Open azraelkuan opened 3 years ago
Do you have a specific use-case in mind for these two additions? I'm open to adding these features – it would be nice to have a sense of the scope and value of these changes.
@sharvil oh,thanks to your reply. for the first question: in the original paper, it has two different zonout on lstm states. for the second question: the dropout will be benifit for very long sequence. like tts acoustic modeling
hi,any plan about these two questions
lstm zoneout on cell state the same with hidden state https://github.com/lmnt-com/haste/blob/9da2454584d5b5bc9b2ae84a3fa2b271306ec622/frameworks/pytorch/layer_norm_lstm.py#L62-L66
add recurrent dropout the same with keras https://github.com/tensorflow/tensorflow/blob/fcc4b966f1265f466e82617020af93670141b009/tensorflow/python/keras/layers/recurrent.py#L2450-L2459
thanks!