dgenerate-ultralytics-headless 8.3.222__py3-none-any.whl → 8.3.225__py3-none-any.whl

ultralytics/models/yolo/pose/train.py

@@ -12,8 +12,7 @@ from ultralytics.utils import DEFAULT_CFG, LOGGER
 
 
 class PoseTrainer(yolo.detect.DetectionTrainer):
-    """
-    A class extending the DetectionTrainer class for training YOLO pose estimation models.
+    """A class extending the DetectionTrainer class for training YOLO pose estimation models.
 
     This trainer specializes in handling pose estimation tasks, managing model training, validation, and visualization
     of pose keypoints alongside bounding boxes.
@@ -39,8 +38,7 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides: dict[str, Any] | None = None, _callbacks=None):
-        """
-        Initialize a PoseTrainer object for training YOLO pose estimation models.
+        """Initialize a PoseTrainer object for training YOLO pose estimation models.
 
         Args:
             cfg (dict, optional): Default configuration dictionary containing training parameters.
@@ -68,8 +66,7 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
         weights: str | Path | None = None,
         verbose: bool = True,
     ) -> PoseModel:
-        """
-        Get pose estimation model with specified configuration and weights.
+        """Get pose estimation model with specified configuration and weights.
 
         Args:
             cfg (str | Path | dict, optional): Model configuration file path or dictionary.
@@ -105,8 +102,7 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
         )
 
     def get_dataset(self) -> dict[str, Any]:
-        """
-        Retrieve the dataset and ensure it contains the required `kpt_shape` key.
+        """Retrieve the dataset and ensure it contains the required `kpt_shape` key.
 
         Returns:
             (dict): A dictionary containing the training/validation/test dataset and category names.

ultralytics/models/yolo/pose/val.py

@@ -14,11 +14,10 @@ from ultralytics.utils.metrics import OKS_SIGMA, PoseMetrics, kpt_iou
 
 
 class PoseValidator(DetectionValidator):
-    """
-    A class extending the DetectionValidator class for validation based on a pose model.
+    """A class extending the DetectionValidator class for validation based on a pose model.
 
-    This validator is specifically designed for pose estimation tasks, handling keypoints and implementing
-    specialized metrics for pose evaluation.
+    This validator is specifically designed for pose estimation tasks, handling keypoints and implementing specialized
+    metrics for pose evaluation.
 
     Attributes:
         sigma (np.ndarray): Sigma values for OKS calculation, either OKS_SIGMA or ones divided by number of keypoints.
@@ -33,8 +32,8 @@ class PoseValidator(DetectionValidator):
         _prepare_batch: Prepare a batch for processing by converting keypoints to float and scaling to original
             dimensions.
         _prepare_pred: Prepare and scale keypoints in predictions for pose processing.
-        _process_batch: Return correct prediction matrix by computing Intersection over Union (IoU) between
-            detections and ground truth.
+        _process_batch: Return correct prediction matrix by computing Intersection over Union (IoU) between detections
+            and ground truth.
         plot_val_samples: Plot and save validation set samples with ground truth bounding boxes and keypoints.
         plot_predictions: Plot and save model predictions with bounding boxes and keypoints.
         save_one_txt: Save YOLO pose detections to a text file in normalized coordinates.
@@ -49,8 +48,7 @@ class PoseValidator(DetectionValidator):
     """
 
     def __init__(self, dataloader=None, save_dir=None, args=None, _callbacks=None) -> None:
-        """
-        Initialize a PoseValidator object for pose estimation validation.
+        """Initialize a PoseValidator object for pose estimation validation.
 
         This validator is specifically designed for pose estimation tasks, handling keypoints and implementing
         specialized metrics for pose evaluation.
@@ -106,8 +104,7 @@ class PoseValidator(DetectionValidator):
         )
 
     def init_metrics(self, model: torch.nn.Module) -> None:
-        """
-        Initialize evaluation metrics for YOLO pose validation.
+        """Initialize evaluation metrics for YOLO pose validation.
 
         Args:
             model (torch.nn.Module): Model to validate.
@@ -119,17 +116,15 @@ class PoseValidator(DetectionValidator):
         self.sigma = OKS_SIGMA if is_pose else np.ones(nkpt) / nkpt
 
     def postprocess(self, preds: torch.Tensor) -> dict[str, torch.Tensor]:
-        """
-        Postprocess YOLO predictions to extract and reshape keypoints for pose estimation.
+        """Postprocess YOLO predictions to extract and reshape keypoints for pose estimation.
 
