GaussianNoise

class myoverse.transforms.GaussianNoise(std=0.1, p=1.0, **kwargs)

Add Gaussian noise to the signal.

Parameters:

• std (float) – Standard deviation of the noise.

• p (float) – Probability of applying the augmentation.

Examples

>>> x = torch.randn(64, 2048, device='cuda', names=('channel', 'time'))
>>> noise = GaussianNoise(std=0.1)
>>> y = noise(x)

Methods

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