Skip to content

About use #15

@zy-charon

Description

@zy-charon

Hello, will the gradient of loss be calculated when ffl is used as loss? I try to put ffl on cuda, but it is always a scalar, and mse is a tensor with calculated gradient. Here are my changes:
image
image
The following are the values of mse and ffl, their forms are different, I don’t know if I’m wrong here.
image

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