Nan value in convolution output

1

I am getting nan value in the convolution output like this [ 6.6468e+00, 7.1471e+00, -7.2259e+00, nan].

I am using efficient net. Please help me.

2

Hi, Can you please put the code here for reproduction?

3

It is not the output of the convolution that produces nan but the input to the loss function. It is due to divisibility by negligible amount I think.

4

log of a negative decimal value is resulting nan value. Do you know how to solve this?. Should take absolute difference or make relu?