MedSegDiff icon indicating copy to clipboard operation
MedSegDiff copied to clipboard
verified publisher icon KidsWithTokens

The generated image is black

Open haoli-maker opened this issue 1 year ago • 2 comments

The image I generated after training looks like this, is that correct please? How can I process it to get the image in the author's paper? Thank you so much! image

haoli-maker avatar Sep 09 '24 08:09 haoli-maker

If you increase the contrast and brightness, you will find that there are generated contents inside. It seems that you might have used the wrong training model. Using the "emasavedmodel_0.9999_000000.pt" for training might be better.

MilkTeaAddicted avatar Sep 23 '24 06:09 MilkTeaAddicted

How many steps have you trained, and it may be caused by insufficient training time

MilkTeaAddicted avatar Sep 23 '24 09:09 MilkTeaAddicted