thuml
Cross-Entropy Loss is not included in the total loss
Hi,
In the paper "Transferable Representation Learning with Deep Adaptation Networks", you use cross-entropy loss (which is corresponding to equation 8 in the paper) to minimize the uncertainty of predicting the labels of the target data.
I find the corresponding implementation of that equation which is defined as EntropyLoss() in loss.py. In the paper, the total loss is composed of three main parts: the classification loss, the mmd loss and the cross-entropy loss.
What confused me is that in train.py, you do add the mmd loss and the classification loss together, but you don't actually add the cross-entropy loss. I am wondering do I miss something or do you do it on purpose?
Looking forward to hearing from you soon.
Thank you, Ke
Actually this confused me as well.
The fact is there are two versions of DAN, in year 2015 and 2018. The code you mentioned is a reimplement of DAN 2015, there are only two losses in paper DAN 2015.
