RodinIvan

Why do you use log_softmax in sampling?

1

In line 94 in caption.py you use: `scores = F.log_softmax(scores, dim=1)` Could you explain the reason for `log_softmax` here? You did not use it in `forward()` method. More than that,...

Long-term anticipation

1

Hi, thanks for repo! Excuse me, could you please tell how to perform long-term anticipation as showed in the paper? Have I missed this part in code, or it's not...

sample() with temperature

1

I've implemented run your network on my data, and seems that it struggles sometimes in generating texts - it just generates the sequence of dots of 'a a a a...