Skip to content

Incorrect BoundingBoxes format conversion CXCYWH -> XYXY #8887

Open
@NicolasHug

Description

@NicolasHug

Thanks to @AntoineSimoulin for uncovering this issue in 5321f23

old_format = tv_tensors.BoundingBoxFormat.CXCYWH
new_format = tv_tensors.BoundingBoxFormat.XYXY

dtype = torch.int64
fn_type = "functional"
device = torch.device("cpu")


# bounding_boxes = make_bounding_boxes(format=old_format, dtype=dtype, device=device)
bounding_boxes = tv_tensors.BoundingBoxes([[ 5,  6, 10, 13]], format=tv_tensors.BoundingBoxFormat.CXCYWH, canvas_size=(17, 11))

if fn_type == "functional":
    fn = functools.partial(F.convert_bounding_box_format, new_format=new_format)
else:
    fn = transforms.ConvertBoundingBoxFormat(format=new_format)

actual = fn(bounding_boxes)
expected = _reference_convert_bounding_box_format(bounding_boxes, new_format)

assert_equal(actual, expected)

Gives:

BoundingBoxes([[ 0, -1, 10, 12]], format=BoundingBoxFormat.XYXY, canvas_size=(17, 11))
BoundingBoxes([[ 0,  0, 10, 12]], format=BoundingBoxFormat.XYXY, canvas_size=(17, 11))

The -1 part is clearly wrong. Maybe an easy fix is to call max(0, ...) at some point but I haven't looked into it yet.

cc @vfdev-5

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions