Heath30zyl

Results 1 issues of Heath30zyl

self.soft_plus(torch.logsumexp(logit_n, dim=0) + torch.logsumexp(logit_p, dim=0))

2 comment

Isn't it "loss = self.soft_plus(torch.logsumexp(logit_n, dim=0) * torch.logsumexp(logit_p, dim=0))" ?