Zurück zu den Modellen
Metric

DirectedChamfer

Directed Chamfer distance between event points.

Schnellstart

python
from sktime.performance_metrics.detection import DirectedChamfer

estimator = DirectedChamfer(normalize=False)

Parameter(1)

normalizebool, default=False
If True, the Chamfer distance is normalized by the number of detected events, i.e., divided by \(n\). If unnormalized, making too many detections will be penalized, whereas the normalized distance penalizes only the average distance to the closest true events, regardless of the number of detections.