flowseq

flowseq copied to clipboard

Can someone explain why restricting the posterior `z` as diagonal Gaussian?

1

Maybe I do not understand this paper throughly, but can someone explain this? The posterior `z` is modelled as diagonal Gaussian. And in the `Zero initialization` part, `ensures that the...

seekerzz

a question about `tgt_path_ori`

1

Why we need `tgt_path_ori` and what is the difference between `tgt_path_ori` and `tgt_path`?

ghost

Fix for `self.embedding_dim` which is not a attribute of the module.

DeNeutoy

Hi, Thanks for sharing your code. How many steps or training time do it need to train the flowseq model on WMT14 EN-DE? Will you release the distillation dataset? It...

shaochenze