In Colab practice part, it suggest that we use return sequence = True for all LSTM layers. Why is that?
suppose we want to predict the next character in a given sequence.
Since the intention is to predict a character for every time step i.e. for every character in the sequence, the next character needs to be predicted.
So, the argument “return_sequences=True” is set to true.
If this argument is set to False, then only the last output would be returned.
that’s why it’s suggested to use “return_sequences=True”.
Rakib Hossain Rifat