-        This method extends the parent class postprocessing by extracting keypoints from the 'extra'
-        field of predictions and reshaping them according to the keypoint shape configuration.
-        The keypoints are reshaped from a flattened format to the proper dimensional structure
-        (typically [N, 17, 3] for COCO pose format).
+        This method extends the parent class postprocessing by extracting keypoints from the 'extra' field of
+        predictions and reshaping them according to the keypoint shape configuration. The keypoints are reshaped from a
+        flattened format to the proper dimensional structure (typically [N, 17, 3] for COCO pose format).
 
         Args:
-            preds (torch.Tensor): Raw prediction tensor from the YOLO pose model containing
-                bounding boxes, confidence scores, class predictions, and keypoint data.
+            preds (torch.Tensor): Raw prediction tensor from the YOLO pose model containing bounding boxes, confidence
+                scores, class predictions, and keypoint data.
 
         Returns:
             (dict[torch.Tensor]): Dict of processed prediction dictionaries, each containing:
@@ -138,10 +133,10 @@ class PoseValidator(DetectionValidator):
                 - 'cls': Class predictions
                 - 'keypoints': Reshaped keypoint coordinates with shape (-1, *self.kpt_shape)
 
-        Note:
-            If no keypoints are present in a prediction (empty keypoints), that prediction
-            is skipped and continues to the next one. The keypoints are extracted from the
-            'extra' field which contains additional task-specific data beyond basic detection.
+        Notes:
+            If no keypoints are present in a prediction (empty keypoints), that prediction is skipped and continues
+            to the next one. The keypoints are extracted from the 'extra' field which contains additional
+            task-specific data beyond basic detection.
         """
         preds = super().postprocess(preds)
         for pred in preds:
@@ -149,8 +144,7 @@ class PoseValidator(DetectionValidator):
         return preds
 
     def _prepare_batch(self, si: int, batch: dict[str, Any]) -> dict[str, Any]:
-        """
-        Prepare a batch for processing by converting keypoints to float and scaling to original dimensions.
+        """Prepare a batch for processing by converting keypoints to float and scaling to original dimensions.
 
         Args:
             si (int): Batch index.
@@ -173,18 +167,18 @@ class PoseValidator(DetectionValidator):
         return pbatch
 
     def _process_batch(self, preds: dict[str, torch.Tensor], batch: dict[str, Any]) -> dict[str, np.ndarray]:
-        """
-        Return correct prediction matrix by computing Intersection over Union (IoU) between detections and ground truth.
+        """Return correct prediction matrix by computing Intersection over Union (IoU) between detections and ground
+        truth.
 
         Args:
             preds (dict[str, torch.Tensor]): Dictionary containing prediction data with keys 'cls' for class predictions
                 and 'keypoints' for keypoint predictions.
-            batch (dict[str, Any]): Dictionary containing ground truth data with keys 'cls' for class labels,
-                'bboxes' for bounding boxes, and 'keypoints' for keypoint annotations.
+            batch (dict[str, Any]): Dictionary containing ground truth data with keys 'cls' for class labels, 'bboxes'
+                for bounding boxes, and 'keypoints' for keypoint annotations.
 
         Returns:
-            (dict[str, np.ndarray]): Dictionary containing the correct prediction matrix including 'tp_p' for pose
-                true positives across 10 IoU levels.
+            (dict[str, np.ndarray]): Dictionary containing the correct prediction matrix including 'tp_p' for pose true
+                positives across 10 IoU levels.
 
         Notes:
             `0.53` scale factor used in area computation is referenced from
@@ -203,11 +197,10 @@ class PoseValidator(DetectionValidator):
         return tp
 
     def save_one_txt(self, predn: dict[str, torch.Tensor], save_conf: bool, shape: tuple[int, int], file: Path) -> None:
-        """
-        Save YOLO pose detections to a text file in normalized coordinates.
+        """Save YOLO pose detections to a text file in normalized coordinates.
 
         Args:
-            predn (dict[str, torch.Tensor]): Dictionary containing predictions with keys 'bboxes', 'conf', 'cls' and 'keypoints.
+            predn (dict[str, torch.Tensor]): Prediction dict with keys 'bboxes', 'conf', 'cls' and 'keypoints.
             save_conf (bool): Whether to save confidence scores.
             shape (tuple[int, int]): Shape of the original image (height, width).
             file (Path): Output file path to save detections.
@@ -227,15 +220,14 @@ class PoseValidator(DetectionValidator):
         ).save_txt(file, save_conf=save_conf)
 
     def pred_to_json(self, predn: dict[str, torch.Tensor], pbatch: dict[str, Any]) -> None:
-        """
-        Convert YOLO predictions to COCO JSON format.
+        """Convert YOLO predictions to COCO JSON format.
 
