Python：加载 MNIST 数据时出错

Question

Error occured when I was loading the MNIST data using the following code.(anaconda has already been installed and coded on online Jupyter notebook.)

from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')

Timeouterror appeared and I have no idea where I made mistakes. I have closed my vpn proxy and it didnt work. Help!

TimeoutError                              Traceback (most recent call last)
<ipython-input-1-3ba7b9c02a3b> in <module>()
      1 from sklearn.datasets import fetch_mldata
----> 2 mnist = fetch_mldata('MNIST original')

~\Anaconda3\lib\site-packages\sklearn\datasets\mldata.py in fetch_mldata(dataname, target_name, data_name, transpose_data, data_home)
    152         urlname = MLDATA_BASE_URL % quote(dataname)
    153         try:
--> 154             mldata_url = urlopen(urlname)
    155         except HTTPError as e:
    156             if e.code == 404:

~\Anaconda3\lib\urllib\request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    221     else:
    222         opener = _opener
--> 223     return opener.open(url, data, timeout)
    224 
    225 def install_opener(opener):

~\Anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
    524             req = meth(req)
    525 
--> 526         response = self._open(req, data)
    527 
    528         # post-process response

~\Anaconda3\lib\urllib\request.py in _open(self, req, data)
    542         protocol = req.type
    543         result = self._call_chain(self.handle_open, protocol, protocol +
--> 544                                   '_open', req)
    545         if result:
    546             return result

~\Anaconda3\lib\urllib\request.py in _call_chain(self, chain, kind, meth_name, *args)
    502         for handler in handlers:
    503             func = getattr(handler, meth_name)
--> 504             result = func(*args)
    505             if result is not None:
    506                 return result

~\Anaconda3\lib\urllib\request.py in http_open(self, req)
   1344 
   1345     def http_open(self, req):
-> 1346         return self.do_open(http.client.HTTPConnection, req)
   1347 
   1348     http_request = AbstractHTTPHandler.do_request_

~\Anaconda3\lib\urllib\request.py in do_open(self, http_class, req, **http_conn_args)
   1319             except OSError as err: # timeout error
   1320                 raise URLError(err)
-> 1321             r = h.getresponse()
   1322         except:
   1323             h.close()

~\Anaconda3\lib\http\client.py in getresponse(self)
   1329         try:
   1330             try:
-> 1331                 response.begin()
   1332             except ConnectionError:
   1333                 self.close()

~\Anaconda3\lib\http\client.py in begin(self)
    295         # read until we get a non-100 response
    296         while True:
--> 297             version, status, reason = self._read_status()
    298             if status != CONTINUE:
    299                 break

~\Anaconda3\lib\http\client.py in _read_status(self)
    256 
    257     def _read_status(self):
--> 258         line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
    259         if len(line) > _MAXLINE:
    260             raise LineTooLong("status line")

~\Anaconda3\lib\socket.py in readinto(self, b)
    584         while True:
    585             try:
--> 586                 return self._sock.recv_into(b)
    587             except timeout:
    588                 self._timeout_occurred = True

TimeoutError: [WinError 10060] A connection attempt failed because the connected party did not properly respond after a period of time, or established connection failed because connected host has failed to respond

I downloaded the MNIST dataset and tried to load the data myself instead. I copied the code used to load the MNIST but I failed to load data again. I thought I need to change some code rather than completely copy the code from Internet but I dont know where I should do the change.(Just a beginner of Python) The code I used to load the downloaded MNIST data.Is it because I put the data in a wrong file?

def loadmnist(imagefile, labelfile):

    # Open the images with gzip in read binary mode
    images = open(imagefile, 'rb')
    labels = open(labelfile, 'rb')

    # Get metadata for images
    images.read(4)  # skip the magic_number
    number_of_images = images.read(4)
    number_of_images = unpack('>I', number_of_images)[0]
    rows = images.read(4)
    rows = unpack('>I', rows)[0]
    cols = images.read(4)
    cols = unpack('>I', cols)[0]

