python3中ascii字节不够的问题

在学习机器学习时，用了http://deeplearning.net/tutorial/中的案例
f = gzip.open('mnist.pkl.gz','rb')
train_set, valid_set, test_set = pickle.load(f)
f.close()
结果因为python3编码的问题一直报错如下
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "C:\rdataset\161028\d1Ml.py", line 7, in <module>
    train_set, valid_set, test_set = pickle.load(f)
UnicodeDecodeError: 'ascii' codec can't decode byte 0x90 in position 614: ordinal not in range(128)
最终在一个日本的博客里找到解决办法点击打开链接
f = gzip.open(dataset, 'rb')
train_set, valid_set, test_set = pickle.load(f, encoding='latin1')
f.close()