Inference gives NaN
jchengai opened this issue · 1 comments
jchengai commented
Hi, thanks for your nice work.
When running python test.py -m lanegcn --weight=lane_masking.ckpt --split=val, the evaluation results are NaNs. Could you please tell me the cuda version of your experiment environment?
jchengai commented
Well, I solve this issue with by upgrading pytorch from torch1.5.1+cu10.2 to torch1.11+cu113.