Though I can find you have implemented this function in your another repository 'video-caption-openNMT.pytorch', it's hard to comprehend it. Would you please make it available in this repository? Thanks a lot.
If I want to port opennmt's beam search to this project, I have to change the structure of my code a lot. But I don't have so much time now. You can issue a pull request if you implement it.
Though I can find you have implemented this function in your another repository 'video-caption-openNMT.pytorch', it's hard to comprehend it. Would you please make it available in this repository? Thanks a lot.