unet-nested-multiple-classification
unet-nested-multiple-classification copied to clipboard
issue in testing
for masks, I make a multi-classification for 10 classes, I set the value of background as "0" for gray image, but in the testing result, I can always see the original image for the background, which means the background have not been classified. could you bring me some suggestions? should I begin background in value "1" in masks?
In other words, why can I see the original picture in testing result? why doesn't each pixel in the result has been classified? in my result, some pixels has been classified, and others display as original pixel value, but not been classified in any of the classes. Thank you.
Hello, i meet the same problem,have you solved it ?