Class Visualizer

preprocess/oneformer_code/demo/visualizer.py:343–1354

Visualizer that draws data about detection/segmentation on images. It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}` that draw primitive objects to images, as well as high-level wrappers like `draw_{instance_predictions,sem_seg,panoptic_seg_predictions,datas

class Visualizer:
    """
    Visualizer that draws data about detection/segmentation on images.
    It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}`
    that draw primitive objects to images, as well as high-level wrappers like
    `draw_{instance_predictions,sem_seg,panoptic_seg_predictions,dataset_dict}`
    that draw composite data in some pre-defined style.
    Note that the exact visualization style for the high-level wrappers are subject to change.
    Style such as color, opacity, label contents, visibility of labels, or even the visibility
    of objects themselves (e.g. when the object is too small) may change according
    to different heuristics, as long as the results still look visually reasonable.
    To obtain a consistent style, you can implement custom drawing functions with the
    abovementioned primitive methods instead. If you need more customized visualization
    styles, you can process the data yourself following their format documented in
    tutorials (:doc:`/tutorials/models`, :doc:`/tutorials/datasets`). This class does not
    intend to satisfy everyone's preference on drawing styles.
    This visualizer focuses on high rendering quality rather than performance. It is not
    designed to be used for real-time applications.
    """

    # TODO implement a fast, rasterized version using OpenCV

    def __init__(self, img_rgb, is_img=True, metadata=None, scale=1.0, instance_mode=ColorMode.IMAGE):
        """
        Args:
            img_rgb: a numpy array of shape (H, W, C), where H and W correspond to
                the height and width of the image respectively. C is the number of
                color channels. The image is required to be in RGB format since that
                is a requirement of the Matplotlib library. The image is also expected
                to be in the range [0, 255].
            metadata (Metadata): dataset metadata (e.g. class names and colors)
            instance_mode (ColorMode): defines one of the pre-defined style for drawing
                instances on an image.
        """
        if is_img:
            self.img = np.asarray(img_rgb).clip(0, 255).astype(np.uint8)
        else:
            self.img = np.zeros_like(img_rgb).clip(0, 255).astype(np.uint8)
        if metadata is None:
            metadata = MetadataCatalog.get("__nonexist__")
        self.metadata = metadata
        self.output = VisImage(self.img, scale=scale)
        self.cpu_device = torch.device("cpu")

        # too small texts are useless, therefore clamp to 9
        self._default_font_size = max(
            np.sqrt(self.output.height * self.output.width) // 90, 10 // scale
        )
        self._instance_mode = instance_mode
        self.keypoint_threshold = _KEYPOINT_THRESHOLD

    def get_image(self, img):
        img = np.asarray(img).clip(0, 255).astype(np.uint8)
        return VisImage(img, scale=1.0)
    
    def draw_box_predictions(
        self,
        boxes=None,