Clash Royale CLAN TAG#URR8PPP

the alternative to from keras.datasets import mnist

I have been experimenting with a Keras example, which needs to import MNIST data

from keras.datasets import mnist
import numpy as np
(x_train, _), (x_test, _) = mnist.load_data()


It generates error messages such as Exception: URL fetch failure on https://s3.amazonaws.com/img-datasets/mnist.pkl.gz: None -- [Errno 110] Connection timed out


Exception: URL fetch failure on https://s3.amazonaws.com/img-datasets/mnist.pkl.gz: None -- [Errno 110] Connection timed out


It should be related to the network environment I am using. My question is that, are there any function or code that can let me directly import mnist data set that has been manually downloaded. Thanks.

This is the modified approach

import sys
import pickle
import gzip
f = gzip.open('/data/mnist.pkl.gz', 'rb')
if sys.version_info < (3,):
data = pickle.load(f)
else:
data = pickle.load(f, encoding='bytes')
f.close()
import numpy as np
(x_train, _), (x_test, _) = data


Then I get the following error message

Traceback (most recent call last):
File "test.py", line 45, in <module>
(x_train, _), (x_test, _) = data
ValueError: too many values to unpack (expected 2)


2 Answers
2

Well, the keras.datasets.mnist file is really short. You can manually simulate the same action, that is:

keras.datasets.mnist

.

import gzip
f = gzip.open('mnist.pkl.gz', 'rb')
if sys.version_info < (3,):
data = cPickle.load(f)
else:
data = cPickle.load(f, encoding='bytes')
f.close()
(x_train, _), (x_test, _) = data


You do not need additional code for that but can tell load_data to load a local version in the first place:

load_data

~/.keras/datasets/

load_data(path='mnist.npz')

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.