[A Bug?] The diffused boxes as input may have negative coordinates.

[YTEP-ZHI]

DiffusionDet/diffusiondet/detector.py

Lines 400 to 403 in 1efb36d

	x = torch.clamp(x, min=-1 * self.scale, max=self.scale)
	x = ((x / self.scale) + 1) / 2.
	diff_boxes = box_cxcywh_to_xyxy(x)

Though you clamped the coordinates (x) at line400, they may become negative number when converted from (cx, cy, w, h) to (x, y, x, y) mode. Here is an example:

It happens when cx or cy is close to zero (or clamped to zero), if conducting cx - w/2 or cy - h/2, it becomes negative number.

Is it acceptable to pass the negative coordinates to the RCNN head? Will it cause any unexpected behavior extracting roi feature?

[ShoufaChen]

Hi,

Thanks for your interest.

Yes, the RCNN head can accept negative coordinates.

[YTEP-ZHI]

Thanks for your reply.