confusion about Discriminator

[Goody7]

In my experiment, the output of the discriminator is about 0.49 after GAN convergence. How could you make the discriminator output probability larger than 0.5?

[cod3r0k]

In my experiment, the output of the discriminator is about 0.49 after GAN convergence. How could you make the discriminator output probability larger than 0.5?

As I mentioned before I hope the authors answer these questions as soon as possible, but I had the same problem with your mentioned issue, but it depends on our training stop. The GAN training with pure optimization scenarios, has some tricks for stopping criteria.

[khalooei]

In my experiment, the output of the discriminator is about 0.49 after GAN convergence. How could you make the discriminator output probability larger than 0.5?

In my experiment, the output of the discriminator is about 0.49 after GAN convergence. How could you make the discriminator output probability larger than 0.5?

As I mentioned before I hope the authors answer these questions as soon as possible, but I had the same problem with your mentioned issue, but it depends on our training stop. The GAN training with pure optimization scenarios, has some tricks for stopping criteria.

Dear @Goody7 and @cod3r0k , As you know, the GANs are difficult to train. The reason they are difficult to train is that both the generator model and the discriminator model are trained simultaneously in a game. This means that improvements to one model come at the expense of the other model (In our case, we have R as generator model and D as reference discriminator model). The goal of training two models involves finding a point of equilibrium between the two competing concerns and as we mentioned in our paper, it depends on our stopping criteria over the time and status of each network.