Scale

class myoverse.transforms.Scale(scale_range=(0.8, 1.2), p=1.0, **kwargs)

Random amplitude scaling.

Parameters:

• scale_range (tuple[float, float]) – Range of scale factors (min, max).

• p (float) – Probability of applying scaling.

Examples

>>> x = torch.randn(64, 2048, device='cuda', names=('channel', 'time'))
>>> scale = Scale(scale_range=(0.8, 1.2))
>>> y = scale(x)

Methods

__init__([scale_range, p])
_apply(x)	Apply the transform.