autointent.advisor.recommend#

autointent.advisor.recommend(*, stats=None, presets=None, budget_vram_gb=None, budget_time_h=None)#

Walk bundled presets and return the best feasible fit plus all per-preset reports.

Parameters:

  • stats (autointent.advisor._report.DatasetStats | None) – Dataset stats to score against. Defaults to a placeholder if None.

  • presets (collections.abc.Iterable[str] | None) – Override of the preset list (defaults to PRESET_COST_ORDER).

  • budget_vram_gb (float | None) – Optional VRAM-budget override for the hardware probe.

  • budget_time_h (float | None) – Optional wall-time ceiling in hours; presets exceeding it get an extra Severity.OVER finding so they drop out of the feasible ranking.

Returns:

RecommendationResult with the chosen preset name and full results list.

Return type:

autointent.advisor._report.RecommendationResult

Note

Among feasible presets we pick the heaviest one that still fits the hardware budget — “use what you have” semantics. This is a cost ranking, not a quality ranking: a heavier preset is not strictly better and may overfit on small datasets where a classic-* preset would win on accuracy. Override presets= if you want a different ranking.

On this page