vak.transforms.defaults.frame_classification

Default transforms for frame classification models.

These are “item” transforms because they apply transforms to input parameters and then return them in an “item” (dictionary) that is turn returned by the __getitem__ method of a vak.FramesDataset. Having the transform return a dictionary makes it possible to avoid coupling the FramesDataset __getitem__ implementation to the transforms needed for specific neural network models, e.g., whether the returned output includes a mask to crop off padding that was added.

Functions

get_default_frame_classification_transform(...)

Get default transform for frame classification model.

Classes

EvalItemTransform(window_size[, ...])	Default transform used when evaluating frame classification models.
PredictItemTransform(window_size[, ...])	Default transform used when using trained frame classification models to make predictions.
TrainItemTransform([spect_standardizer])	Default transform used when training frame classification models