Closed xueyushan closed 5 years ago
@Peiliang
It's normal. Because each loss is weighted by their uncertainty: loss = sum(loss_i * torch.exp(-uncert[i]) + uncert[i]). As the loss_i becomes smaller, the uncertainty will become negative.
The larger the absolute value of the loss,the network is in convergence?
The optimizing variable is the loss instead of abs(loss).
Why is the loss negative? What do the plus or minus of the loss represent? Thanks very much!