songhyunyu / didn Goto Github PK

Hi Author,
I am trying to train my data set.
So,I am very curious about the data content generation rules in training_rgb_5to50_uint8_samples.h5. If possible, could you please share this file through baidu cloud disk or some other ways ?Thank you very much.

hi, I have a question when I read the codes.
When I use DIDN for raw images, which model should I choose? The gray_model? Or I need to modify them?

I am trying to test the code on noisy images, the original images are noisy images however for I assign noiseSigma to 0 when generating the dataset, that way the noisy and orginal dataset contains the same values. In this case the model outputs the same noisy image I started with

Hi there, thanks for sharing the code!

I am trying to use the code and cite it in my paper but I need to get clearance of the License requirement.

If you have time, would you mind updating the License information of your code base?

Thanks a lot!

Hi,

I have a question regarding the use of bias in the convolutions. I notice that you don't use them (see here for example). What is the rationale behind that? I seem to find no trace of it in the paper.