About controlling model outputs

[kyoto7250]

Hello, Thank you for your paper and code!

Currently I'm running your model and experimenting.

In many generative models, it is possible to manipulate the maximum length of outputs or adjust the number of outputs, where can this be done in run_model.lua?

[kyoto7250]

adjust the number of outputs

I read your code, and I understood number of captions is len(detected object) * (len(detected object) - 1).