Skip to content

semipy.methods.utils.EarlyStopping

Warning

This section is in construction.

    class semipy.methods.utils.EarlyStopping(monitor: str = 'VALIDATION/Loss',
                                             patience: int = 3,
                                             min_delta: float = 0.0) -> None

This class is useful to add Early Stopping without using PyTorch Lightning.

Parameters

  • monitor (str) - The metric to monitor. Default: 'VALIDATION/Loss'
  • patience (int) - Number of events to wait if no improvement and then stop the training. Default: 3
  • min_delta (float) - A minimum increase in the score to qualify as an improvement, i.e. an increase of less than or equal to min_delta, will count as no improvement. Default: 0.0