Hello, a question about the CDAN function in loss.py

[BaeHann]

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?

[BaeHann]

I am not that proficient in English. If there is anything grammatically wrong or incomprehensible, please be so kind as to inform me.