load_degradation#

deepinv.utils.load_degradation(name, data_dir=None, index=0, download=True)[source]#

Loads a degradation tensor from DeepInverse HuggingFace repository.

Parameters:

  • name (str, pathlib.Path) – degradation name with file extension

  • data_dir (str, pathlib.Path) – dataset root directory, defaults to None

  • index (int) – degradation index, defaults to 0

  • download (bool) – whether to download, defaults to True

Returns:

(torch.Tensor) containing degradation.

Return type:

Tensor

Examples using load_degradation:#

Image deblurring with Total-Variation (TV) prior

Image deblurring with Total-Variation (TV) prior

DPIR method for PnP image deblurring.

DPIR method for PnP image deblurring.

Regularization by Denoising (RED) for Super-Resolution.

Regularization by Denoising (RED) for Super-Resolution.

Self-supervised learning with Equivariant Imaging for MRI.

Self-supervised learning with Equivariant Imaging for MRI.

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring