You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I suspect that ib_encoder_to_point is correct and that if there is a bug in language_to_ib_point then it comes from converting the language to the encoder, i.e. the Speaker weights, in language_to_ib_encoder_decoder.
I’m pretty sure the LiteralSpeaker has to be the problem. Because if we look at line 230 of agent.py we’ll see it initializes a binary matrix, which is not right.
I should consider refactoring these agents to be more flexible at initialization and have this be default behavior if a weight matrix isn’t passed in.
What we probably want to do is use the regular Speaker class and pass in weights as one of the kwargs, since CommunicativeAgent will then initialize correctly.
This will require some rewriting of the relevant functions in rate_distortion
The text was updated successfully, but these errors were encountered:
I suspect that
ib_encoder_to_point
is correct and that if there is a bug inlanguage_to_ib_point
then it comes from converting the language to the encoder, i.e. theSpeaker
weights, inlanguage_to_ib_encoder_decoder
.I’m pretty sure the LiteralSpeaker has to be the problem. Because if we look at line 230 of agent.py we’ll see it initializes a binary matrix, which is not right.
The text was updated successfully, but these errors were encountered: