spandrel.architectures.DnCNN.DnCNN

class documentation

class DnCNN(nn.Module): (source)

Constructor: DnCNN(in_nc, out_nc, nc, nb, ...)

View In Hierarchy

Undocumented

Method __init__ # ------------------------------------ in_nc: channel number of input out_nc: channel number of output nc: channel number nb: total number of conv layers act_mode: batch norm + activation function; 'BR' means BN+ReLU...
Method forward Undocumented
Class Variable hyperparameters Undocumented
Instance Variable mode Undocumented
Instance Variable model Undocumented
def __init__(self, *, in_nc=1, out_nc=1, nc=64, nb=17, act_mode='BR', mode: Literal['DnCNN', 'FDnCNN'] = 'DnCNN'): (source)

# ------------------------------------ in_nc: channel number of input out_nc: channel number of output nc: channel number nb: total number of conv layers act_mode: batch norm + activation function; 'BR' means BN+ReLU. # ------------------------------------ Batch normalization and residual learning are beneficial to Gaussian denoising (especially for a single noise level). The residual of a noisy image corrupted by additive white Gaussian noise (AWGN) follows a constant Gaussian distribution which stablizes batch normalization during training. # ------------------------------------

def forward(self, x): (source)

Undocumented

hyperparameters: dict = (source)

Undocumented

mode = (source)

Undocumented

model = (source)

Undocumented