pumpp.task.StructureTransformer

class pumpp.task.StructureTransformer(name='structure', sr=22050, hop_length=512)[source]

Structure agreement transformer.

This transformer maps a labeled, flat structural segmentation to an n*n boolean matrix indicating whether two frames belong to a similarly labeled segment or not.

Attributes

name (str) The name of this transformer
sr (number > 0) The audio sampling rate
hop_length (int > 0) The number of samples between each annotation frame
__init__(name='structure', sr=22050, hop_length=512)[source]

Initialize a structure agreement transformer

Methods

__init__([name, sr, hop_length]) Initialize a structure agreement transformer
decode_events(encoded) Decode labeled events into (time, value) pairs
decode_intervals(encoded[, duration, multi, ...]) Decode labeled intervals into (start, end, value) triples
empty(duration)
encode_events(duration, events, values[, dtype]) Encode labeled events as a time-series matrix.
encode_intervals(duration, intervals, values) Encode labeled intervals as a time-series matrix.
inverse(agree[, duration])
merge(data) Merge an array of output dictionaries into a single dictionary with properly scoped names.
pop(field)
register(field, shape, dtype) Register a field as a tensor with specified shape and type.
scope(key) Apply the name scope to a key
transform(jam[, query]) Transform jam object to make data for this task
transform_annotation(ann, duration) Apply the structure agreement transformation.