Doubt about the defined hinge version Loss

[hhguo]

Hi, I am curious about the hinge loss defined in your paper. It seems that your implementation is different.

This is the definition in your paper.

But you use F.relu in the code, which is max(0, D(x))

I tend to believe that the code implementation is correct, so maybe the paper definition is wrong?

[allenhung1025]

I have the same doubt, too.

[jamesliu]

I believe the implementation is right, but the paper definition is likely not correct(max instead of min or adding -). May someone confirm it? Thanks.