Skip to content

Pre-trained weight file appears to be corrupted (RuntimeError: failed finding central directory) #2

@EricShenYuQi

Description

@EricShenYuQi

Thank you for your impressive work on MSRNet. I am trying to reproduce the results using the code and pre-trained weights provided in the repository.

Description However, I encountered a RuntimeError when trying to load the pre-trained weights. It appears that the weight file is corrupted or incomplete, as PyTorch cannot recognize it as a valid zip archive.

I have tried re-downloading the file multiple times to rule out network transmission errors, but the issue persists.

Target File

Model Name: PvtV2B4_MSRNet

Corrupted File Name: PvtV2B4_MSRNet.pth

File Source: Google Drive link
Error Log:
Traceback (most recent call last):
...
File "torch/serialization.py", line 1326, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "torch/serialization.py", line 671, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
Request Could you please check the integrity of the uploaded weight files? It would be greatly appreciated if you could re-upload a valid version of the pre-trained weights (preferably to Hugging Face or Google Drive).

Thanks again for your contribution!

Best regards.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions