ValueError: vec Nan

[aakash-saboo]

Hi I was training a GAN using the optimizer. It runs fine for 80 iterations but on 81st iteration, it gave ValueError: vec Nan.

Can you suggest me a possible way to debug it? The same code with adam is just running fine.

Thanks

[devzhk]

I will push a new code in like one week. You can try that one. However, for the current version, I would suggest add use nn.BCEwithLogits and L2 weight penalty to the loss.

[aakash-saboo]

Hey, Thanks for your quick response.

I am using nn.BCEWithLogits but not L2. I am using L1 loss. Ill try replacing it with L2.