Open vinitjain1011 opened 5 years ago
What if we already have noisy input and noisy target images? In that case, how do we tweak the changes to this architecture?
In that case, you should modify data generator to generate (noisy input, noisy target) pairs.
https://github.com/yu4u/noise2noise/blob/master/generator.py
What if we already have noisy input and noisy target images? In that case, how do we tweak the changes to this architecture?