vak.transforms.defaults.frame_classification.EvalItemTransform

class vak.transforms.defaults.frame_classification.EvalItemTransform(window_size, spect_standardizer=None, padval=0.0, return_padding_mask=True, channel_dim=1)

Bases: object

Default transform used when evaluating frame classification models.

Returned item includes “source” spectrogram reshaped into a stack of windows, with padded added to make reshaping possible, and annotation also padded and reshaped. If return_padding_mask is True, item includes ‘padding_mask’ that can be used to crop off any predictions made on the padding.

__init__(window_size, spect_standardizer=None, padval=0.0, return_padding_mask=True, channel_dim=1)

Methods

__init__(window_size[, spect_standardizer, ...])