Pytorch implementation of four neural network based domain adaptation techniques: DeepCORAL, DDC, CDAN and CDAN+E. Evaluated on benchmark dataset Office31.
80
stars
22
forks
source link
Hello, a question about the CDAN function in loss.py #7
Hello!
Within the CDAN function, entropy.detach() was not found. Does that mean the entropy will be affected (as well as the classification result and relevant parameters in model) when loss.backward() was executed?
Hello! Within the CDAN function, entropy.detach() was not found. Does that mean the entropy will be affected (as well as the classification result and relevant parameters in model) when loss.backward() was executed?