FewX
FewX copied to clipboard
NaN
Dear author, thanks for you great work. Currently I am trying to run your code but always report NaN error, the following is the error traceback, can you have a look? Thanks in advance!
detectron2/detectron2/modeling/proposal_generator/proposal_utils.py", line 103, in find_top_rpn_
proposals
raise FloatingPointError(
FloatingPointError: Predicted boxes or scores contain Inf/NaN. Training has diverged.
When I train with 4 GPU, NaN gone. However, when I train on 8GPU, it always yield NaN