People ask how to implement LSTM Seq2Seq in Keras. Here's the tweet version (a bit verbose). I'll publish the complete script soon.pic.twitter.com/r85bNQpQwr
-
What if one would like to try without basic teacher forcing, also using the output of the decoder?
The model above uses teacher forcing for training. Not-teacher-forcing could be done with a custom RNN cell, or a static loop for fixed-len
-
-
Do you know where I can find good examples of this? Thanks!
-
I will be posting a blog post about seq2seq, which will include a code example for the static loop solution.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.