DnCNN

class deepinv.models.DnCNN(in_channels=3, out_channels=3, depth=20, bias=True, nf=64, pretrained='download', device='cpu')[source]

Bases: Module

DnCNN convolutional denoiser.

The architecture was introduced in https://arxiv.org/abs/1608.03981 and is composed of a series of convolutional layers with ReLU activation functions. The number of layers can be specified by the user. Unlike the original paper, this implementation does not include batch normalization layers.

The network can be initialized with pretrained weights, which can be downloaded from an online repository. The pretrained weights are trained with the default parameters of the network, i.e. 20 layers, 64 channels and biases.

Parameters:
  • in_channels (int) – input image channels

  • out_channels (int) – output image channels

  • depth (int) – number of convolutional layers

  • bias (bool) – use bias in the convolutional layers

  • nf (int) – number of channels per convolutional layer

  • pretrained (str, None) – use a pretrained network. If pretrained=None, the weights will be initialized at random using Pytorch’s default initialization. If pretrained='download', the weights will be downloaded from an online repository (only available for architecture with depth 20, 64 channels and biases). It is possible to download weights trained via the regularization method in https://epubs.siam.org/doi/abs/10.1137/20M1387961 using pretrained='download_lipschitz'. Finally, pretrained can also be set as a path to the user’s own pretrained weights. See pretrained-weights for more details.

  • train (bool) – training or testing mode

  • device (str) – gpu or cpu

forward(x, sigma=None)[source]

Run the denoiser on noisy image. The noise level is not used in this denoiser.

Parameters:

Examples using DnCNN:

Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.

Plug-and-Play algorithm with Mirror Descent for Poisson noise inverse problems.

Vanilla PnP for computed tomography (CT).

Vanilla PnP for computed tomography (CT).

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)

PnP with custom optimization algorithm (Condat-Vu Primal-Dual)

Uncertainty quantification with PnP-ULA.

Uncertainty quantification with PnP-ULA.

Vanilla Unfolded algorithm for super-resolution

Vanilla Unfolded algorithm for super-resolution

Deep Equilibrium (DEQ) algorithms for image deblurring

Deep Equilibrium (DEQ) algorithms for image deblurring