Motivation behind the denormalize function

The denormalize function in layers.py is defined as (layer + 1.)/2. If the aim is to revert the earlier normalization, shouldn't we have (layer + 1.)*127.5?

Asking because I'm facing a problem where the refined images are extremely dark (low intensity), since the pixel values are very low after denormalization.

Open layers.py and inspect denormalize alongside the earlier normalization described in the issue. Trace the value ranges through the refined-image path and determine whether denormalization restores the intended pixel range. Done means the formula is consistent with normalization and refined images no longer have unexpectedly low intensity.

Written by the indexing model from the issue text.