Inconsistency in temporal model output shapes

[dmitra79]

Hello,

I am playing with temporal models, like in Video.ipynb tutorial. One thing I noticed was that for those models, with v>1, the return shapes are different for label_model.predict and label_model.predict_proba_marginalized. The former returns a value for each v in a frame, while the later returns a single value for the whole frame. So if v=3, and there are 1000 frames, the first returns (1000,3) while the second returns (3000,). I think it would be convenient to have the same shapes in both cases.

Thanks!

[DanFu09]

Thanks for this suggestion! The difference between predict and predict_proba_marginalized is that predict operates in terms of "sequences" (for v=3, this would be sequences of 3 frames), while predict_proba_marginalized flattens them out into individual elements. That's why predict returns (1000, 3), and predict_proba_marginalized returns (3000,).