clab/dynet
Vedi su GitHub"empty" RNNStates should be rigged to return zero vectors on .s(), .h(), etc
Open
#1322 aperta il 24 mar 2018
good first issueminor bug
Metriche repository
- Star
- (3433 star)
- Metriche merge PR
- (Metriche PR in attesa)
Descrizione
having .s() return nothing on an RNN's initial state is very confusing (at least to me), as there must be some kind of value from which the RNN starts and not revealing it just hides what's going on (making things like automaton-extraction very difficult).
to my understanding, RNNStates with empty .s() are effectively treated as having zero-vectors in .add_input() computations (the matrix multiplication with the missing c/h vectors is simply skipped). It would be nice if .s(), .h(), .output(), etc reflected this.