コード例 #1
0
def annotations_to_instances_rotated(annos, image_size):
    """
    Create an :class:`Instances` object used by the models,
    from instance annotations in the dataset dict.
    Compared to `annotations_to_instances`, this function is for rotated boxes only

    Args:
        annos (list[dict]): a list of instance annotations in one image, each
            element for one instance.
        image_size (tuple): height, width

    Returns:
        Instances:
            Containing fields "gt_boxes", "gt_classes",
            if they can be obtained from `annos`.
            This is the format that builtin models expect.
    """
    boxes = [obj["bbox"] for obj in annos]
    target = Instances(image_size)
    boxes = target.gt_boxes = RotatedBoxes(boxes)
    boxes.clip(image_size)

    classes = [obj["category_id"] for obj in annos]
    classes = torch.tensor(classes, dtype=torch.int64)
    target.gt_classes = classes

    return target
コード例 #2
0
def annotations_to_instances(annos, image_size, mask_format="polygon"):
    """
    Create an :class:`Instances` object used by the models,
    from instance annotations in the dataset dict.

    Args:
        annos (list[dict]): a list of instance annotations in one image, each
            element for one instance.
        image_size (tuple): height, width

    Returns:
        Instances:
            It will contain fields "gt_boxes", "gt_classes",
            "gt_masks", "gt_keypoints", if they can be obtained from `annos`.
            This is the format that builtin models expect.
    """
    boxes = [BoxMode.convert(obj["bbox"], obj["bbox_mode"], BoxMode.XYXY_ABS) for obj in annos]
    target = Instances(image_size)
    boxes = target.gt_boxes = Boxes(boxes)
    boxes.clip(image_size)

    classes = [obj["category_id"] for obj in annos]
    classes = torch.tensor(classes, dtype=torch.int64)
    target.gt_classes = classes

    if len(annos) and "segmentation" in annos[0]:
        polygons = [obj["segmentation"] for obj in annos]
        if mask_format == "polygon":
            masks = PolygonMasks(polygons)
        else:
            assert mask_format == "bitmask", mask_format
            masks = BitMasks.from_polygon_masks(polygons, *image_size)
        target.gt_masks = masks

    if len(annos) and "keypoints" in annos[0]:
        kpts = [obj.get("keypoints", []) for obj in annos]
        target.gt_keypoints = Keypoints(kpts)

    return target