Losses in Fasterrcnn end up becoming NAN during training.Why the model returning nan as output's Loss?

vision
1

I replaced L1-smooth Loss in bounding box refinement state with IoU Loss and GIoU Loss in Fasterrcnn,but the result of class_loss ,regression_loss,rpn_class_loss and rpn_bbox_regression_loss is Nan.Thus,Fasterrcnn is stopping train. I use the same parameters as L1-smooth Loss.

image
image764×696 117 KB

debug is Nan

2

image
image1020×382 58.5 KB

This my result of debug!