DCGAN-Keras
DCGAN-Keras copied to clipboard
Images seem to be dimmed with grey
Is it some dcgan problem or just an architectural mistake? Net seems to return images not in [-1; 1], lower bound is lifted up in -0.6, -0.5 or so. So normalization like in this code makes greyed images. I tried to calculate min value and use it, but this makes images look a bit weird and have unrealistic colors sometimes. Any ideas?
this is indeed a mistake. the input to the network are ranged in [-0.5, 0.5]; please multiply the input (data for training) by 2.