Minh Vu

Hi author, I am curious about the "eps" parameter. To perform SGD for the meta step, why don't you use eps?

> Hi, as your suggestion, I really want to clarify that, You mean, we should use like term_a = torch.log(self.prior_d(prior)).mean() term_b = torch.log(1.0 - self.prior_d(y.detach())).mean() PRIOR = - (term_a +...

Excellent work Yura! FYI @susie-ku working with Transformer you usually encounter matrix multiplication. I always keep my eyes on whether a vector with shape `(x,)` or `(x,y)`. Reshape `(x,)` to...