Skip to content

Issues with Training #6

@arnavm30

Description

@arnavm30

Hi,

I'm trying to reproduce the results of the paper on the MalNetTiny dataset, but the model does not seem to be training properly, with the loss and accuracy not improving, even after modifying some hyperparameters. I think there could potentially be an issue in the training pipeline as I'm getting the following warning:

torchmetrics/utilities/prints.py:36: UserWarning: No positive samples in targets, true positive value should be meaningless. Returning zero tensor in true positive score

Could an author confirm that this public code should work?

Thanks!

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