Could not find the discriminators (the adversarial losses)

[sean-sun]

As written in the paper, the NAN model is composed of three sub-nets, each one trained with some prediction loss (compared with ground truth labels) and adversarial loss. However I could not find the adversarial losses in the code. Is it not included, or lying somethere that I missed? BTW, thanks for sharing the code.

[Minssnail]

I also have the same problem.

As written in the paper, the NAN model is composed of three sub-nets, each one trained with some prediction loss (compared with ground truth labels) and adversarial loss. However I could not find the adversarial losses in the code. Is it not included, or lying somethere that I missed? BTW, thanks for sharing the code.