compare_models

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the Habitat Guide and Python API guide (v2.0) for usage.

compare_models(config: Any, *, logger: Logger | None = None, output_dir: str | None = None) → WorkflowResult[Mapping[str, Any]][source]

Compare multiple trained models from a validated comparison config.

Parameters:

  • config – Validated ModelComparisonConfig or compatible mapping.

  • logger – Optional run logger (CLI attaches processing.log).

  • output_dir – Optional output directory override.

Returns:

WorkflowResult with the metrics store in data and written artefact paths in artifacts.