What does spatial_size do in datapoints.BoundingBox()?

vision
1

I had thought that using spatial_size in BoundingBox() would cause clipping, but this code:

r = TVF2.convert_format_bounding_box(
        datapoints.BoundingBox(ltwh, format=datapoints.BoundingBoxFormat.XYWH, spatial_size=img_hw, ),
        new_format=datapoints.BoundingBoxFormat.XYXY,
    )

converts ltwh to xyxy regardless of the spatial size I give it. Does it only store it for usage down the pipeline?

Also, I see in the documentation that spatial_size is (h, w) whereas XYWH implies the reverse order, why is this not consistent? perhaps I’m missing something?

Thanks.