Yiyun Chen

thank you! and I am confused about the code: for x = 1 : stride : (hei-size_input+1) for y = 1 : stride : (wid-size_input+1) x_l = stride_low*(x-1)/stride + 1;...

Is it used to compute the 'count'?

hello, I am also confused with the 'degradation_params', it seems that the images blurred by different sigma are get with the same 'degradation_params': DASR_model.py#L100 self.degradation_params[:, self.road_map[0]+1:self.road_map[0]+2] = (data['kernel1']['sigma_x'].unsqueeze(1) - self.opt_train['blur_sigma'][0])...