pytorch/ignite

Enhancements to EarlyStopping handler

Fechada

#3.411 aberto em 4 de jun. de 2025

 (19 comentários) (0 reação) (0 responsável)Python (602 forks)batch import
enhancementhelp wantedmodule: handlers

Métricas do repositório

Stars
 (4.313 estrelas)
Métricas de merge de PR
 (Mesclagem média 18d 23h) (19 fundiu PRs em 30d)

Description

🚀 Feature

I would propose several enhancements to the EarlyStopping handler.

  1. Introduce a new parameter, min_delta_mode, mimicking the parameter threshold_mode of ReduceLROnPlateau. If min_delta_mode="abs" (default) everything works as of now, while if min_delta_mode="rel" the score comparison becomes score >= best_score (1 + min_delta).
  2. Introduce a new parameter mode that work's as in ReduceLROnPlateau, allowing to handle validation metrics to be minimized.

Other ideas I'd like to discuss are:

  • Natively implementing min_epochs/min_evals, preventing EarlyStopping from terminating until it has been evaluated at least X times. I know this could be addressed as in #3317 but this solution might be more compact?
  • It would be nice to have the same threshold and threshold_mode nomenclature as ReduceLROnPlateau, but I realize this would probably break older code.
  • I personally find the parameter name cumulative_delta quite counter-intuitive. When I first read about that parameter, I understood it was taking the cumulative sum of the improvements and comparing this cumulative sum to min_delta.

Guia do colaborador