Some questions about future_prediction.py

[okay-okay]

Hi,

I'm trying to re-implement the model from the paper, and for a time horizon of 2 seconds I'm able to reach the same recall, however, increasing that time horizon didn't result in an increase of accuracy or recall. I noticed that here:

AVT/models/future_prediction.py

Line 71 in b372773

self.assign_to_centroids = assign_to_centroids

, there's this block of code on kmeans/centroids that is not described in the paper, so I'm unsure if this is the insight that I'm missing for longer horizons, or not. Would you be able to help shine some light on what this code is doing? Additionally, do you have any tips on how to see an increase in accuracy / recall when increasing horizon time?

[rohitgirdhar]

Sorry for the confusion, this portion of code is actually not used in the paper, it's from some initial experiments I tried with quantized features. You can just ignore that part from the point of view of the paper.

[okay-okay]

I see. Do you have any insight into how you were able to reach higher accuracy / recall in increased horizon time? For longer horizons the re-implemented model overfits and there’s no performance boost from using longer horizon, are we missing anything when training for different horizons?

[rohitgirdhar]

Hi, I'm not sure what might be causing the overfitting. You should be able to experiment with different horizons in this code base by setting data_train.num_frames and data_eval.num_frames