lesson 2 decoder impl output to linear

[iyersathya]

//feed, embedding+context and hidden state to RNN.
output, hidden = self.rnn(emb_con, hidden)

Shouldn't the line below be concat (embedding + output + context) instead of (embedding + hidden + context) ? Calculated hidden vector by RNN at time step t will be fed to next rnn at t+1 anyway.

output = torch.cat((embedded.squeeze(0), hidden.squeeze(0), context.squeeze(0)),
dim = 1)

prediction = self.out(output)

[bentrevett]

It can be either output or hidden here. Both of these tensors are exactly the same. You can test this with: assert torch.all(torch.eq(output, hidden))

[iyersathya]

@bentrevett Thank you.