clab/dynet

"empty" RNNStates should be rigged to return zero vectors on .s(), .h(), etc

Open

#1 322 ouverte le 24 mars 2018

Voir sur GitHub
 (2 commentaires) (0 réactions) (0 assignés)C++ (701 forks)github user discovery
good first issueminor bug

Métriques du dépôt

Stars
 (3 433 stars)
Métriques de merge PR
 (Métriques PR en attente)

Description

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.

Guide contributeur