keras中無法下載 https://s3.amazonaws.com/img-datasets/mnist.npz 解決方法

網址：https://s3.amazonaws.com/img-datasets/mnist.npz，由於顯而易見的原因，無法訪問。
npz實際上是numpy提供的數組存儲方式，簡單的可看做是一系列npy數據的組合，利用np.load函數讀取后得到一個類似字典的對象，可以通過關鍵字進行值查詢，關鍵字對應的值其實就是一個npy數據。
如果用keras自帶的example（from keras.datasets import mnist，在mnist.py下的load_data函數），會使用這種格式。

 

我自己解決方法是在國外的vps機器上下載，然后傳到本地，假設保存為mnist.npz，則加載方法：

import numpy as np
def load_data(path='mnist.npz'):
    """Loads the MNIST dataset.
    # Arguments
        path: path where to cache the dataset locally
            (relative to ~/.keras/datasets).
    # Returns
        Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
    path = get_file(path,
                    origin='https://s3.amazonaws.com/img-datasets/mnist.npz',
                    file_hash='8a61469f7ea1b51cbae51d4f78837e45')
    """
    f = np.load(path)
    x_train, y_train = f['x_train'], f['y_train']
    x_test, y_test = f['x_test'], f['y_test']
    f.close()
    return (x_train, y_train), (x_test, y_test)

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = load_data()

 

原來的是：

(x_train, y_train), (x_test, y_test) = mnist.load_data()

 替換下OK!