Anyone know what do I do wrong?
Hi @pongyuenlam
Your Logit shape has missing unit when compared to the expected output.
So first I would check the below two codes in the def call for decode layer being called correctly or not
Do a pass through the post attention LSTM
x = MAKE SURE YOU HAVE RECALLED THIS WITH THE CORRECT POST ATTENTION LSTM, WHICH would be ACCORDING TO THE RNN AFTER ATTENTION i.e. ???(x)
Compute the log-its
FOR THIS YOU ARE SUPPOSE TO USE THE RECALL LAYER FROM THE DENSE LAYER WITH LOGSOFTMAX ACTIVATION, W…
if you notice your output to expected output, your only results match with logit shape
so I would check the cross attention as well as the decoder call function codes.
I found the root cause. It was because I didn’t set the return_sequences=True in the post_attention_rnn, which should be identical to pre_attention_rnn except for the change that return_state should change to False.
