Skip to content

the result is bad #39

@fuziwang

Description

@fuziwang

According to the provided parameters, the model training is performed. The effect is good in the first two epochs, but over-fitting in the latter? may I know what is the reason? How can the results in the text be reproduced?

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