Skip to content

The loss cost is negative #11

@haitaoWi

Description

@haitaoWi

Hello, I would like to ask how to handle the situation where the loss cost is negative when training casdiffmvs on my own private dataset? The final depth error was very high.

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