    # Get metadata for labels
    labels.read(4)
    N = labels.read(4)
    N = unpack('>I', N)[0]

    # Get data
    x = np.zeros((N, rows*cols), dtype=np.uint8)  # Initialize numpy array
    y = np.zeros(N, dtype=np.uint8)  # Initialize numpy array
    for i in range(N):
        for j in range(rows*cols):
            tmp_pixel = images.read(1)  # Just a single byte
            tmp_pixel = unpack('>B', tmp_pixel)[0]
            x[i][j] = tmp_pixel
        tmp_label = labels.read(1)
        y[i] = unpack('>B', tmp_label)[0]

    images.close()
    labels.close()
    return (x, y)

Above part is fine.

train_img, train_lbl = loadmnist('data/train-images-idx3-ubyte'
                                 , 'data/train-labels-idx1-ubyte')
test_img, test_lbl = loadmnist('data/t10k-images-idx3-ubyte'
                               , 'data/t10k-labels-idx1-ubyte')

Error is like this.

FileNotFoundError                         Traceback (most recent call last)
<ipython-input-5-b23a5078b5bb> in <module>()
      1 train_img, train_lbl = loadmnist('data/train-images-idx3-ubyte'
----> 2                                  , 'data/train-labels-idx1-ubyte')
      3 test_img, test_lbl = loadmnist('data/t10k-images-idx3-ubyte'
      4                                , 'data/t10k-labels-idx1-ubyte')

<ipython-input-4-967098b85f28> in loadmnist(imagefile, labelfile)
      2 
      3     # Open the images with gzip in read binary mode
----> 4     images = open(imagefile, 'rb')
      5     labels = open(labelfile, 'rb')
      6 

FileNotFoundError: [Errno 2] No such file or directory: 'data/train-images-idx3-ubyte'

The data I downloaded was put in a folder I just made. enter image description here

Answer 1

If you want to load the dataset from some library directly rather than downloading it and then loading it, load it from Keras.

It can be done like this

from keras.datasets import mnist

(X_train, y_train), (X_test, y_test) = mnist.load_data()

If you are a beginner to Machine Learning and Python who want to know more about it, I recommend you to take a look at this excellent blog post.

Also, the extension of the file is also required when passing it to the function. ie you have to call the function like this.

train_img, train_lbl = loadmnist('mnist//train-images-idx3-ubyte.gz'
                                 , 'mnist//train-labels-idx1-ubyte.gz')
test_img, test_lbl = loadmnist('mnist//t10k-images-idx3-ubyte.gz'
                               , 'mnist//t10k-labels-idx1-ubyte.gz')

In the code you are using to load data from the local disk, it throws an error because the file is not present in the given location. Make sure that the folder mnist is present in the folder your notebook is present.

Answer 2

服务器已经宕机了一段时间，请参考这个GitHub线程中的一些解决方案，包括从Tensorflow导入或直接从其他来源导入。

Answer 3

You can load it from the sklearn datsets directly.

from sklearn import datasets
digits = datasets.load_digits()

Or you could load it using Keras.

from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()

Another option is to just download the dataset and load it in with something like pandas.

df = pd.read_csv('filename.csv')

Answer 4

I've faced this Error while I was coding on Spyder (Python 3.7) installed on Anaconda locally. I've tried many answers and at last I was only able to come across this error by specifying the target file location of the Mnist dataset after downloading it.

from scipy.io import loadmat
mnist_path = (r"C:\Users\duppa\Desktop\mnist-original.mat")
mnist_raw = loadmat(mnist_path)
mnist = {
    "data": mnist_raw["data"].T,
    "target": mnist_raw["label"][0],
    "COL_NAMES": ["label", "data"],
    "DESCR": "mldata.org dataset: mnist-original",
        }
mnist