point-transformer
point-transformer copied to clipboard
NaN Loss
Hi, first of all thank you for the great repository and the efficient implementation. Does someone else encounter a NaN loss due to the sum operation in the TransitionUP module of the decoder 5. I removed the two linear layers and the training works fine. Please comment if you solved the issue.
I am facing the same issue as well. Did you figure out how to solve this error?
@vardeep-sandhu Did you find out the reason? Thanks