i cannot find a way of combining the two examples from the documentation.
E.g., i want to decode a 13-dimensional state vector s0 into a sequence of length 11. Each element of the sequence is a softmax over a vocabulary of 3 words. I'm using batch size of 7. This is what I've got, but it fails in fit due to a shape problem:
i cannot find a way of combining the two examples from the documentation. E.g., i want to decode a 13-dimensional state vector
s0
into a sequence of length 11. Each element of the sequence is a softmax over a vocabulary of 3 words. I'm using batch size of 7. This is what I've got, but it fails infit
due to a shape problem:i also tried passing s0 in the
initial_state
parameter ofrnn
, but that breaks even earlier (pop from emptyinputs_list
in thernn(...)
call.