Closed Yupei-Du closed 4 years ago
As you see here, the size of context
is the size of encoder outputs (512 = bidirectional rnn of 256).
And decoder input size is 812 = 300 (word embedding size) + 512 (encoder output size) here
So you need to change the size of encoder to 256 as well to match it.
The authors of NQG++ used 512-dim decoder for match dimensions of encoder and decoder
Thanks a lot, I'd like to close this issue 👍
Hi, thanks for open-source the code!
However, when I change the 'dec_hidden_size' to 256, an error occurs:
I guess it is because the 'context' doesn't 'bridge' to the right size. How should I fix it? Thank you so much.