在Python中使用mnist库
我需要使用mnist Python库下载和读取mnist数据: 在我的大学集群上,我可以毫无问题地加载数据。但是,在我的PC上,我可以获得:在Python中使用mnist库,python,http,mnist,Python,Http,Mnist,我需要使用mnist Python库下载和读取mnist数据: 在我的大学集群上,我可以毫无问题地加载数据。但是,在我的PC上,我可以获得: --------------------------------------------------------------------------- HTTPError Traceback (most recent call last) <ipython-input-24-78f59b
---------------------------------------------------------------------------
HTTPError Traceback (most recent call last)
<ipython-input-24-78f59b728818> in <module>
8 DATASET_SIZE = 512
9 DIGIT_SIZE = 28
---> 10 mnist_dataset = mnist.test_images().astype(np.float32)
11 np.random.shuffle(mnist_dataset)
12 mnist_dataset = np.reshape(mnist_dataset[:DATASET_SIZE] / 255.0, newshape=(DATASET_SIZE, DIGIT_SIZE*DIGIT_SIZE))
~\anaconda3\lib\site-packages\mnist\__init__.py in test_images()
174 columns of the image
175 """
--> 176 return download_and_parse_mnist_file('t10k-images-idx3-ubyte.gz')
177
178
~\anaconda3\lib\site-packages\mnist\__init__.py in download_and_parse_mnist_file(fname, target_dir, force)
141 Numpy array with the dimensions and the data in the IDX file
142 """
--> 143 fname = download_file(fname, target_dir=target_dir, force=force)
144 fopen = gzip.open if os.path.splitext(fname)[1] == '.gz' else open
145 with fopen(fname, 'rb') as fd:
~\anaconda3\lib\site-packages\mnist\__init__.py in download_file(fname, target_dir, force)
57 if force or not os.path.isfile(target_fname):
58 url = urljoin(datasets_url, fname)
---> 59 urlretrieve(url, target_fname)
60
61 return target_fname
~\anaconda3\lib\urllib\request.py in urlretrieve(url, filename, reporthook, data)
245 url_type, path = splittype(url)
246
--> 247 with contextlib.closing(urlopen(url, data)) as fp:
248 headers = fp.info()
249
~\anaconda3\lib\urllib\request.py in urlopen(url, data, timeout, cafile, capath, cadefault, context)
220 else:
221 opener = _opener
--> 222 return opener.open(url, data, timeout)
223
224 def install_opener(opener):
~\anaconda3\lib\urllib\request.py in open(self, fullurl, data, timeout)
529 for processor in self.process_response.get(protocol, []):
530 meth = getattr(processor, meth_name)
--> 531 response = meth(req, response)
532
533 return response
~\anaconda3\lib\urllib\request.py in http_response(self, request, response)
639 if not (200 <= code < 300):
640 response = self.parent.error(
--> 641 'http', request, response, code, msg, hdrs)
642
643 return response
~\anaconda3\lib\urllib\request.py in error(self, proto, *args)
567 if http_err:
568 args = (dict, 'default', 'http_error_default') + orig_args
--> 569 return self._call_chain(*args)
570
571 # XXX probably also want an abstract factory that knows when it makes
~\anaconda3\lib\urllib\request.py in _call_chain(self, chain, kind, meth_name, *args)
501 for handler in handlers:
502 func = getattr(handler, meth_name)
--> 503 result = func(*args)
504 if result is not None:
505 return result
~\anaconda3\lib\urllib\request.py in http_error_default(self, req, fp, code, msg, hdrs)
647 class HTTPDefaultErrorHandler(BaseHandler):
648 def http_error_default(self, req, fp, code, msg, hdrs):
--> 649 raise HTTPError(req.full_url, code, msg, hdrs, fp)
650
651 class HTTPRedirectHandler(BaseHandler):
HTTPError: HTTP Error 403: Forbidden
我已经通过inspect模块检查了功能。本地版本和群集版本调用的HTTP地址相同,即。我可以从我的网络浏览器下载它,没有问题
在Python中,我可以对此做些什么?此模块非常陈旧且已存档 我预计它可能会使用新的服务器和新的安全系统,代码可能需要一些设置,如头用户代理,以正确访问数据 使用@wwii comment的建议,我下载了源代码并添加了用户代理 现在我可以下载图片了 薄荷糖 测试代码:
import mnist
import numpy as np
print(mnist.__file__) # to see if I uses local version with changes
print(mnist.datasets_url)
print(mnist.temporary_dir()) # to see where it is downloaded
mnist_dataset = mnist.test_images().astype(np.float32)
print(mnist_dataset)
仅使用Python3.8和Python2.x进行测试将需要另一个解决方案是自行下载文件。使用我找到的函数和来自
这很好,它只是将zip文件下载到当前的工作目录。您仍然需要。使用其他答案,我已经能够构建一个允许直接使用软件包的解决方案 以下代码必须执行一次并在全局范围内工作:
from six.moves import urllib
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)
有了它,所有mnist功能都可以使用,文件将根据需要下载。在调用mnist_dataset=mnist.test_images.astypenp.float32之前,我在Jupyter笔记本的一个单元格中直接执行上面的代码。错误可能意味着下载它有问题-可能它等待数据的时间太长,或者是互联网速度太慢的问题,或者文件太大,当连接松动时,它无法重新连接并继续下载。但我认为应该有功能使用已经下载的文件。或者您应该解压缩.gz以更正文件夹并跳过下载。此模块已有4年历史,可能使用了错误的URL。或者服务器更改某些设置,出于安全原因,它会阻止来自bots/scripts/spamers/hacker的连接。使用mnist进行搜索并显示错误消息:找到了相关的SO Q&a:-接下来,如果不调整下载和解压缩数据的调用,您可能无法使用mnist包。
import mnist
import numpy as np
print(mnist.__file__) # to see if I uses local version with changes
print(mnist.datasets_url)
print(mnist.temporary_dir()) # to see where it is downloaded
mnist_dataset = mnist.test_images().astype(np.float32)
print(mnist_dataset)
import requests, gzip
urls = [(r'http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz','training_images.gz'),
(r'http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz','training_labels.gz'),
(r'http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz','test_images.gz'),
(r'http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz','test_labels.gz')]
def download_url(url, save_path, chunk_size=128):
r = requests.get(url, stream=True)
with open(save_path, 'wb') as fd:
for chunk in r.iter_content(chunk_size=chunk_size):
fd.write(chunk)
for url,path in urls:
download_url(url,path)
from six.moves import urllib
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/5.0')]
urllib.request.install_opener(opener)