ef-ever

if "aff_loss_edge" and "aff_loss_nedge" do not have a coefficient of "dec" that decreases with "step", can "aff_loss" converge?

1

Excuse me, if "aff_loss_edge" and "aff_loss_nedge" do not have a coefficient of "dec" that decreases with "step", can "aff_loss" converge? When I run "train_affinity.py" with the parameters mentioned in "train_pspnet_affinity.sh",...