Reference for ultralytics/models/yolo/pose/predict.py

Bases: DetectionPredictor

              flowchart TD
              ultralytics.models.yolo.pose.predict.PosePredictor[PosePredictor]
              ultralytics.models.yolo.detect.predict.DetectionPredictor[DetectionPredictor]
              ultralytics.engine.predictor.BasePredictor[BasePredictor]

                              ultralytics.models.yolo.detect.predict.DetectionPredictor --> ultralytics.models.yolo.pose.predict.PosePredictor
                                ultralytics.engine.predictor.BasePredictor --> ultralytics.models.yolo.detect.predict.DetectionPredictor
                



              click ultralytics.models.yolo.pose.predict.PosePredictor href "" "ultralytics.models.yolo.pose.predict.PosePredictor"
              click ultralytics.models.yolo.detect.predict.DetectionPredictor href "" "ultralytics.models.yolo.detect.predict.DetectionPredictor"
              click ultralytics.engine.predictor.BasePredictor href "" "ultralytics.engine.predictor.BasePredictor"
            

A class extending the DetectionPredictor class for prediction based on a pose model.

This class specializes in pose estimation, handling keypoints detection alongside standard object detection capabilities inherited from DetectionPredictor.

Attributes:

Methods:

Examples:

>>> 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()

Sets up a PosePredictor instance, configuring it for pose detection tasks and handling device-specific warnings for Apple MPS.

Parameters:

Examples:

>>> 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()

28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52

def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """Initialize PosePredictor for pose estimation tasks.

    Sets up a PosePredictor instance, configuring it for pose detection tasks and handling device-specific warnings
    for Apple MPS.

    Args:
        cfg (Any): Configuration for the predictor.
        overrides (dict, optional): Configuration overrides that take precedence over cfg.
        _callbacks (list, optional): List of callback functions to be invoked during prediction.

    Examples:
        >>> 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()
    """
    super().__init__(cfg, overrides, _callbacks)
    self.args.task = "pose"
    if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
        LOGGER.warning(
            "Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
            "See https://github.com/ultralytics/ultralytics/issues/4031."
        )

construct_result(pred, img, orig_img, img_path)

54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77

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

    Extends the parent class implementation by extracting keypoint data from predictions and adding them to the
    result object.

    Args:
        pred (torch.Tensor): The predicted bounding boxes, scores, and keypoints with shape (N, 6+K*D) where N is
            the number of detections, K is the number of keypoints, and D is the keypoint dimension.
        img (torch.Tensor): The processed input image tensor with shape (B, C, H, W).
        orig_img (np.ndarray): The original unprocessed image as a numpy array.
        img_path (str): The path to the original image file.

    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)
    # Extract keypoints from prediction and reshape according to model's keypoint shape
    pred_kpts = pred[:, 6:].view(pred.shape[0], *self.model.kpt_shape)
    # Scale keypoints coordinates to match the original image dimensions
    pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, orig_img.shape)
    result.update(keypoints=pred_kpts)
    return result