pyFDN.MatchMelSpectrogram#

class pyFDN.MatchMelSpectrogram(target, *, nfft=(256, 512, 1024), device=None, **kwargs)[source]#

Mel-scaled multi-resolution STFT distance (FLAMO’s mel_mss_loss).

__init__(target, *, nfft=(256, 512, 1024), device=None, **kwargs)#

Methods

__init__(target, *[, nfft, device])

check(model)

Preflight against the model it will train, before the first step.

terms()

Flatten into (weight, loss) leaves.

Attributes

name

Short label, used as the key in pyFDN.TrainLog.loss_log.