Open ed-Im opened 2 years ago
I am learning by custom dataset. The problem is that the loss value becomes negative after a few iterations after learning. May I know the cause of your prediction?
It's natural for RMI loss to go negative: https://github.com/ZJULearning/RMI/issues/5
But there's another issue which is that you're out of memory in the GPU. Try to shrink the crop size to something like 800
I am learning by custom dataset. The problem is that the loss value becomes negative after a few iterations after learning. May I know the cause of your prediction?