Zhang-haotian
Zhang-haotian
put_your_model_name, means that the directory that you want to save the file produced by the running code!
您好,我问下您在 `loss = self.soft_plus(torch.logsumexp(logit_n, dim=0) + torch.logsumexp(logit_p, dim=0))` 这一行代码写的loss函数,是不是和原文函数不太一样啊? 原文中log中还要再加上1吖?是我理解错了么 @TinyZeaMays
> > 您好,我问下您在 > > `loss = self.soft_plus(torch.logsumexp(logit_n, dim=0) + torch.logsumexp(logit_p, dim=0))` > > 这一行代码写的loss函数,是不是和原文函数不太一样啊? > > > > 原文中log中还要再加上1吖?是我理解错了么 > > @TinyZeaMays > > e的0次方等于1,自己看看代码。 好的,感谢🙇
I have solved this problem with the environment: tensorflow-gpu==1.13.1 python ==2.7