remember to include The center loss parameters in the optimizer, othewise it will not work

[mohamedr002]

[toannguyen1904]

can you give us an example?

[cotyyang]

can you give us an example?

maybe he mean is this. in main.py 80 line optimizer_centloss = torch.optim.SGD(criterion_cent.parameters(), lr=args.lr_cent)

[mohamedr002]

can you give us an example?

maybe he mean is this. in main.py 80 line optimizer_centloss = torch.optim.SGD(criterion_cent.parameters(), lr=args.lr_cent)

Yes, exactly, this is what I meant, the center loss parameters are trainable parameters and should be updated during training, by excluding these parameter from the optimizer, it will not change,

[fafafafafafafa]

why i put optimizer_centloss into optimizer, raise ValueError("optimizer got an empty parameter list"? anyone can help me?