voc segmentation dataset source is unavailable

🐛 Describe the bug

Both downloads VOC Segmentation dataset using torchvision.dataset.vocsegmentation and http://host.robots.ox.ac.uk/pascal/VOC/, are unavailable (currently 14/11/2025)

import torchvision

trainset = torchvision.datasets.VOCSegmentation(root='../../data', year='2012', image_set='train', download=True)

---------------------------------------------------------------------------
TimeoutError                              Traceback (most recent call last)
File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:1348, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1347 try:
-> 1348     h.request(req.get_method(), req.selector, req.data, headers,
   1349               encode_chunked=req.has_header('Transfer-encoding'))
   1350 except OSError as err: # timeout error

File d:\Develop\miniconda\envs\torch\lib\http\client.py:1283, in HTTPConnection.request(self, method, url, body, headers, encode_chunked)
   1282 """Send a complete request to the server."""
-> 1283 self._send_request(method, url, body, headers, encode_chunked)

File d:\Develop\miniconda\envs\torch\lib\http\client.py:1329, in HTTPConnection._send_request(self, method, url, body, headers, encode_chunked)
   1328     body = _encode(body, 'body')
-> 1329 self.endheaders(body, encode_chunked=encode_chunked)

File d:\Develop\miniconda\envs\torch\lib\http\client.py:1278, in HTTPConnection.endheaders(self, message_body, encode_chunked)
   1277     raise CannotSendHeader()
-> 1278 self._send_output(message_body, encode_chunked=encode_chunked)

File d:\Develop\miniconda\envs\torch\lib\http\client.py:1038, in HTTPConnection._send_output(self, message_body, encode_chunked)
   1037 del self._buffer[:]
-> 1038 self.send(msg)
   1040 if message_body is not None:
   1041 
   1042     # create a consistent interface to message_body

File d:\Develop\miniconda\envs\torch\lib\http\client.py:976, in HTTPConnection.send(self, data)
    975 if self.auto_open:
--> 976     self.connect()
    977 else:

File d:\Develop\miniconda\envs\torch\lib\http\client.py:942, in HTTPConnection.connect(self)
    941 sys.audit("http.client.connect", self, self.host, self.port)
--> 942 self.sock = self._create_connection(
    943     (self.host,self.port), self.timeout, self.source_address)
    944 # Might fail in OSs that don't implement TCP_NODELAY

File d:\Develop\miniconda\envs\torch\lib\socket.py:857, in create_connection(address, timeout, source_address)
    856 try:
--> 857     raise err
    858 finally:
    859     # Break explicitly a reference cycle

File d:\Develop\miniconda\envs\torch\lib\socket.py:845, in create_connection(address, timeout, source_address)
    844     sock.bind(source_address)
--> 845 sock.connect(sa)
    846 # Break explicitly a reference cycle

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

During handling of the above exception, another exception occurred:

URLError                                  Traceback (most recent call last)
Cell In[4], line 4
      1 import torch
      2 import torchvision
----> 4 trainset = torchvision.datasets.VOCSegmentation(root='../../data', year='2011', image_set='train', download=True)

File d:\Develop\miniconda\envs\torch\lib\site-packages\torchvision\datasets\voc.py:98, in _VOCBase.__init__(self, root, year, image_set, download, transform, target_transform, transforms)
     95 voc_root = os.path.join(self.root, base_dir)
     97 if download:
---> 98     download_and_extract_archive(self.url, self.root, filename=self.filename, md5=self.md5)
    100 if not os.path.isdir(voc_root):
    101     raise RuntimeError("Dataset not found or corrupted. You can use download=True to download it")

File d:\Develop\miniconda\envs\torch\lib\site-packages\torchvision\datasets\utils.py:395, in download_and_extract_archive(url, download_root, extract_root, filename, md5, remove_finished)
    392 if not filename:
    393     filename = os.path.basename(url)
--> 395 download_url(url, download_root, filename, md5)
    397 archive = os.path.join(download_root, filename)
    398 print(f"Extracting {archive} to {extract_root}")

File d:\Develop\miniconda\envs\torch\lib\site-packages\torchvision\datasets\utils.py:122, in download_url(url, root, filename, md5, max_redirect_hops)
    119     _download_file_from_remote_location(fpath, url)
    120 else:
    121     # expand redirect chain if needed
--> 122     url = _get_redirect_url(url, max_hops=max_redirect_hops)
    124     # check if file is located on Google Drive
    125     file_id = _get_google_drive_file_id(url)

