MedianFilter

class deepinv.models.MedianFilter(kernel_size=9, padding=0, same=True)

Bases: Denoiser

Median filter.

It computes the median value of a sliding window over the input tensor. The window is defined by the kernel size.

Parameters:

• kernel_size (int) – size of pooling kernel, int or 2-tuple

• padding – pool padding, int or 4-tuple (l, r, t, b) as in pytorch F.pad

• same – override padding and enforce same padding, boolean

forward(x, sigma=None, **kwargs)

Applies denoiser \(\denoiser{x}{\sigma}\).

Parameters:

• x (torch.Tensor) – noisy input.

• sigma (torch.Tensor, float) – noise level.

Returns:

(torch.Tensor) Denoised tensor.

Examples using MedianFilter:

Image transforms for equivariance & augmentations

Image transforms for equivariance & augmentations

Building your custom sampling algorithm.

Building your custom sampling algorithm.