dzimm
1
When running for example
torch.randn(64, 512, 1, 1).normal_(mean=0.0007720401627011597, std=0.01006225310266018))
there are sometimes nans in the tensor.
I’m working on pytorch 0.1.12 with python 3.5 and the “Bug” is reproducible. Am I doing sth wrong or is it already fixed ?
did you figure out how to solve it?
I am running this on pytorch 0.4 and I haven’t seen any nans yet. @isalirezag what version of pytorch are you on?
@richard I am using 0.3 version