EvaluationTrainingCallback
- class EvaluationTrainingCallback(*, evaluation_triples: Tensor, frequency: int = 1, evaluator: str | Evaluator | type[Evaluator] | None = None, evaluator_kwargs: Mapping[str, Any] | None = None, prefix: str | None = None, **kwargs)[source]
Bases:
TrainingCallback
A callback for regular evaluation.
Example: evaluate training performance
from pykeen.datasets import get_dataset from pykeen.pipeline import pipeline dataset = get_dataset(dataset="nations") result = pipeline( dataset=dataset, model="mure", training_loop_kwargs=dict( result_tracker="console", ), training_kwargs=dict( num_epochs=100, callbacks="evaluation", callback_kwargs=dict( evaluation_triples=dataset.training.mapped_triples, prefix="training", ), ), )
Initialize the callback.
- Parameters:
evaluation_triples (MappedTriples) – the triples on which to evaluate
frequency (int) – the evaluation frequency in epochs
evaluator (HintOrType[Evaluator]) – the evaluator to use for evaluation, cf. evaluator_resolver
evaluator_kwargs (OptionalKwargs) – additional keyword-based parameters for the evaluator
prefix (str | None) – the prefix to use for logging the metrics
kwargs – additional keyword-based parameters passed to evaluate
Methods Summary
post_epoch
(epoch, epoch_loss, **kwargs)Call after epoch.
Methods Documentation