grelu.transforms.label_transforms

Classes that perform transformations on labels

The input to the forward method is assumed to be a numpy array of shape (N, T, L)

Classes

LabelTransform

A class to transform sequence labels.

Module Contents

class grelu.transforms.label_transforms.LabelTransform(min_clip: int | None = None, max_clip: int | None = None, transform_func: str | Callable | None = None)

A class to transform sequence labels.

Parameters:

• min_thresh – Minimum allowed value. Elements with value less than this will be clipped to min_thresh.

• max_thresh – Maximum allowed value. Elements with value greater than this will be clipped to max_thresh

• transform_func – A function or name of a function that transforms the label values. Allowed names are “log”.

forward(label: numpy.ndarray) → numpy.ndarray

Apply the transformation.

Parameters:

label – numpy array of shape (B, T, L)

Returns:

Transformed label

__call__(label: numpy.ndarray) → numpy.ndarray