Skip to content

Retrain DLC/DGP models to improve performance #2

Description

@obarnstedt

Currently, labelling performance on some videos is suboptimal, especially if parts of the face (e.g., nose) are not well illuminated. Retraining the model with additional video data may help.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

Labels

enhancementNew feature or request

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions