Information regarding training time about vqa.pytorch HOT 6 OPEN

On one TitanX Pascal, on VQA2, when data loading time is closed to 0, you can expect 5 hours before convergence for a NoAtt model and 12 hours for a Att model.

from vqa.pytorch.

Same for VQA1 too?

from vqa.pytorch.

I don't remember for VQA1, but as it is composed of half of the questions, I would say 3 hours for NoAtt and 7 hours for Att. Let me know :P

from vqa.pytorch.

And you used the whole training set for training 100 epochs?

from vqa.pytorch.

train/val or trainval/test
But in both cases, always the full dataset

from vqa.pytorch.

But you only train with the examples whose multiple choice answer is in the top n% (n determined by nans) and discard other examples. Is that correct?

from vqa.pytorch.