Useless argument in sequence_loss function

Conchylicultor / DeepQA

My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

Apache License 2.0

2.93k stars 1.17k forks source link

Useless argument in sequence_loss function #151

Open apiro opened 7 years ago

apiro commented 7 years ago

Hi,

I noticed that you are passing self.textData.getVocabularySize() to the sequence_loss function while this function doesn't need the vocabulary size. I think that it is a typo that fortunately doesn't affect the overall code correctness.

Correct me if instead there is some kind of reason for the use of this parameter.

Alberto

Conchylicultor commented 7 years ago

Nice catch. Indeed, I'm not sure why this argument is passed.