-        This method takes prediction tensors and a filename, converts the bounding boxes from YOLO format
-        to COCO format, and appends the results to the internal JSON dictionary (self.jdict).
+        This method takes prediction tensors and a filename, converts the bounding boxes from YOLO format to COCO
+        format, and appends the results to the internal JSON dictionary (self.jdict).
 
         Args:
-            predn (dict[str, torch.Tensor]): Prediction dictionary containing 'bboxes', 'conf', 'cls',
-                and 'keypoints' tensors.
+            predn (dict[str, torch.Tensor]): Prediction dictionary containing 'bboxes', 'conf', 'cls', and 'keypoints'
+                tensors.
             pbatch (dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'.
 
         Notes:

ultralytics/models/yolo/segment/predict.py

@@ -6,8 +6,7 @@ from ultralytics.utils import DEFAULT_CFG, ops
 
 
 class SegmentationPredictor(DetectionPredictor):
-    """
-    A class extending the DetectionPredictor class for prediction based on a segmentation model.
+    """A class extending the DetectionPredictor class for prediction based on a segmentation model.
 
     This class specializes in processing segmentation model outputs, handling both bounding boxes and masks in the
     prediction results.
@@ -31,8 +30,7 @@ class SegmentationPredictor(DetectionPredictor):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
-        """
-        Initialize the SegmentationPredictor with configuration, overrides, and callbacks.
+        """Initialize the SegmentationPredictor with configuration, overrides, and callbacks.
 
         This class specializes in processing segmentation model outputs, handling both bounding boxes and masks in the
         prediction results.
@@ -46,8 +44,7 @@ class SegmentationPredictor(DetectionPredictor):
         self.args.task = "segment"
 
     def postprocess(self, preds, img, orig_imgs):
-        """
-        Apply non-max suppression and process segmentation detections for each image in the input batch.
+        """Apply non-max suppression and process segmentation detections for each image in the input batch.
 
         Args:
             preds (tuple): Model predictions, containing bounding boxes, scores, classes, and mask coefficients.
@@ -55,8 +52,8 @@ class SegmentationPredictor(DetectionPredictor):
             orig_imgs (list | torch.Tensor | np.ndarray): Original image or batch of images.
 
         Returns:
-            (list): List of Results objects containing the segmentation predictions for each image in the batch.
-                Each Results object includes both bounding boxes and segmentation masks.
+            (list): List of Results objects containing the segmentation predictions for each image in the batch. Each
+                Results object includes both bounding boxes and segmentation masks.
 
         Examples:
             >>> predictor = SegmentationPredictor(overrides=dict(model="yolo11n-seg.pt"))
@@ -67,8 +64,7 @@ class SegmentationPredictor(DetectionPredictor):
         return super().postprocess(preds[0], img, orig_imgs, protos=protos)
 
     def construct_results(self, preds, img, orig_imgs, protos):
-        """
-        Construct a list of result objects from the predictions.
+        """Construct a list of result objects from the predictions.
 
         Args:
             preds (list[torch.Tensor]): List of predicted bounding boxes, scores, and masks.
@@ -77,8 +73,8 @@ class SegmentationPredictor(DetectionPredictor):
             protos (list[torch.Tensor]): List of prototype masks.
 
         Returns:
-            (list[Results]): List of result objects containing the original images, image paths, class names,
-                bounding boxes, and masks.
+            (list[Results]): List of result objects containing the original images, image paths, class names, bounding
+                boxes, and masks.
         """
         return [
             self.construct_result(pred, img, orig_img, img_path, proto)
@@ -86,8 +82,7 @@ class SegmentationPredictor(DetectionPredictor):
         ]
 
     def construct_result(self, pred, img, orig_img, img_path, proto):
-        """
-        Construct a single result object from the prediction.
+        """Construct a single result object from the prediction.
 
         Args:
             pred (torch.Tensor): The predicted bounding boxes, scores, and masks.

ultralytics/models/yolo/segment/train.py

@@ -11,8 +11,7 @@ from ultralytics.utils import DEFAULT_CFG, RANK
 
 
 class SegmentationTrainer(yolo.detect.DetectionTrainer):
-    """
-    A class extending the DetectionTrainer class for training based on a segmentation model.
+    """A class extending the DetectionTrainer class for training based on a segmentation model.
 
     This trainer specializes in handling segmentation tasks, extending the detection trainer with segmentation-specific
     functionality including model initialization, validation, and visualization.
@@ -28,8 +27,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides: dict | None = None, _callbacks=None):
-        """
-        Initialize a SegmentationTrainer object.
+        """Initialize a SegmentationTrainer object.
 
