The URL for the SUN397 dataset isn't working

[jshn9515]

🐛 Describe the bug

The URL for the SUN397 dataset seems to be dead.

import torchvision.datasets as datasets

dataset = datasets.SUN397('datasets', download=True)

The output is:

Traceback (most recent call last):
  File "d:\Project\Python Project\cc.py", line 3, in <module>
    dataset = datasets.SUN397('datasets', download=True)
  File "D:\Project\Python Project\venv\Lib\site-packages\torchvision\datasets\sun397.py", line 44, in __init__
    self._download()
    ~~~~~~~~~~~~~~^^
  File "D:\Project\Python Project\venv\Lib\site-packages\torchvision\datasets\sun397.py", line 81, in _download
    download_and_extract_archive(self._DATASET_URL, download_root=self.root, md5=self._DATASET_MD5)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Project\Python Project\venv\Lib\site-packages\torchvision\datasets\utils.py", line 388, in download_and_extract_archive
    download_url(url, download_root, filename, md5)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\Project\Python Project\venv\Lib\site-packages\torchvision\datasets\utils.py", line 118, in download_url
    url = _get_redirect_url(url, max_hops=max_redirect_hops)
  File "D:\Project\Python Project\venv\Lib\site-packages\torchvision\datasets\utils.py", line 63, in _get_redirect_url
    with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as response:
         ~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 187, in urlopen
    return opener.open(url, data, timeout)
           ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 493, in open
    response = meth(req, response)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 602, in http_response
    response = self.parent.error(
        'http', request, response, code, msg, hdrs)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 525, in error
    result = self._call_chain(*args)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 464, in _call_chain
    result = func(*args)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 718, in http_error_302
    return self.parent.open(new, timeout=req.timeout)
           ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 493, in open
    response = meth(req, response)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 602, in http_response
    response = self.parent.error(
        'http', request, response, code, msg, hdrs)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 525, in error
    result = self._call_chain(*args)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 464, in _call_chain
    result = func(*args)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 718, in http_error_302
    return self.parent.open(new, timeout=req.timeout)
           ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 493, in open
    response = meth(req, response)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 602, in http_response
    response = self.parent.error(
        'http', request, response, code, msg, hdrs)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 531, in error
    return self._call_chain(*args)
           ~~~~~~~~~~~~~~~~^^^^^^^
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 464, in _call_chain
    result = func(*args)
  File "C:\Users\jshn9\AppData\Local\Programs\Python\Python314\Lib\urllib\request.py", line 611, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found

Versions

PyTorch version: 2.9.1+xpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 11 (10.0.26200 64 bit)
GCC version: (x86_64-posix-seh-rev0, Built by MinGW-Builds project) 15.2.0
Clang version: Could not collect
CMake version: version 4.2.0
Libc version: N/A

Python version: 3.14.2 (tags/v3.14.2:df79316, Dec 5 2025, 17:18:21) [MSC v.1944 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-11-10.0.26200-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: True
XPU used to build PyTorch: 20250200
Intel GPU driver version:

• 32.0.101.7026 (20250819000000.***+)
  Intel GPU models onboard:
• Intel(R) Arc(TM) 140T GPU (16GB)
  Intel GPU models detected:
• [0] _XpuDeviceProperties(name='Intel(R) Arc(TM) 140T GPU (16GB)', platform_name='Intel(R) oneAPI Unified Runtime over Level-Zero', type='gpu', device_id=0x7D51, uuid=8680517d-0300-0000-0002-000000000000, driver_version='1.6.34541', total_memory=16797MB, max_compute_units=128, gpu_eu_count=128, gpu_subslice_count=16, max_work_group_size=1024, max_num_sub_groups=128, sub_group_sizes=[8 16 32], has_fp16=1, has_fp64=1, has_atomic64=1)
  HIP runtime version: N/A
  MIOpen runtime version: N/A
  Is XNNPACK available: True
  Caching allocator config: N/A

CPU:
Name: Intel(R) Core(TM) Ultra 7 255H
Manufacturer: GenuineIntel
Family: 774
Architecture: 9
ProcessorType: 3
DeviceID: CPU0
CurrentClockSpeed: 2000
MaxClockSpeed: 2000
L2CacheSize: 28672
L2CacheSpeed: None
Revision: None

[justnotmegryan-cld]

Used this synthetic data generator to fill the gap - https://rendered.ai/

[viniciusarruda]

Any update on this? It is a problem of the URL: http://vision.princeton.edu/projects/2010/SUN/SUN397.tar.gz that is not working anymore.