input_data.read_data_sets("MNIST_data/", one_hot=True)异常

tensorflow下载mnist数据到当前路径下的MNIST_data目录

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

网络异常，报错如下

WARNING:tensorflow:From /home/leon.lai/miniconda3/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py:252: _internal_retry..wrap..wrapped_fn (from tensorflow.contrib.learn.python.learn.datasets.base) is deprecated and will be removed in a future version.
Instructions for updating:
Please use urllib or similar directly.
---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
~/miniconda3/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1317                 h.request(req.get_method(), req.selector, req.data, headers,
-> 1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error

~/miniconda3/lib/python3.6/http/client.py in request(self, method, url, body, headers, encode_chunked)
   1238         """Send a complete request to the server."""
-> 1239         self._send_request(method, url, body, headers, encode_chunked)
   1240 

~/miniconda3/lib/python3.6/http/client.py in _send_request(self, method, url, body, headers, encode_chunked)
   1284             body = _encode(body, 'body')
-> 1285         self.endheaders(body, encode_chunked=encode_chunked)
   1286 

~/miniconda3/lib/python3.6/http/client.py in endheaders(self, message_body, encode_chunked)
   1233             raise CannotSendHeader()
-> 1234         self._send_output(message_body, encode_chunked=encode_chunked)
   1235 

~/miniconda3/lib/python3.6/http/client.py in _send_output(self, message_body, encode_chunked)
   1025         del self._buffer[:]
-> 1026         self.send(msg)
   1027 

~/miniconda3/lib/python3.6/http/client.py in send(self, data)
    963             if self.auto_open:
--> 964                 self.connect()
    965             else:

~/miniconda3/lib/python3.6/http/client.py in connect(self)
   1391 
-> 1392             super().connect()
   1393 

~/miniconda3/lib/python3.6/http/client.py in connect(self)
    935         self.sock = self._create_connection(
--> 936             (self.host,self.port), self.timeout, self.source_address)
    937         self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)

~/miniconda3/lib/python3.6/socket.py in create_connection(address, timeout, source_address)
    721     if err is not None:
--> 722         raise err
    723     else:

~/miniconda3/lib/python3.6/socket.py in create_connection(address, timeout, source_address)
    712                 sock.bind(source_address)
--> 713             sock.connect(sa)
    714             return sock

OSError: [Errno 101] Network is unreachable

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
 in ()
      1 from tensorflow.examples.tutorials.mnist import input_data
----> 2 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

~/miniconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
    304               'in a future version' if date is None else ('after %s' % date),
    305               instructions)
--> 306       return func(*args, **kwargs)
    307     return tf_decorator.make_decorator(
    308         func, new_func, 'deprecated',

~/miniconda3/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py in read_data_sets(train_dir, fake_data, one_hot, dtype, reshape, validation_size, seed, source_url)
    259 
    260   local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
--> 261                                    source_url + TRAIN_IMAGES)
    262   with gfile.Open(local_file, 'rb') as f:
    263     train_images = extract_images(f)

~/miniconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
    304               'in a future version' if date is None else ('after %s' % date),
    305               instructions)
--> 306       return func(*args, **kwargs)
    307     return tf_decorator.make_decorator(
    308         func, new_func, 'deprecated',

~/miniconda3/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py in maybe_download(filename, work_directory, source_url)
    250   filepath = os.path.join(work_directory, filename)
    251   if not gfile.Exists(filepath):
--> 252     temp_file_name, _ = urlretrieve_with_retry(source_url)
    253     gfile.Copy(temp_file_name, filepath)
    254     with gfile.GFile(filepath) as f:

~/miniconda3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
    304               'in a future version' if date is None else ('after %s' % date),
    305               instructions)
--> 306       return func(*args, **kwargs)
    307     return tf_decorator.make_decorator(
    308         func, new_func, 'deprecated',

~/miniconda3/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py in wrapped_fn(*args, **kwargs)
    203       for delay in delays():
    204         try:
--> 205           return fn(*args, **kwargs)
    206         except Exception as e:  # pylint: disable=broad-except
    207           if is_retriable is None:

~/miniconda3/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/base.py in urlretrieve_with_retry(url, filename)
    231 @_internal_retry(initial_delay=1.0, max_delay=16.0, is_retriable=_is_retriable)
    232 def urlretrieve_with_retry(url, filename=None):
--> 233   return urllib.request.urlretrieve(url, filename)
    234 
    235 

