[weighted_box_fussion] - an alternative for `box_non_max_suppression`

Search before asking

• I have searched the Supervision issues and found no similar feature requests.

Description

Current object detection models removes overlapping boxes by nms which can reduce accuracy of the final results. It can be avoided by Weighted Box Fusion which can accepts all the prediction whether from a single model or multiple models.

Reference: Weighted Box Fusion
Original Implementation: ensemble-boxes

Use case

import supervision as sv

wbf = sv.WeightedBoxFusion()

res_a = model_a(image)
det_a = sv.Detection(res_a)

res_b = model_b(image)
det_b = sv.Detection(res_b)

wbf_detections = wbf([det_a, det_b])

Additional

class WeightedBoxFusion:

	def __init__(self):
		pass
	
	def __call__(self, detections: Union[Detections, List[Detections]]) -> Detections:
		pass
		result_detections = Detections(...)
		return result_detections 

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!