loss: Nan.
linyingyingkarina opened this issue · comments
linyingyingkarina commented
Hi, thanks for your work.
I have succeeded to run the code. But when I ran it in a new GPU, the data, the code, all the same. However, during the training, even in the first epoch. The loss is shown with Nan. Do you know why? or any possible of causing this??
Thanks a lot.
Noam Suissa commented
Having the same issue. Any success lately?
Bear commented
Same issue. This can be avoided when gamma is set to 1.