到C:\Users\mage\.keras\datasets

REF：读取cifar-10数据集_zhanzi1538的博客-CSDN博客_cifar10数据集读取

from __future__ import print_function
from six.moves import cPickle as pickle
import numpy as np
import os
import platform


# 读取文件
def load_pickle(f):
    version = platform.python_version_tuple()  # 取python版本号
    if version[0] == '2':
        return pickle.load(f)  # pickle.load, 反序列化为python的数据类型
    elif ve