Questions about the setting of network when denoising.

[leonmakise]

I saw that your also involve in the 'NTIRE 2019 Challenge on Real Image Denoising: Methods and Results' and reach good results. In your code ,it's more about archs for SR. I wonder how you set it for denoising, especially for raw data.

I want to reimplement your results for comparison. Here is my attempt:
scale_factor == 1
kernel = 4
stride = 2
padding = 1
DBPN(num_channels=1, base_filter=64, feat = 256, num_stages=7, scale_factor=1)

Can you give some advices on it? Thanks a lot!