jams.eval.hierarchy

jams.eval.hierarchy(ref, est, **kwargs)[source]

Multi-level segmentation evaluation

Parameters:
ref : jams.Annotation

Reference annotation object

est : jams.Annotation

Estimated annotation object

kwargs

Additional keyword arguments

Returns:
scores : dict

Dictionary of scores, where the key is the metric name (str) and the value is the (float) score achieved.

Examples

>>> # Load in the JAMS objects
>>> ref_jam = jams.load('reference.jams')
>>> est_jam = jams.load('estimated.jams')
>>> # Select the first relevant annotations
>>> ref_ann = ref_jam.search(namespace='multi_segment')[0]
>>> est_ann = est_jam.search(namespace='multi_segment')[0]
>>> scores = jams.eval.hierarchy(ref_ann, est_ann)