~/miniconda3/lib/python3.6/urllib/request.py in urlretrieve(url, filename, reporthook, data)
    246     url_type, path = splittype(url)
    247 
--> 248     with contextlib.closing(urlopen(url, data)) as fp:
    249         headers = fp.info()
    250 

~/miniconda3/lib/python3.6/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):

~/miniconda3/lib/python3.6/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

~/miniconda3/lib/python3.6/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

~/miniconda3/lib/python3.6/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

~/miniconda3/lib/python3.6/urllib/request.py in https_open(self, req)
   1359         def https_open(self, req):
   1360             return self.do_open(http.client.HTTPSConnection, req,
-> 1361                 context=self._context, check_hostname=self._check_hostname)
   1362 
   1363         https_request = AbstractHTTPHandler.do_request_

~/miniconda3/lib/python3.6/urllib/request.py in do_open(self, http_class, req, **http_conn_args)
   1318                           encode_chunked=req.has_header('Transfer-encoding'))
   1319             except OSError as err: # timeout error
-> 1320                 raise URLError(err)
   1321             r = h.getresponse()
   1322         except:

URLError: 

 原因：input_data.read_data_sets访问https://storage.googleapis.com/cvdf-datasets/mnist/被限制，需要修改read_data_sets函数，将source_url设置成http://yann.lecun.com/exdb/mnist/，修改后代码如下

@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
            ' from tensorflow/models.')
def read_data_sets(train_dir,
                   fake_data=False,
                   one_hot=False,
                   dtype=dtypes.float32,
                   reshape=True,
                                                                                                                                                                                                                          236,20        73%
                   dtype=dtypes.float32,
                   reshape=True,
                   validation_size=5000,
                   seed=None,
                   source_url=DEFAULT_SOURCE_URL):
  if fake_data:

    def fake():
      return DataSet(
          [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)

    train = fake()
    validation = fake()
    test = fake()
    return base.Datasets(train=train, validation=validation, test=test)

  if not source_url:  # empty string check
    source_url = DEFAULT_SOURCE_URL

  print(source_url)
  # 修改source_url
  source_url = 'http://yann.lecun.com/exdb/mnist/'
  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
  TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
  TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
  TEST_LABELS = 't10k-labels-idx1-ubyte.gz'

  local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
                                   source_url + TRAIN_IMAGES)
  with gfile.Open(local_file, 'rb') as f:
    train_images = extract_images(f)

  local_file = base.maybe_download(TRAIN_LABELS, train_dir,
                                   source_url + TRAIN_LABELS)
  with gfile.Open(local_file, 'rb') as f:
    train_labels = extract_labels(f, one_hot=one_hot)

  local_file = base.maybe_download(TEST_IMAGES, train_dir,
                                   source_url + TEST_IMAGES)
  with gfile.Open(local_file, 'rb') as f:
    test_images = extract_images(f)

  local_file = base.maybe_download(TEST_LABELS, train_dir,
                                   source_url + TEST_LABELS)
  with gfile.Open(local_file, 'rb') as f:
    test_labels = extract_labels(f, one_hot=one_hot)

  if not 0 <= validation_size <= len(train_images):
    raise ValueError('Validation size should be between 0 and {}. Received: {}.'
                     .format(len(train_images), validation_size))

  validation_images = train_images[:validation_size]
  validation_labels = train_labels[:validation_size]
  train_images = train_images[validation_size:]
  train_labels = train_labels[validation_size:]

  options = dict(dtype=dtype, reshape=reshape, seed=seed)
                                                                                                                                                                                                                          235,20        95%

  options = dict(dtype=dtype, reshape=reshape, seed=seed)

  train = DataSet(train_images, train_labels, **options)
  validation = DataSet(validation_images, validation_labels, **options)
  test = DataSet(test_images, test_labels, **options)

  return base.Datasets(train=train, validation=validation, test=test)

重新运行，正常！

查看MNIST_data下的新下载文件

$ ll MNIST_data
total 11336
-rw-r--r-- 1 leon.lai users 1648877 Jan 14 14:33 t10k-images-idx3-ubyte.gz
-rw-r--r-- 1 leon.lai users    4542 Jan 14 14:33 t10k-labels-idx1-ubyte.gz
-rw-r--r-- 1 leon.lai users 9912422 Jan 14 14:33 train-images-idx3-ubyte.gz
-rw-r--r-- 1 leon.lai users   28881 Jan 14 14:33 train-labels-idx1-ubyte.gz