Knowing the nature of my time series problem, I am using a stateful LSTM to forecast one step ahead.
My question is quite straightforward.
Do I need to explicitly save and pass the hidden cell in every prediction step in deployment, or Keras model already saves, updates and uses the states between predictions, and what I will do is simply predict as new data arrives?
Thanks in advance.
I think the Keras documentation gives a good explanation
stateful: Boolean (default False). If True, the last state for each sample at index i in a batch will be used as initial state for the sample of index i in the following batch.
In other words, when stateful=True, Keras saves the state between batches so that you don't have to.
This blog post has more details. http://philipperemy.github.io/keras-stateful-lstm/
