algeriapy
(Fares Bougourzi)
June 13, 2020, 5:34pm
1
I am trying to implement Adaptive Loss function, which has the formulas
here my code
def Adaptive_loss(preds, labels, sigma):
l2 = (1+sigma)*(torch.mean(preds - labels)**2)
l1 = sigma + torch.mean(torch.abs(preds - labels))
return l2/l1
The issue I got very very worse performance compared with using MSE loss
Could anyone check if I have any mistake
You are taking mean
in the numerator and denominator separately instead of taking the mean
after l2/l1
. In other words, mean(l1/l2)
is not mean(l1)/mean(l2)
1 Like
algeriapy
(Fares Bougourzi)
June 13, 2020, 7:44pm
3
Thanks a lot, your note fixed the issue
I am having difficulties implementing adaptive loss. Can you kindly share your solution function with me?