Impossible d'obtenir la base de données MNIST via Anaconda/jupyter
Hu les gars,
Je suis nouveau sur python/anaconda/jupyter/numPy, panda, etc. Mais à chaque fois, je reçois une erreur HTTP 500 à la fin. Est-ce vraiment un problème de serveur (comme le suggère 500) ou est-ce que je fais quelque chose de mal?
Entrée dans jupyter:
from sklearn.datasets import fetch_mldata
mnist = fetch_mldata('MNIST original')
Résultat:
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
<ipython-input-1-15dc285fb373> in <module>()
1 from sklearn.datasets import fetch_mldata
----> 2 mnist = fetch_mldata('MNIST original')
e:\ProgramData\Anaconda3\lib\site-packages\sklearn\datasets\mldata.py in fetch_mldata(dataname, target_name, data_name, transpose_data, data_home)
140 urlname = MLDATA_BASE_URL % quote(dataname)
141 try:
--> 142 mldata_url = urlopen(urlname)
143 except HTTPError as e:
144 if e.code == 404:
e:\ProgramData\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):
e:\ProgramData\Anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
530 for processor in self.process_response.get(protocol, []):
531 meth = getattr(processor, meth_name)
--> 532 response = meth(req, response)
533
534 return response
e:\ProgramData\Anaconda3\lib\urllib\request.py in http_response(self, request, response)
640 if not (200 <= code < 300):
641 response = self.parent.error(
--> 642 'http', request, response, code, msg, hdrs)
643
644 return response
e:\ProgramData\Anaconda3\lib\urllib\request.py in error(self, proto, *args)
562 http_err = 0
563 args = (dict, proto, meth_name) + args
--> 564 result = self._call_chain(*args)
565 if result:
566 return result
e:\ProgramData\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
e:\ProgramData\Anaconda3\lib\urllib\request.py in http_error_302(self, req, fp, code, msg, headers)
754 fp.close()
755
--> 756 return self.parent.open(new, timeout=req.timeout)
757
758 http_error_301 = http_error_303 = http_error_307 = http_error_302
e:\ProgramData\Anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
530 for processor in self.process_response.get(protocol, []):
531 meth = getattr(processor, meth_name)
--> 532 response = meth(req, response)
533
534 return response
e:\ProgramData\Anaconda3\lib\urllib\request.py in http_response(self, request, response)
640 if not (200 <= code < 300):
641 response = self.parent.error(
--> 642 'http', request, response, code, msg, hdrs)
643
644 return response
e:\ProgramData\Anaconda3\lib\urllib\request.py in error(self, proto, *args)
568 if http_err:
569 args = (dict, 'default', 'http_error_default') + orig_args
--> 570 return self._call_chain(*args)
571
572 # XXX probably also want an abstract factory that knows when it makes
e:\ProgramData\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
e:\ProgramData\Anaconda3\lib\urllib\request.py in http_error_default(self, req, fp, code, msg, hdrs)
648 class HTTPDefaultErrorHandler(BaseHandler):
649 def http_error_default(self, req, fp, code, msg, hdrs):
--> 650 raise HTTPError(req.full_url, code, msg, hdrs, fp)
651
652 class HTTPRedirectHandler(BaseHandler):
HTTPError: HTTP Error 500: INTERNAL SERVER ERROR
J'ai également eu la même erreur et j'ai dû désactiver le pare-feu. Sur le Macbook, sélectionnez Préférences Système> Sécurité et confidentialité> Pare-feu> Désactiver le pare-feu.
from sklearn.datasets import fetch_mldata
try:
mnist = fetch_mldata('MNIST original')
except Exception as ex:
from six.moves import urllib
from scipy.io import loadmat
import os
mnist_path = os.path.join(".", "datasets", "mnist-original.mat")
# download dataset from github.
mnist_alternative_url = "https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat"
response = urllib.request.urlopen(mnist_alternative_url)
with open(mnist_path, "wb") as f:
content = response.read()
f.write(content)
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",
}
print("Done!")
J'ai aussi la même erreur que toi. Voici quelques solutions possibles qui ne nécessitent pas ce serveur.
Si vous avez installé tensorflow, vous pouvez obtenir les données MNIST de la manière suivante:
import tensorflow.examples.tutorials.mnist.input_data as input_data
m=input_data.read_data_sets("MNIST")
Alors, par exemple, len(m.train.images) est 55000.
Si vous n'avez pas tensorflow, vous pouvez obtenir cet ensemble de données en suivant les instructions ici .
