predicted boxes are weird(x1=x2, y1=y2)

[HyunjiEllenPak]

Hi, I had trained FCOS model on my own dataset and I evaluate the model using the modified coco_eval.py The performance is very low but the predicted boxes are weird. They are all boxes such that x1 and x2 are same and y1 and y2 are same. Why the predictions are almost points, not boxes? Could you give me some advices?