很多大佬在介紹代碼案例的時候，用到的MNIST數(shù)據(jù)集都是在代碼中直接下載使用，這樣做存在好處，但是，同樣存在弊端。
好處：不需要附上數(shù)據(jù)集
壞處：有時候網(wǎng)絡(luò)不好的時候，或者遠(yuǎn)程服務(wù)關(guān)閉了，導(dǎo)致數(shù)據(jù)無法下載。

下面介紹如何本地導(dǎo)入下載好的MNIST數(shù)據(jù)集：

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

# 定義加載數(shù)據(jù)的函數(shù)，data_folder為保存gz數(shù)據(jù)的文件夾，該文件夾下有4個文件
# '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/')