bacpipe.model_pipelines.feature_extractors.beats

Classes

BEATs(cfg)
BEATsConfig([cfg])
BeatsModel(checkpoint_path)
Model(**kwargs)
ModelBaseClass(sr, segment_length, model_name)

class bacpipe.model_pipelines.feature_extractors.beats.BeatsModel(checkpoint_path)

Bases: object

get_embeddings(spectrogram_input)

Taken from the BEATS forward call. Adapted to work based on the spectrogram input to enable visualization of spectrograms for model result interpretation.

Parameters:

spectrogram_input (torch.Tensor) – batched spectrograms from self.model.preprocess

Returns:

batched embeddings

Return type:

torch.Tensor

class bacpipe.model_pipelines.feature_extractors.beats.Model(**kwargs)

Bases: ModelBaseClass

preprocess(audio)