Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

prediction_score: adapt it so it's like a percentage of the best prediction. So interpretation is more clear #162

Closed
dieuska opened this issue Jan 23, 2025 · 2 comments
Assignees
Labels
enhancement New feature or request
Milestone

Comments

@dieuska
Copy link
Collaborator

dieuska commented Jan 23, 2025

When predicting geometries, a prediction_score is determined. This is an absolute value.
It could be better that we can adapt the calculation of this score so it is more relative score so comparisons can be made more clearly

@dieuska dieuska self-assigned this Jan 23, 2025
@dieuska dieuska added the enhancement New feature or request label Jan 23, 2025
@dieuska dieuska added this to the 0.8.0 milestone Jan 23, 2025
@dieuska
Copy link
Collaborator Author

dieuska commented Jan 27, 2025

or maybe this stays better a absolute value since this is a measurement of how long the geometry stays stable while augmenting the relevant distance. A higher score stays longer stable. to clarify/define:
Prediction_score is a measurement for the stability of the predicted geometry (in cm if we multiply it by the prediction_step?)

@dieuska
Copy link
Collaborator Author

dieuska commented Feb 5, 2025

we close this, as the score is adapted to cm (absolute value)

dieuska added a commit that referenced this issue Feb 5, 2025
@dieuska dieuska closed this as completed Feb 7, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant