Suppose I have a multi-task learning problems, I have a shared CNN module and there are 4 different small network behind the module, the losses for each network are L1, L2,L3,L4, so the total loss are L = L1+ L2+L3+L4, how to update 4 different network parameters? L.backward()? or L1.backward(),L2.…

Loss function backward problem

lxtGH (Latou) March 8, 2018, 5:17am 2

How to combine multiple criterions to a loss function?

I;m building recursive neural nets, so I’ll have a variable list of criterions. I want to sum them up and backpropagate error. All the errors are single float values and of same scale. So the total loss is the sum of individual losses To understand this, I crystallized this problem. It’s for another classification project. I wrote this code and it works def loss_calc(data,targets): data = Variable(torch.FloatTensor(data)).cuda() targets = Variable(torch.LongTensor(targets)).cuda() outp…

show post in topic

Home
Categories
Guidelines
Terms of Service
Privacy Policy

Powered by Discourse, best viewed with JavaScript enabled