File d:\Develop\miniconda\envs\torch\lib\site-packages\torchvision\datasets\utils.py:66, in _get_redirect_url(url, max_hops)
     63 headers = {"Method": "HEAD", "User-Agent": USER_AGENT}
     65 for _ in range(max_hops + 1):
---> 66     with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as response:
     67         if response.url == url or response.url is None:
     68             return url

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:216, in urlopen(url, data, timeout, cafile, capath, cadefault, context)
    214 else:
    215     opener = _opener
--> 216 return opener.open(url, data, timeout)

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:519, in OpenerDirector.open(self, fullurl, data, timeout)
    516     req = meth(req)
    518 sys.audit('urllib.Request', req.full_url, req.data, req.headers, req.get_method())
--> 519 response = self._open(req, data)
    521 # post-process response
    522 meth_name = protocol+"_response"

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:536, in OpenerDirector._open(self, req, data)
    533     return result
    535 protocol = req.type
--> 536 result = self._call_chain(self.handle_open, protocol, protocol +
    537                           '_open', req)
    538 if result:
    539     return result

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:496, in OpenerDirector._call_chain(self, chain, kind, meth_name, *args)
    494 for handler in handlers:
    495     func = getattr(handler, meth_name)
--> 496     result = func(*args)
    497     if result is not None:
    498         return result

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:1377, in HTTPHandler.http_open(self, req)
   1376 def http_open(self, req):
-> 1377     return self.do_open(http.client.HTTPConnection, req)

File d:\Develop\miniconda\envs\torch\lib\urllib\request.py:1351, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1348         h.request(req.get_method(), req.selector, req.data, headers,
   1349                   encode_chunked=req.has_header('Transfer-encoding'))
   1350     except OSError as err: # timeout error
-> 1351         raise URLError(err)
   1352     r = h.getresponse()
   1353 except:

URLError: <urlopen error [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>

Versions

Collecting environment information...
PyTorch version: 2.5.1
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 11 Pro (10.0.26200 64-bit)
GCC version: Could not collect
Clang version: Could not collect
CMake version: Could not collect
Libc version: N/A

Python version: 3.10.18 | packaged by Anaconda, Inc. | (main, Jun 5 2025, 13:08:55) [MSC v.1929 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.26200-SP0
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Name: AMD Ryzen 7 9700X 8-Core Processor
Manufacturer: AuthenticAMD
Family: 107
Architecture: 9
ProcessorType: 3
DeviceID: CPU0
CurrentClockSpeed: 3800
MaxClockSpeed: 3800
L2CacheSize: 8192
L2CacheSpeed: None
Revision: 17408

Versions of relevant libraries:
[pip3] mkl_fft==1.3.11
[pip3] mkl_random==1.2.8
[pip3] mkl-service==2.4.0
[pip3] numpy==1.23.5
[pip3] torch==2.5.1
[pip3] torchaudio==2.5.1
[pip3] torchvision==0.20.1
[conda] blas 1.0 mkl
[conda] cpuonly 2.0 0 pytorch
[conda] intel-openmp 2023.1.0 h59b6b97_46320
[conda] mkl 2023.1.0 h6b88ed4_46358
[conda] mkl-service 2.4.0 py310h827c3e9_2
[conda] mkl_fft 1.3.11 py310h827c3e9_0
[conda] mkl_random 1.2.8 py310hc64d2fc_0
[conda] numpy 1.23.5 pypi_0 pypi
[conda] pytorch 2.5.1 py3.10_cpu_0 pytorch
[conda] pytorch-mutex 1.0 cpu pytorch
[conda] tbb 2021.8.0 h59b6b97_0
[conda] torchaudio 2.5.1 py310_cpu pytorch
[conda] torchvision 0.20.1 py310_cpu pytorch

Start with torchvision/datasets/voc.py and the download path shown in the traceback, then verify the VOC Segmentation source URL and redirect behavior. Reproduce the failure with VOCSegmentation using download=True on the reported environment; done means the dataset can be downloaded successfully from a maintained source and the existing dataset tests cover the working path.