Skip to content

Training with Negative Samples will Harm the Performance Significantly #2

Description

@tim5go

I tried to mix some negative samples when training my classifier under your framework.
However, the validation accuracy drops from 94% to 61%.

Should I never do that?

Is it possible to modify the loss function to cope with negative samples?

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