Handling images with no bboxes in it

[kulkarnikeerti]

Thanks a lot for the great repo. I am trying to use the repo with custom dataset. I have my own input pipeline which provides the required data. However, I have few images where there are no bboxes. I would like to know how to handle this situation? Do you handle it somewhere in the repo? https://github.com/tztztztztz/yolov2.pytorch/blob/014559ce4df8f7e580e339919a05a05d988073a4/loss.py#L89 I will have an issue in calculating iou when there are no bboxes in it.