Reference for ultralytics/models/yolo/world/train_world.py

def build_dataset(self, img_path, mode="train", batch=None):
    """
    Build YOLO Dataset for training or validation.

    This method constructs appropriate datasets based on the mode and input paths, handling both
    standard YOLO datasets and grounding datasets with different formats.

    Args:
        img_path (List[str] | str): Path to the folder containing images or list of paths.
        mode (str): 'train' mode or 'val' mode, allowing customized augmentations for each mode.
        batch (int, optional): Size of batches, used for rectangular training/validation.

    Returns:
        (YOLOConcatDataset | Dataset): The constructed dataset for training or validation.
    """
    gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
    if mode != "train":
        return build_yolo_dataset(self.args, img_path, batch, self.data, mode=mode, rect=mode == "val", stride=gs)
    dataset = [
        build_yolo_dataset(self.args, im_path, batch, self.data, stride=gs, multi_modal=True)
        if isinstance(im_path, str)
        else build_grounding(self.args, im_path["img_path"], im_path["json_file"], batch, stride=gs)
        for im_path in img_path
    ]
    return YOLOConcatDataset(dataset) if len(dataset) > 1 else dataset[0]

def final_eval(self):
    """
    Perform final evaluation and validation for the YOLO-World model.

    Configures the validator with appropriate dataset and split information before running evaluation.

    Returns:
        (dict): Dictionary containing evaluation metrics and results.
    """
    val = self.args.data["val"]["yolo_data"][0]
    self.validator.args.data = val
    self.validator.args.split = "minival" if isinstance(val, str) and "lvis" in val else "val"
    return super().final_eval()

def get_dataset(self):
    """
    Get train and validation paths from data dictionary.

    Processes the data configuration to extract paths for training and validation datasets,
    handling both YOLO detection datasets and grounding datasets.

    Returns:
        (str): Train dataset path.
        (str): Validation dataset path.

    Raises:
        AssertionError: If train or validation datasets are not found, or if validation has multiple datasets.
    """
    final_data = {}
    data_yaml = self.args.data
    assert data_yaml.get("train", False), "train dataset not found"  # object365.yaml
    assert data_yaml.get("val", False), "validation dataset not found"  # lvis.yaml
    data = {k: [check_det_dataset(d) for d in v.get("yolo_data", [])] for k, v in data_yaml.items()}
    assert len(data["val"]) == 1, f"Only support validating on 1 dataset for now, but got {len(data['val'])}."
    val_split = "minival" if "lvis" in data["val"][0]["val"] else "val"
    for d in data["val"]:
        if d.get("minival") is None:  # for lvis dataset
            continue
        d["minival"] = str(d["path"] / d["minival"])
    for s in ["train", "val"]:
        final_data[s] = [d["train" if s == "train" else val_split] for d in data[s]]
        # save grounding data if there's one
        grounding_data = data_yaml[s].get("grounding_data")
        if grounding_data is None:
            continue
        grounding_data = grounding_data if isinstance(grounding_data, list) else [grounding_data]
        for g in grounding_data:
            assert isinstance(g, dict), f"Grounding data should be provided in dict format, but got {type(g)}"
        final_data[s] += grounding_data
    # NOTE: to make training work properly, set `nc` and `names`
    final_data["nc"] = data["val"][0]["nc"]
    final_data["names"] = data["val"][0]["names"]
    self.data = final_data
    return final_data["train"], final_data["val"][0]

def plot_training_labels(self):
    """Do not plot labels for YOLO-World training."""
    pass