在detectron2中，如何在对象检测中仅在没有标签(类名)的图像上绘制边界？

from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog

cfg = get_cfg()
cfg.merge_from_file("path/to/config.yaml")
cfg.MODEL.WEIGHTS = "path/to/model_weights.pth"

predictor = DefaultPredictor(cfg)

image = cv2.imread("path/to/image.jpg")

outputs = predictor(image)

boxes = outputs["instances"].pred_boxes.tensor.cpu().numpy()
labels = outputs["instances"].pred_classes.cpu().numpy()

metadata = MetadataCatalog.get(cfg.DATASETS.TEST[0])
visualizer = Visualizer(image[:, :, ::-1], metadata=metadata, scale=1.0)
visualizer = visualizer.draw_box(boxes, edge_color='red', line_style='--')

output_image = visualizer.get_image()[:, :, ::-1]

cv2.imshow("Object Detection", output_image)
cv2.waitKey(0)
cv2.destroyAllWindows()