         Args:
             cfg (dict): Configuration dictionary with default training settings.
@@ -42,8 +40,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         super().__init__(cfg, overrides, _callbacks)
 
     def get_model(self, cfg: dict | str | None = None, weights: str | Path | None = None, verbose: bool = True):
-        """
-        Initialize and return a SegmentationModel with specified configuration and weights.
+        """Initialize and return a SegmentationModel with specified configuration and weights.
 
         Args:
             cfg (dict | str, optional): Model configuration. Can be a dictionary, a path to a YAML file, or None.

ultralytics/models/yolo/segment/val.py

@@ -17,11 +17,10 @@ from ultralytics.utils.metrics import SegmentMetrics, mask_iou
 
 
 class SegmentationValidator(DetectionValidator):
-    """
-    A class extending the DetectionValidator class for validation based on a segmentation model.
+    """A class extending the DetectionValidator class for validation based on a segmentation model.
 
-    This validator handles the evaluation of segmentation models, processing both bounding box and mask predictions
-    to compute metrics such as mAP for both detection and segmentation tasks.
+    This validator handles the evaluation of segmentation models, processing both bounding box and mask predictions to
+    compute metrics such as mAP for both detection and segmentation tasks.
 
     Attributes:
         plot_masks (list): List to store masks for plotting.
@@ -38,8 +37,7 @@ class SegmentationValidator(DetectionValidator):
     """
 
     def __init__(self, dataloader=None, save_dir=None, args=None, _callbacks=None) -> None:
-        """
-        Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics.
+        """Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics.
 
         Args:
             dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation.
@@ -53,8 +51,7 @@ class SegmentationValidator(DetectionValidator):
         self.metrics = SegmentMetrics()
 
     def preprocess(self, batch: dict[str, Any]) -> dict[str, Any]:
-        """
-        Preprocess batch of images for YOLO segmentation validation.
+        """Preprocess batch of images for YOLO segmentation validation.
 
         Args:
             batch (dict[str, Any]): Batch containing images and annotations.
@@ -67,8 +64,7 @@ class SegmentationValidator(DetectionValidator):
         return batch
 
     def init_metrics(self, model: torch.nn.Module) -> None:
-        """
-        Initialize metrics and select mask processing function based on save_json flag.
+        """Initialize metrics and select mask processing function based on save_json flag.
 
         Args:
             model (torch.nn.Module): Model to validate.
@@ -96,8 +92,7 @@ class SegmentationValidator(DetectionValidator):
         )
 
     def postprocess(self, preds: list[torch.Tensor]) -> list[dict[str, torch.Tensor]]:
-        """
-        Post-process YOLO predictions and return output detections with proto.
+        """Post-process YOLO predictions and return output detections with proto.
 
         Args:
             preds (list[torch.Tensor]): Raw predictions from the model.
@@ -122,8 +117,7 @@ class SegmentationValidator(DetectionValidator):
         return preds
 
     def _prepare_batch(self, si: int, batch: dict[str, Any]) -> dict[str, Any]:
-        """
-        Prepare a batch for training or inference by processing images and targets.
+        """Prepare a batch for training or inference by processing images and targets.
 
         Args:
             si (int): Batch index.
@@ -149,8 +143,7 @@ class SegmentationValidator(DetectionValidator):
         return prepared_batch
 
     def _process_batch(self, preds: dict[str, torch.Tensor], batch: dict[str, Any]) -> dict[str, np.ndarray]:
-        """
-        Compute correct prediction matrix for a batch based on bounding boxes and optional masks.
+        """Compute correct prediction matrix for a batch based on bounding boxes and optional masks.
 
         Args:
             preds (dict[str, torch.Tensor]): Dictionary containing predictions with keys like 'cls' and 'masks'.
@@ -159,14 +152,14 @@ class SegmentationValidator(DetectionValidator):
         Returns:
             (dict[str, np.ndarray]): A dictionary containing correct prediction matrices including 'tp_m' for mask IoU.
 
-        Notes:
-            - If `masks` is True, the function computes IoU between predicted and ground truth masks.
-            - If `overlap` is True and `masks` is True, overlapping masks are taken into account when computing IoU.
-
         Examples:
             >>> preds = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)}
             >>> batch = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)}
             >>> correct_preds = validator._process_batch(preds, batch)
+
+        Notes:
+            - If `masks` is True, the function computes IoU between predicted and ground truth masks.
+            - If `overlap` is True and `masks` is True, overlapping masks are taken into account when computing IoU.
         """
         tp = super()._process_batch(preds, batch)
         gt_cls = batch["cls"]
@@ -179,8 +172,7 @@ class SegmentationValidator(DetectionValidator):
         return tp
 
     def plot_predictions(self, batch: dict[str, Any], preds: list[dict[str, torch.Tensor]], ni: int) -> None:
-        """
-        Plot batch predictions with masks and bounding boxes.
+        """Plot batch predictions with masks and bounding boxes.
 
