HTTP Error 404: Not Found when downloading StanfordCars

[xmfan]

🐛 Describe the bug

When downloading StanfordCars, torchvision attemps to download a resource at https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz, but the resource is no longer available

To reproduce:

import torchvision
torchvision.datasets.StanfordCars(root='.', download=True)

Stack trace:

---------------------------------------------------------------------------
HTTPError                                 Traceback (most recent call last)
Cell In[9], line 2
      1 import torchvision
----> 2 torchvision.datasets.StanfordCars(root='.', download=True)

File ~/projects/ldm/.venv/lib/python3.10/site-packages/torchvision/datasets/stanford_cars.py:60, in StanfordCars.__init__(self, root, split, transform, target_transform, download)
     57     self._images_base_path = self._base_folder / "cars_test"
     59 if download:
---> 60     self.download()
     62 if not self._check_exists():
     63     raise RuntimeError("Dataset not found. You can use download=True to download it")

File ~/projects/ldm/.venv/lib/python3.10/site-packages/torchvision/datasets/stanford_cars.py:94, in StanfordCars.download(self)
     91 if self._check_exists():
     92     return
---> 94 download_and_extract_archive(
     95     url="https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz",
     96     download_root=str(self._base_folder),
     97     md5="c3b158d763b6e2245038c8ad08e45376",
     98 )
     99 if self._split == "train":
    100     download_and_extract_archive(
    101         url="https://ai.stanford.edu/~jkrause/car196/cars_train.tgz",
    102         download_root=str(self._base_folder),
    103         md5="065e5b463ae28d29e77c1b4b166cfe61",
    104     )

File ~/projects/ldm/.venv/lib/python3.10/site-packages/torchvision/datasets/utils.py:434, in download_and_extract_archive(url, download_root, extract_root, filename, md5, remove_finished)
    431 if not filename:
    432     filename = os.path.basename(url)
--> 434 download_url(url, download_root, filename, md5)
    436 archive = os.path.join(download_root, filename)
    437 print(f"Extracting {archive} to {extract_root}")

File ~/projects/ldm/.venv/lib/python3.10/site-packages/torchvision/datasets/utils.py:134, in download_url(url, root, filename, md5, max_redirect_hops)
    131     _download_file_from_remote_location(fpath, url)
    132 else:
    133     # expand redirect chain if needed
--> 134     url = _get_redirect_url(url, max_hops=max_redirect_hops)
    136     # check if file is located on Google Drive
    137     file_id = _get_google_drive_file_id(url)

File ~/projects/ldm/.venv/lib/python3.10/site-packages/torchvision/datasets/utils.py:82, in _get_redirect_url(url, max_hops)
     79 headers = {"Method": "HEAD", "User-Agent": USER_AGENT}
     81 for _ in range(max_hops + 1):
---> 82     with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as response:
     83         if response.url == url or response.url is None:
     84             return url

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/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 /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py:525, in OpenerDirector.open(self, fullurl, data, timeout)
    523 for processor in self.process_response.get(protocol, []):
    524     meth = getattr(processor, meth_name)
--> 525     response = meth(req, response)
    527 return response

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py:634, in HTTPErrorProcessor.http_response(self, request, response)
    631 # According to RFC 2616, "2xx" code indicates that the client's
    632 # request was successfully received, understood, and accepted.
    633 if not (200 <= code < 300):
--> 634     response = self.parent.error(
    635         'http', request, response, code, msg, hdrs)
    637 return response

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py:563, in OpenerDirector.error(self, proto, *args)
    561 if http_err:
    562     args = (dict, 'default', 'http_error_default') + orig_args
--> 563     return self._call_chain(*args)

File /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/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 /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/urllib/request.py:643, in HTTPDefaultErrorHandler.http_error_default(self, req, fp, code, msg, hdrs)
    642 def http_error_default(self, req, fp, code, msg, hdrs):
--> 643     raise HTTPError(req.full_url, code, msg, hdrs, fp)

HTTPError: HTTP Error 404: Not Found

Versions

Collecting environment information...
PyTorch version: 2.0.1
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: macOS 13.3.1 (arm64)
GCC version: Could not collect
Clang version: 14.0.3 (clang-1403.0.22.14.1)
CMake version: Could not collect
Libc version: N/A

Python version: 3.10.11 (v3.10.11:7d4cc5aa85, Apr  4 2023, 19:05:19) [Clang 13.0.0 (clang-1300.0.29.30)] (64-bit runtime)
Python platform: macOS-13.3.1-arm64-arm-64bit
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
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Apple M2 Pro

Versions of relevant libraries:
[pip3] numpy==1.25.0
[pip3] torch==2.0.1
[pip3] torchvision==0.15.2
[conda] Could not collect

[pmeier]

Duplicate of #7545.