Bugs in Seq2Seq model

[JianLiu91]

Hi, the code has a nice abstraction and easy to follow. Thanks!!

However, there are some issues in your implement....

(code)

If you don't pass c_t through a Linear layer from encoder hidden to decoder hidden, then the code crashes. (Encoder and Decoder can have different dimensions)

(code)

When self.decoder.num_layers != 1 the view function will crash because of dimension dis-match.

[MaximumEntropy]

Hi,

Thanks for pointing this out, I was working on fixing these in the refactor branch. I should merge refactor into master sometime soon and these issues should be fixed.