Got NaN loss when use the Gaussian idea to regression TASK.
FunkyKoki opened this issue · comments
So sorry, I press 'Enter' just now.
I want to apply the Gaussian idea into my regression task, but I cannot solve the NaN problem.
I used the Gradient Clip and small learning rate, it changed nothing but decayed the time the NaN came out.
So, will the Gaussian loss xy be negative when you train the Gaussian model?
Anyway, thanks for your great work~
Hi, @FunkyKoki.
Introducing sigma_const
parameter may work.
You need to modify YOLOLayer class to do that (just add sigma_const
to predicted uncertainties when compute gaussian losses).
jwchoi384/Gaussian_YOLOv3#40
So, will the Gaussian loss xy be negative when you train the Gaussian model?
Yes. it goes to negative value but this is not a problem.
Thank you so much,with the sigma_const
set, the training process becomes stable.
Hug you~ You save my life.