LaplaceNoise#

class deepinv.physics.LaplaceNoise(b=0.1, rng=None)[source]#

Bases: NoiseModel

Laplace noise \(y = z + \epsilon\) where \(\epsilon\sim\text{Laplace}(0,b)\). In the laplace distribution, b is the scale parameter and the variance is given by \(\sigma^2=2b^2\).

Parameters:

  • b (Union[float, torch.Generator]) – scale of the noise.

  • rng (torch.Generator, None) – (optional) a pseudorandom random number generator for the parameter generation.

:Examples:

Adding Laplace noise to a physics operator by setting the noise_model attribute of the physics operator:

>>> from deepinv.physics import Denoising, LaplaceNoise
>>> import torch
>>> physics = Denoising()
>>> physics.noise_model = LaplaceNoise()
>>> x = torch.rand(1, 1, 2, 2)
>>> y = physics(x)
forward(x, b=None, seed=None, **kwargs)[source]#

Adds the noise to measurements x

Parameters:

  • x (torch.Tensor) – measurements

  • b (float, torch.Tensor) – scale of the noise. If not None, it will overwrite the current noise level.

  • seed (int) – the seed for the random number generator, if rng is provided.

Returns:

noisy measurements