ZeroDivisionError: division by zero

[tzj66]

When I run train_net.py， this problem happened.
This problem occurs when the dataloader is being built.
In builtin.py, when computing the ratio_bbox_below_vis_per_seq, there are many zeros in the denominator.

ratio_bbox_below_vis_per_seq = {
k: 100 * num_bbox_below_vis_per_seq[k] / (num_bbox_below_vis_per_seq[k] + sum_bbox_per_seq[k]) for k in
num_bbox_below_vis_per_seq.keys()}

I don't know what this variable means, or why this problem arises.

[HYUNJS]

This measures the ratio of objects whose visibility is very low. I don't think (num_bbox_below_vis_per_seq[k] + sum_bbox_per_seq[k]) could be zero since they are the number of objects in the video (=sequence). If your input video does not have any object, the problem would be occured. Please let me know if you have further questions.

[tzj66]

This measures the ratio of objects whose visibility is very low. I don't think (num_bbox_below_vis_per_seq[k] + sum_bbox_per_seq[k]) could be zero since they are the number of objects in the video (=sequence). If your input video does not have any object, the problem would be occured. Please let me know if you have further questions.

Thanks for your reply. I have solved this problem, and it was caused by my dataset MOT17. There are many other detector versions in the folder. When I downloaded the dataset from your link, the problem was solved, and I knew the reason.

[HYUNJS]

Good to hear that you solved the problem. Please let me know if you have other questions.