personalitylinmult.inference.register_models

Register the trained FI models into the MLflow Model Registry.

Reads the best checkpoint each training run logged (under its model/ artifact path), wraps it as a pyfunc model, and registers it under a stable name so it can be served or containerised. Run after training; idempotent in the sense that re-running adds a new version rather than clobbering the old one.

Example

Register the three audio models (LinMulT fusion + two LinT unimodal arms):

uv run python -m personalitylinmult.inference.register_models

Attributes

logger	Module-level logger.
DEFAULT_TRACKING_URI	Where the training runs were logged.
REGISTRATIONS	LinMulT fusion (wavlm+emotion2vec) plus the two LinT

Classes

Registration

One model to register.

Functions

register_all(→ dict[str, str])	Register every configured model, returning {name: version}.
main(→ None)	CLI entry point.

Module Contents

personalitylinmult.inference.register_models.logger

Module-level logger.

personalitylinmult.inference.register_models.DEFAULT_TRACKING_URI = 'sqlite:///mlflow.db'

Where the training runs were logged.

class personalitylinmult.inference.register_models.Registration

One model to register.

Parameters:

• experiment (str) – MLflow experiment holding the trained run.

• registered_name (str) – Name to register under, e.g. fi_linmult_wavlm-emotion2vec.

• run_id (str | None) – Exact run to register. None falls back to the experiment’s most recently started run – convenient while iterating, but not a deliberate choice of “the best run”, so a promotion decision should pin this explicitly (see set_champion() for the separate, deliberate promotion step).

personalitylinmult.inference.register_models.REGISTRATIONS: list[Registration]

LinMulT fusion (wavlm+emotion2vec) plus the two LinT unimodal arms (wavlm only, emotion2vec only).

Type:

The audio models

personalitylinmult.inference.register_models.register_all(registrations: list[Registration] | None = None, tracking_uri: str = DEFAULT_TRACKING_URI) → dict[str, str]

Register every configured model, returning {name: version}.

Parameters:

• registrations (list[Registration] | None) – Models to register; the module default when None.

• tracking_uri (str) – MLflow backend store.

Returns:

Registered name to version.

Return type:

dict[str, str]

personalitylinmult.inference.register_models.main() → None

CLI entry point.

With no arguments, registers every model in REGISTRATIONS. Passing --experiment/--registered-name registers exactly that one model instead – the deliberate, ad hoc path for a run that is not (yet, or ever) part of the standing registration list. --alias additionally promotes the newly registered version, so a single command can both register and mark a version as the champion.