Skip to content

The loss curve during clipcap training #85

@gWeiXP

Description

@gWeiXP

Has anyone recorded the loss curve during clipcap training? I used clipcap as a basline in my experiments and found that the loss curve was always far from ideal. Then I measured the loss curve during clipcap training and found that he was not ideal either.
M7ZC %564S2EJL5FE0J7DFS

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