You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have the same issue. That might because the images are processed wrongly at the very beginning. You can check the generated/samples_groundtruth.png. If this image is also black wiht noise then it's likely that you used training images with .jpg format. I found another repository Carysss/GANGogh whose traning images are PNGs(see smallimage). Since Carysss published the successful outcomes in the folder generated. I suspect the format of tranning data causes this problem.
After more than 25k runs, the generated output is still the same:
I am using the default settings, nothing changed. Is this is familiar issue?
The text was updated successfully, but these errors were encountered: