LIR-for-Unsupervised-IR

LIR-for-Unsupervised-IR copied to clipboard

In the gen_update method, why is random noise (torch.randn) added to the reconstruction process?

1

wudishuaishuainiu

我的数据集是640*512的红外噪声图像（Celeba_B）与干净图像（Celeba_A），但是一直在 File "G:\WIN\LIR-for-Unsupervised-IR-master\networks.py", line 344, in forward return self.model(x) 与 File "G:\WIN\LIR-for-Unsupervised-IR-master\networks.py", line 467, in forward x = self.conv(self.pad(x))的 def forward(self, x): x = self.conv(self.pad(x)) if self.norm_type != 'wn' and...

Furxier

Hello How are you? I am going to apply this method to a general image restoration such as deblur & denoising. I found that the training step requires testA and...

rose-jinyang

Hello, I would like to ask whether you correspond the clear image and the unmatched noise image to Celeba_A and Celeba_B respectively, or the reverse

wyhhhhhhhh