Hello there,
If the testing set does not have any segmentation mask (ground truth), then how are we going to calculate the Dice and IoU (Jaccard Index) of the generated samples?
There seems to be no code for that at all.
Another issue I got is that the model generates black samples most of the time, I tried to train it a few times, but still had the same problem.
Can you please provide me with some solutions.
I will be highly grateful.
Thank You!
Hello there, If the testing set does not have any segmentation mask (ground truth), then how are we going to calculate the Dice and IoU (Jaccard Index) of the generated samples? There seems to be no code for that at all.
Another issue I got is that the model generates black samples most of the time, I tried to train it a few times, but still had the same problem. Can you please provide me with some solutions. I will be highly grateful. Thank You!