akshaydudhane16/BIPNet

Loss nan for BurstSR Track 2 training

bluedream1121 opened this issue · 2 comments

bluedream1121 commented

When I train the real-world burst SR benchmark using Track_2_evaluation.py, the value of loss becomes nan.

I did not modify any of the source code from the released version.

loss_nan_track2_bipnet

Do you know how to fix this issue?

bluedream1121 commented

this is an issue of the evaluation metric.

SuperStacie commented

Hi, I met the same problem, how do you solve it? Thanks!