EvaluationTrainingCallback¶
- class EvaluationTrainingCallback(*, evaluation_triples, frequency=1, evaluator=None, evaluator_kwargs=None, prefix=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 (
LongTensor
) – the triples on which to evaluatefrequency (
int
) – the evaluation frequency in epochsevaluator (
Union
[str
,Evaluator
,Type
[Evaluator
],None
]) – the evaluator to use for evaluation, cf. evaluator_resolverevaluator_kwargs (
Optional
[Mapping
[str
,Any
]]) – additional keyword-based parameters for the evaluatorprefix (
Optional
[str
]) – the prefix to use for logging the metricskwargs – additional keyword-based parameters passed to evaluate
Methods Summary
post_epoch
(epoch, epoch_loss, **kwargs)Call after epoch.
Methods Documentation