Regarding the loss_att

[Aboelenien]

In this block in training, I don't get the loss_att and its use.

loss_att = 0
loss = criterion(y, target)
loss = loss + loss_att

[ok1zjf]

Sorry for the confusion. The loss_att is not being used in this implementation. We experimented with a number
of composite loss functions but didn't use them in the final implementation. You can remove the "loss_att = 0" and
"loss = loss + loss_att"