Ultralytics YOLO Format

Support for Ultralytics YOLO pose format.

sleap_io.io.main.load_ultralytics(dataset_path, split='train', skeleton=None, **kwargs)

Load an Ultralytics YOLO pose dataset as a SLEAP Labels object.

Parameters:

Name	Type	Description	Default
dataset_path	str	Path to the Ultralytics dataset root directory containing data.yaml.	required
split	str	Dataset split to read ('train', 'val', or 'test'). Defaults to 'train'.	'train'
skeleton	Skeleton | None	Optional skeleton to use. If not provided, will be inferred from data.yaml.	None
**kwargs		Additional arguments passed to ultralytics.read_labels. Currently supports: - image_size: Tuple of (height, width) for coordinate denormalization. Defaults to (480, 640). Will attempt to infer from actual images if available.	required

Returns:

Type	Description
Labels	The dataset as a Labels object.

Source code in sleap_io/io/main.py

def load_ultralytics(
    dataset_path: str,
    split: str = "train",
    skeleton: Skeleton | None = None,
    **kwargs,
) -> Labels:
    """Load an Ultralytics YOLO pose dataset as a SLEAP `Labels` object.

    Args:
        dataset_path: Path to the Ultralytics dataset root directory containing
            data.yaml.
        split: Dataset split to read ('train', 'val', or 'test'). Defaults to 'train'.
        skeleton: Optional skeleton to use. If not provided, will be inferred from
            data.yaml.
        **kwargs: Additional arguments passed to `ultralytics.read_labels`.
            Currently supports:
            - image_size: Tuple of (height, width) for coordinate denormalization.
              Defaults to
              (480, 640). Will attempt to infer from actual images if available.

    Returns:
        The dataset as a `Labels` object.
    """
    from sleap_io.io import ultralytics

    return ultralytics.read_labels(
        dataset_path, split=split, skeleton=skeleton, **kwargs
    )

sleap_io.io.main.save_ultralytics(labels, dataset_path, split_ratios={'train': 0.8, 'val': 0.2}, **kwargs)

Save a SLEAP dataset to Ultralytics YOLO pose format.

Parameters:

Name	Type	Description	Default
labels	Labels	A SLEAP Labels object.	required
dataset_path	str	Path to save the Ultralytics dataset.	required
split_ratios	dict	Dictionary mapping split names to ratios (must sum to 1.0). Defaults to {"train": 0.8, "val": 0.2}.	{'train': 0.8, 'val': 0.2}
**kwargs		Additional arguments passed to ultralytics.write_labels. Currently supports: - class_id: Class ID to use for all instances (default: 0). - image_format: Image format to use for saving frames. Either "png" (default, lossless) or "jpg". - image_quality: Image quality for JPEG format (1-100). For PNG, this is the compression level (0-9). If None, uses default quality settings. - verbose: If True (default), show progress bars during export. - use_multiprocessing: If True, use multiprocessing for parallel image saving. Default is False. - n_workers: Number of worker processes. If None, uses CPU count - 1. Only used if use_multiprocessing=True.	required

Source code in sleap_io/io/main.py

def save_ultralytics(
    labels: Labels,
    dataset_path: str,
    split_ratios: dict = {"train": 0.8, "val": 0.2},
    **kwargs,
):
    """Save a SLEAP dataset to Ultralytics YOLO pose format.

    Args:
        labels: A SLEAP `Labels` object.
        dataset_path: Path to save the Ultralytics dataset.
        split_ratios: Dictionary mapping split names to ratios (must sum to 1.0).
                     Defaults to {"train": 0.8, "val": 0.2}.
        **kwargs: Additional arguments passed to `ultralytics.write_labels`.
            Currently supports:
            - class_id: Class ID to use for all instances (default: 0).
            - image_format: Image format to use for saving frames. Either "png"
              (default, lossless) or "jpg".
            - image_quality: Image quality for JPEG format (1-100). For PNG, this is
              the compression
              level (0-9). If None, uses default quality settings.
            - verbose: If True (default), show progress bars during export.
            - use_multiprocessing: If True, use multiprocessing for parallel image
              saving. Default is False.
            - n_workers: Number of worker processes. If None, uses CPU count - 1.
              Only used if
              use_multiprocessing=True.
    """
    from sleap_io.io import ultralytics

    ultralytics.write_labels(labels, dataset_path, split_ratios=split_ratios, **kwargs)