Skip to content

Conversation

@Jubeku
Copy link
Contributor

@Jubeku Jubeku commented Jan 6, 2026

Description

Originally we converted mse loss to mse_channel_location_weighted in LossPhysical.
As mse_channel_location_weighted calculates the non-weighted mse if no weights are given, this PR renames mse_channel_location_weighted to mse and removes the old mse function.

Issue Number

Closes #1536

Is this PR a draft? Mark it as draft.

Checklist before asking for review

  • I have performed a self-review of my code
  • My changes comply with basic sanity checks:
    • I have fixed formatting issues with ./scripts/actions.sh lint
    • I have run unit tests with ./scripts/actions.sh unit-test
    • I have documented my code and I have updated the docstrings.
    • I have added unit tests, if relevant
  • I have tried my changes with data and code:
    • I have run the integration tests with ./scripts/actions.sh integration-test
    • (bigger changes) I have run a full training and I have written in the comment the run_id(s): launch-slurm.py --time 60
    • (bigger changes and experiments) I have shared a hegdedoc in the github issue with all the configurations and runs for this experiments
  • I have informed and aligned with people impacted by my change:
    • for config changes: the MatterMost channels and/or a design doc
    • for changes of dependencies: the MatterMost software development channel

@Jubeku Jubeku self-assigned this Jan 6, 2026
@github-actions github-actions bot added the model Related to model training or definition (not generic infra) label Jan 6, 2026
@Jubeku Jubeku added bug Something isn't working and removed model Related to model training or definition (not generic infra) labels Jan 6, 2026
@github-actions github-actions bot added the model Related to model training or definition (not generic infra) label Jan 6, 2026
@Jubeku Jubeku mentioned this pull request Jan 6, 2026
4 tasks
@clessig clessig merged commit 310eb81 into develop Jan 7, 2026
6 checks passed
@clessig clessig deleted the jk/develop/unify_mse_fct branch January 7, 2026 07:33
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working model Related to model training or definition (not generic infra)

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

Implicit loss function conversion in LossPhysical

3 participants