Combine two kinds of loss function about open-reid HOT 6 CLOSED

You need to write a new loss, similar to the one reid/loss/triplet.py and use that instead. Usually, you can just add losses together, just make sure to scale them since softmax can be much larger than triplet.

You would probably need to write your own data loader since softmax and triplet use different sampling techniques.

from open-reid.

@Rizhiy Thank you very much for the answer!

from open-reid.

@Rizhiy Thank you for your reply. But how to scale this two loss? In my network, I got softmax loss 1.5 and triplet loss 1.27, seeming unusual.

from open-reid.

To be honest I have never tried to train a network with multi-loss. Perhaps train softmax and triplet loss separately first, then calculate the scale such that they become the same value.

from open-reid.

You can add a parameter to control the balance between them.
For example:

loss = loss1 + lambda * loss2 

from open-reid.

@Rizhiy @zydou Thanks a lot for your answers!

from open-reid.