yu4u / noise2noise

An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"
MIT License
1.07k stars 237 forks source link

Already have Input-Output Noisy Pairs #37

Open vinitjain1011 opened 5 years ago

vinitjain1011 commented 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?

yu4u commented 5 years ago

In that case, you should modify data generator to generate (noisy input, noisy target) pairs.

https://github.com/yu4u/noise2noise/blob/master/generator.py