what inputs you will provide, if any: normal document image(+weird shaped, stretched image)
what outputs you are expecting: Object detection with Polygon shape(x1, y1, x2, y2, x3, y3, x4, y4)
Hi, I'm beginner of DETR. I knew the DETR return format is (x, y, w, h).
Is there any way to get the polygon shaped bbox?
❓ How to do something using DETR
Describe what you want to do, including:
what inputs you will provide, if any: normal document image(+weird shaped, stretched image)
what outputs you are expecting: Object detection with Polygon shape(x1, y1, x2, y2, x3, y3, x4, y4) Hi, I'm beginner of DETR. I knew the DETR return format is (x, y, w, h). Is there any way to get the polygon shaped bbox?