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
The paper 'Self-critical Sequence Training for Image Captioning' mentions that our baseline is greedy argmax decoding, which is the same as the inference time technique used.
If that's the case, shouldn't the beam size for inference be always 1? If we just choose argmax at each step, there's just one possible way of forming a sentence right?
The text was updated successfully, but these errors were encountered:
The paper 'Self-critical Sequence Training for Image Captioning' mentions that our baseline is greedy argmax decoding, which is the same as the inference time technique used.
If that's the case, shouldn't the beam size for inference be always 1? If we just choose argmax at each step, there's just one possible way of forming a sentence right?
The text was updated successfully, but these errors were encountered: