Skip to content

Explore how data augmentation affects training #587

@adamltyson

Description

@adamltyson

#581 corrected the likelihood of data augmentation being performed, which means that most training was carried out with the "wrong" likelihood. We should explore how data augmentation affects training, and what a sensible default likelihood is.

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions