You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The decoder does not take only the hidden state of the dialog RNN, s_{t},
but also the last hidden state of the encoder RNN, h_{t}. Possibly, the decoder
should take the s_{t-1} and not s_{t}.
The text was updated successfully, but these errors were encountered:
…utterance encoder(s) and utterance decoder. Also factorized UtteranceDecoder to make it easier to add future inputs to the it. In particular, I renamed \'hs\' to \'inp\' in UtteranceDecoder.
The decoder does not take only the hidden state of the dialog RNN, s_{t},
but also the last hidden state of the encoder RNN, h_{t}. Possibly, the decoder
should take the s_{t-1} and not s_{t}.
The text was updated successfully, but these errors were encountered: