dgs.models.similarity.pose_similarity.IntersectionOverUnion.forward

IntersectionOverUnion.forward(data: State, target: State) → torch.Tensor[source]

Given two states containing bounding-boxes, compute the intersection over union between each pair.

Parameters:

  • data – A State object containing the detected bounding-boxes. Size N

  • target – A State object containing the target bounding-boxes. Size T

Returns:

A (Float)Tensor of shape [N x T] with values in [0..1]. If requested, the softmax is computed along the -1 dimension, resulting in probability distributions for each value of the input data.