Results
6
comments of
Yilin Liu
I have the same problem with Dice loss/GDSC.
the input size has to be the multiplies of 8
Actually, using crossEntropy always works for my network but whenever I use the Dice loss or GDSC loss, the training loss just doesn't seem to decrease much no matter how...
Same problem here.
Is the implementation wrong?
I'm having the same error here. Have you resolved it?