J'ai trouvé une bonne solution ici: https://github.com/Lasagne/Lasagne/blob/master/examples/mnist.py
Il télécharge le jeu de données du site Web de Yan LeCun ( http://yann.lecun.com/exdb/mnist/ ).
import os
from urllib import urlretrieve
def download(filename, source='http://yann.lecun.com/exdb/mnist/'):
print("Downloading %s" % filename)
urlretrieve(source + filename, filename)
# We then define functions for loading MNIST images and labels.
# For convenience, they also download the requested files if needed.
import gzip
def load_mnist_images(filename):
if not os.path.exists(filename):
download(filename)
# Read the inputs in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
# The inputs are vectors now, we reshape them to monochrome 2D images,
# following the shape convention: (examples, channels, rows, columns)
data = data.reshape(-1, 1, 28, 28)
# The inputs come as bytes, we convert them to float32 in range [0,1].
# (Actually to range [0, 255/256], for compatibility to the version
# provided at http://deeplearning.net/data/mnist/mnist.pkl.gz.)
return data / np.float32(256)
def load_mnist_labels(filename):
if not os.path.exists(filename):
download(filename)
# Read the labels in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=8)
# The labels are vectors of integers now, that's exactly what we want.
return data
X_train = load_mnist_images('train-images-idx3-ubyte.gz')
y_train = load_mnist_labels('train-labels-idx1-ubyte.gz')
X_test = load_mnist_images('t10k-images-idx3-ubyte.gz')
y_test = load_mnist_labels('t10k-labels-idx1-ubyte.gz')
Voici un autre emplacement pour télécharger le jeu de données MNIST (référencé depuis https://github.com/ageron/handson-ml/blob/master/03_classification.ipynb ).
from six.moves import urllib
from sklearn.datasets import fetch_mldata
try:
mnist = fetch_mldata('MNIST original')
except urllib.error.HTTPError as ex:
print("Could not download MNIST data from mldata.org, trying alternative...")
# Alternative method to load MNIST, if mldata.org is down
from scipy.io import loadmat
mnist_alternative_url = "https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat"
mnist_path = "./mnist-original.mat"
response = urllib.request.urlopen(mnist_alternative_url)
with open(mnist_path, "wb") as f:
content = response.read()
f.write(content)
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",
}
print("Success!")
J'ai trouvé cette solution sur https://github.com/ageron/handson-ml/issues/7 et celle-ci m'a été très utile. Il suffit de télécharger le fichier à partir de https://github.com/amplab/datascience-sp14/raw/master/lab7/mldata/mnist-original.mat
après cela, utilisez ce script:
from scipy.io import loadmat
mnist_path = "my/local/path/mnist-original.mat" #type the directory where you want to the file is located
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",
}
print("Success!")
ceci est pour python 3.6. *
import os
from urllib.request import urlretrieve
import numpy as np
def download(filename, source='http://yann.lecun.com/exdb/mnist/'):
print("Downloading %s" % filename)
urlretrieve(source + filename, filename)
# We then define functions for loading MNIST images and labels.
# For convenience, they also download the requested files if needed.
import gzip
def load_mnist_images(filename):
if not os.path.exists(filename):
download(filename)
# Read the inputs in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
# The inputs are vectors now, we reshape them to monochrome 2D images,
# following the shape convention: (examples, channels, rows, columns)
data = data.reshape(-1, 1, 28, 28)
# The inputs come as bytes, we convert them to float32 in range [0,1].
# (Actually to range [0, 255/256], for compatibility to the version
# provided at http://deeplearning.net/data/mnist/mnist.pkl.gz.)
return data / np.float32(256)
def load_mnist_labels(filename):
if not os.path.exists(filename):
download(filename)
# Read the labels in Yann LeCun's binary format.
with gzip.open(filename, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=8)
# The labels are vectors of integers now, that's exactly what we want.
return data
X_train = load_mnist_images('train-images-idx3-ubyte.gz')
y_train = load_mnist_labels('train-labels-idx1-ubyte.gz')
X_test = load_mnist_images('t10k-images-idx3-ubyte.gz')
y_test = load_mnist_labels('t10k-labels-idx1-ubyte.gz')
En retard pour la fête, mais j'ai eu la même erreur et ma solution simple était d'exécuter les deux commandes séparément, comme:
from sklearn import datasets
et assurez-vous de l'exécuter sur une ligne séparée dans le cahier jupyter
mnist_data = datasets.fetch_mldata('MNIST original', data_home = 'datasets/')