How can I import the MNIST dataset that has been manually downloaded?

Question

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

It should be related to the network environment I am using. Is there any function or code that can let me directly import the MNIST data set that has been manually downloaded?

I tried the following 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)

Answer 1

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

1. Download a dataset from https://s3.amazonaws.com/img-datasets/mnist.pkl.gz

2. .

   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
   

Answer 2

Keras file is located into a new path in Google Cloud Storage (Before it was in AWS S3):

https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz

When using:

tf.keras.datasets.mnist.load_data()

You can pass a path parameter.

load_data() will call get_file() which takes as parameter fname, if path is a full path and file exists, it will not be downloaded.

Example:

# gsutil cp gs://tensorflow/tf-keras-datasets/mnist.npz /tmp/data/mnist.npz
# python3
>>> import tensorflow as tf
>>> path = '/tmp/data/mnist.npz'
>>> (train_images, train_labels), (test_images, test_labels) = tf.keras.datasets.mnist.load_data(path)
>>> len(train_images)
>>> 60000

Answer 3

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

1. You can download the file https://s3.amazonaws.com/img-datasets/mnist.npz from another computer with proper (proxy) access (taken from https://github.com/keras-team/keras/blob/master/keras/datasets/mnist.py),
2. copy it to the the directory ~/.keras/datasets/ (on Linux and macOS)
3. and run load_data(path='mnist.npz') with the right file name

Answer 4

1. Download file https://s3.amazonaws.com/img-datasets/mnist.npz
2. Move mnist.npz to .keras/datasets/ directory

3. Load data

   import keras
   from keras.datasets import mnist
   
   (X_train, y_train), (X_test, y_test) = mnist.load_data()
   

Answer 5

keras.datasets.mnist.load_data() will attempt to fetch from the remote repository even when a local file path is specified. However, the easiest workaround to load the downloaded file is to use numpy.load(), just like they do:

path = '/tmp/data/mnist.npz'

import numpy as np

with np.load(path, allow_pickle=True) as f:
    x_train, y_train = f['x_train'], f['y_train']
    x_test, y_test = f['x_test'], f['y_test']

Answer 6

Gogasca's answer worked for me with a little adjustment. For Python 3.9, changing the code in ~/Library/Python/3.9/lib/python/site-packages/keras/datasets/mnist.py so that it uses the path variable as full path instead of adding the origin_folder makes it possible to pass any local path to the downloaded file.

1. Download the file: https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
2. Put it in ~/Library/Python/3.9/lib/python/site-packages/keras/datasets/, or another location to Your liking.
3. Alter ~/Library/Python/3.9/lib/python/site-packages/keras/datasets/mnist.py

path = path

""" origin_folder = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/' """
""" path = get_file(
path,origin=origin_folder + 'mnist.npz',file_hash='731c5ac602752760c8e48fbffcf8c3b850d9dc2a2aedcf2cc48468fc17b673d1') """

with np.load(path, allow_pickle=True) as f:  # pylint:
    disable=unexpected-keyword-arg
    x_train, y_train = f['x_train'], f['y_train']
    x_test, y_test = f['x_test'], f['y_test']
return (x_train, y_train), (x_test, y_test)

4. use the following code to load data:

path = "/Users/username/Library/Python/3.9/lib/python/site-packages/keras/datasets/mnist.npz"
(train_images, train_labels), (test_images, test_labels ) = mnist.load_data(path=path)```