Skip to content

Loss becoming infinite #11

@Mohdwajtech

Description

@Mohdwajtech

Hi,
I have tried training on new set of 80 images following the steps but somewhere in between the training I get this error which I have just attached within this issue as an image. I tried it multiple times but looks like it gets stuck at any random iteration. The only solution is if I keep the dataset small i.e. 10 - 15 pages I am sure not to get this error. Is there a possible workaround to this issue
training_error
?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions