Hi there,

first of all, very nice tutorials you have written. But I have a short question regarding the prediction stage at the end.
lstm_out, indices = F.max_pool1d(lstm_out, lstm_out.size(2), return_indices=True) # Figure 9
Why do you need max_pooling over the entire sequence again and not just take the last output stage of the lstm model? I have also seen some model, where people just use the last output stage to do further predictions.

Thanks! :-)

Hi,
when I am trying to run the notebook with python 3.6 I keep getting this error message:
RuntimeError: Expected hidden[0] size (1, 32, 32), got (2, 32, 32)
I think the problem starts here, but I am not sure:
---> 26 packed_output, (ht, ct) = self.lstm(packed_input, self.hidden) # Figure 6

It would be very helpful for me if you could fix the error and thus having a running example again.