-
Notifications
You must be signed in to change notification settings - Fork 307
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
RuntimeWarning: overflow encountered in long_scalars #10
Comments
Could you share the network's code? |
I use DnCNN pytorch version from https://github.com/cszn/DnCNN/tree/master/TrainingCodes/dncnn_pytorch |
The following is a customized code
|
I guess the number is too big beyond the default type of python. |
It's strange because that means really huge amount of computations in such a small network.
May be the problem is in strange behavior of python in Windows. Do you use python2? I use python3.6 in ubuntu 16.04. |
Fixed in #43 |
Hello,
Does anyone encounter this issue? A negative flops.
The tested network includes Convolution, Batchnorm, and Relu only.
Thank you
The text was updated successfully, but these errors were encountered: