JS=1,DS>1and loss>1000

Open kimjisoo12 opened this issue 4 years ago • 1 comments

Hello, SORRY to bother you, when I refocused m attention Unet on my custom dataset, I also encountered JS which was always 1 and DICE >1, I saw previous comments, I changed Torch. Max to Max without any improvement, and my loss was always over 1000, what is the reason?

223

Oct 21 '21 01:10 kimjisoo12

update the evaluation.py into the following version: https://github.com/LeeJunHyun/Image_Segmentation/blob/35b98018bf7efcb733ec214200c0ebbdec797f28/evaluation.py

Nov 13 '21 02:11 Lloyd-Pottiger