Closed slchenchn closed 3 years ago
Check the paper, for the noisy image with the original size (not sub-sampled), it also needs to go through the Denoising Network and yields the regularizer term.
Check the paper, for the noisy image with the original size (not sub-sampled), it also needs to go through the Denoising Network and yields the regularizer term.
But why should it stop the gradients produced by the original size image?
It is an empirical training technique. Stopping the gradient is helpful to stabilize the training. It does not violate the theoretical motivation.
I'm a little confused about the question. We don't have the groundtruth of the original size image in this paper, so how to get the gradients produced by the original size image?
Hi, I am confused about the code in the training_cript.md:
It seems that the disabling gradients operation didn't appear in the paper, and could you please explain the special purpose for doing this?