human-motion-prediction icon indicating copy to clipboard operation
human-motion-prediction copied to clipboard

Published 20 hours ago • verified publisher icon una-dinosauria

question about the srnn_loss

Open sukun1045 opened this issue 5 years ago • 3 comments

In the translate.py, when you test with srnn seeds, it looks like the srnn_loss you print out is only for the last action instead of an average loss of all actions.

sukun1045 avatar Feb 21 '19 03:02 sukun1045

Hi,

Sorry this is pretty hard for me to follow. Could you point to me to specific lines in the code, and what you think they should be instead? Better yet, you could open a pull request with the fix and then we can discuss it.

Cheers,

una-dinosauria avatar Feb 21 '19 04:02 una-dinosauria

Sure, in translate.py line 193, you have the srnn_loss for one action. However, after the for loop of all actions, in line 472, you print out the srnn_loss, which is only the srnn_loss for the last action. If i am correct, you should sum up srnn_losses for all actions and print out the average.

sukun1045 avatar Feb 21 '19 04:02 sukun1045

I think I see it. It works fine when there is only one action, but not when we train on all actions. Would you be up for submitting a PR?

una-dinosauria avatar Feb 21 '19 15:02 una-dinosauria