ultralytics/models/yolo/pose/predict.py

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

from ultralytics.models.yolo.detect.predict import DetectionPredictor
from ultralytics.utils import DEFAULT_CFG, LOGGER, ops


class PosePredictor(DetectionPredictor):
    """
    A class extending the DetectionPredictor class for prediction based on a pose model.

    Example:
        ```python
        from ultralytics.utils import ASSETS
        from ultralytics.models.yolo.pose import PosePredictor

        args = dict(model="yolo11n-pose.pt", source=ASSETS)
        predictor = PosePredictor(overrides=args)
        predictor.predict_cli()
        ```
    """

    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
        """Initializes PosePredictor, sets task to 'pose' and logs a warning for using 'mps' as device."""
        super().__init__(cfg, overrides, _callbacks)
        self.args.task = "pose"
        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
            LOGGER.warning(
                "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
                "See https://github.com/ultralytics/ultralytics/issues/4031."
            )

    def construct_result(self, pred, img, orig_img, img_path):
        """
        Constructs the result object from the prediction.

        Args:
            pred (torch.Tensor): The predicted bounding boxes, scores, and keypoints.
            img (torch.Tensor): The image after preprocessing.
            orig_img (np.ndarray): The original image before preprocessing.
            img_path (str): The path to the original image.

        Returns:
            (Results): The result object containing the original image, image path, class names, bounding boxes, and keypoints.
        """
        result = super().construct_result(pred, img, orig_img, img_path)
        pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:]
        pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, orig_img.shape)
        result.update(keypoints=pred_kpts)
        return result