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)[source]#

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”.

min_clip[source]#
max_clip[source]#
transform_func[source]#
forward(label: numpy.ndarray) → numpy.ndarray[source]#

Apply the transformation.

Parameters:

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

Returns:

Transformed label

__call__(label: numpy.ndarray) → numpy.ndarray[source]#