Nan problem for LOG about focal-loss-keras HOT 6 OPEN

@roywang2011 you need to make sure pt_1 does not become 1 and pt_0 does not become 0 when using gamma<1.0. Clip both with K.epsilon().

from focal-loss-keras.

did you find the solution? i am getting nan loss

from focal-loss-keras.

@gulzainali98 adding K.epsilon() fixed Nan

from focal-loss-keras.

can this be used on simple classification? i.e i am using CelebA dataset. Image just have to be classified into 40 different classes there is no object detection.

from focal-loss-keras.

can this be used on simple classification? i.e i am using CelebA dataset. Image just have to be classified into 40 different classes there is no object detection.

did you fixed your problem? I add K.epsilon() and still get nan

from focal-loss-keras.

I add K.epsilon(),and it works! 👍

from focal-loss-keras.