python中本地加载MNIST数据集

很多大佬在介绍代码案例的时候，用到的MNIST数据集都是在代码中直接下载使用，这样做存在好处，但是，同样存在弊端。
好处：不需要附上数据集
坏处：有时候网络不好的时候，或者远程服务关闭了，导致数据无法下载。

下面介绍如何本地导入下载好的MNIST数据集：

            
              # -*- coding: utf-8 -*-
"""
Created on Mon May 27 15:07:23 2019
@author: AugustMe
"""
import numpy as np
import os
import gzip

# 定义加载数据的函数，data_folder为保存gz数据的文件夹，该文件夹下有4个文件
# 'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
# 't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'

def load_data(data_folder):

  files = [
      'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
      't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
  ]

  paths = []
  for fname in files:
    paths.append(os.path.join(data_folder,fname))

  with gzip.open(paths[0], 'rb') as lbpath:
    y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)

  with gzip.open(paths[1], 'rb') as imgpath:
    x_train = np.frombuffer(
        imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)

  with gzip.open(paths[2], 'rb') as lbpath:
    y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)

  with gzip.open(paths[3], 'rb') as imgpath:
    x_test = np.frombuffer(
        imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)

  return (x_train, y_train), (x_test, y_test)

(train_images, train_labels), (test_images, test_labels) = load_data('MNIST_data/')