[Bug]: How to Solve [RuntimeError: Trying to resize storage that is not resizable]

[Osasbro]

Describe the bug

RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\torch\utils\data_utils\worker.py", line 308, in worker_loop
data = fetcher.fetch(index)
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\torch\utils\data_utils\fetch.py", line 54, in fetch
return self.collate_fn(data)
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\anomalib\data\base\datamodule.py", line 46, in collate_fn
out_dict.update({key: default_collate([item[key] for item in batch]) for key in elem})
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\anomalib\data\base\datamodule.py", line 46, in
out_dict.update({key: default_collate([item[key] for item in batch]) for key in elem})
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\torch\utils\data_utils\collate.py", line 265, in default_collate
return collate(batch, collate_fn_map=default_collate_fn_map)
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\torch\utils\data_utils\collate.py", line 123, in collate
return collate_fn_map[collate_type](batch, collate_fn_map=collate_fn_map)
File "C:\Users\bingq\anaconda3\envs\anomalib_env\lib\site-packages\torch\utils\data_utils\collate.py", line 161, in collate_tensor_fn
out = elem.new(storage).resize(len(batch), *list(elem.size()))
RuntimeError: Trying to resize storage that is not resizable

Dataset

Folder

Model

PADiM

Steps to reproduce the behavior

OS information

OS information:

• OS: Win11
• Python version: 3.10.0
• Anomalib version: 1.0.0
• CPU
• I'm using a custom dataset

Expected behavior

Screenshots

No response

Pip/GitHub

pip

What version/branch did you use?

Configuration YAML

-

Logs

-

Code of Conduct

• I agree to follow this project's Code of Conduct

[snoopybingo]

the same question too!

[samet-akcay]

I cannot reproduce this unfortunately. When I try the same configuration as yours, mine works

[Osasbro]

I understand that the 'hazelnut' dataset works fine, but when I try to use my own dataset, it doesn't work. I just want to know what is different about my data that is causing this issue.

[samet-akcay]

I'll try to use MVTec images with Folder dataset to see if it works.

[samet-akcay]

I also tried MVTec bottle category using the Folder datamodule and managed to train a model.

Not sure about what sort of images you have in your dataset

[samet-akcay]

I'm converting this to a Q&A in discussion as it does not seem to be an issue. Feel free to convert it back to an issue if there is more evidence showing that this is a bug