         Args:
             batch (dict[str, Any]): Batch containing images and annotations.
@@ -195,8 +187,7 @@ class SegmentationValidator(DetectionValidator):
         super().plot_predictions(batch, preds, ni, max_det=self.args.max_det)  # plot bboxes
 
     def save_one_txt(self, predn: torch.Tensor, save_conf: bool, shape: tuple[int, int], file: Path) -> None:
-        """
-        Save YOLO detections to a txt file in normalized coordinates in a specific format.
+        """Save YOLO detections to a txt file in normalized coordinates in a specific format.
 
         Args:
             predn (torch.Tensor): Predictions in the format (x1, y1, x2, y2, conf, class).
@@ -215,8 +206,7 @@ class SegmentationValidator(DetectionValidator):
         ).save_txt(file, save_conf=save_conf)
 
     def pred_to_json(self, predn: dict[str, torch.Tensor], pbatch: dict[str, Any]) -> None:
-        """
-        Save one JSON result for COCO evaluation.
+        """Save one JSON result for COCO evaluation.
 
         Args:
             predn (dict[str, torch.Tensor]): Predictions containing bboxes, masks, confidence scores, and classes.

ultralytics/models/yolo/world/train.py

@@ -24,8 +24,7 @@ def on_pretrain_routine_end(trainer) -> None:
 
 
 class WorldTrainer(DetectionTrainer):
-    """
-    A trainer class for fine-tuning YOLO World models on close-set datasets.
+    """A trainer class for fine-tuning YOLO World models on close-set datasets.
 
     This trainer extends the DetectionTrainer to support training YOLO World models, which combine visual and textual
     features for improved object detection and understanding. It handles text embedding generation and caching to
@@ -54,8 +53,7 @@ class WorldTrainer(DetectionTrainer):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides: dict[str, Any] | None = None, _callbacks=None):
-        """
-        Initialize a WorldTrainer object with given arguments.
+        """Initialize a WorldTrainer object with given arguments.
 
         Args:
             cfg (dict[str, Any]): Configuration for the trainer.
@@ -69,8 +67,7 @@ class WorldTrainer(DetectionTrainer):
         self.text_embeddings = None
 
     def get_model(self, cfg=None, weights: str | None = None, verbose: bool = True) -> WorldModel:
-        """
-        Return WorldModel initialized with specified config and weights.
+        """Return WorldModel initialized with specified config and weights.
 
         Args:
             cfg (dict[str, Any] | str, optional): Model configuration.
@@ -95,8 +92,7 @@ class WorldTrainer(DetectionTrainer):
         return model
 
     def build_dataset(self, img_path: str, mode: str = "train", batch: int | None = None):
-        """
-        Build YOLO Dataset for training or validation.
+        """Build YOLO Dataset for training or validation.
 
         Args:
             img_path (str): Path to the folder containing images.
@@ -115,11 +111,10 @@ class WorldTrainer(DetectionTrainer):
         return dataset
 
     def set_text_embeddings(self, datasets: list[Any], batch: int | None) -> None:
-        """
-        Set text embeddings for datasets to accelerate training by caching category names.
+        """Set text embeddings for datasets to accelerate training by caching category names.
 
-        This method collects unique category names from all datasets, then generates and caches text embeddings
-        for these categories to improve training efficiency.
+        This method collects unique category names from all datasets, then generates and caches text embeddings for
+        these categories to improve training efficiency.
 
         Args:
             datasets (list[Any]): List of datasets from which to extract category names.
@@ -141,8 +136,7 @@ class WorldTrainer(DetectionTrainer):
         self.text_embeddings = text_embeddings
 
     def generate_text_embeddings(self, texts: list[str], batch: int, cache_dir: Path) -> dict[str, torch.Tensor]:
-        """
-        Generate text embeddings for a list of text samples.
+        """Generate text embeddings for a list of text samples.
 
         Args:
             texts (list[str]): List of text samples to encode.

ultralytics/models/yolo/world/train_world.py

@@ -10,8 +10,7 @@ from ultralytics.utils.torch_utils import unwrap_model
 
 
 class WorldTrainerFromScratch(WorldTrainer):
-    """
-    A class extending the WorldTrainer for training a world model from scratch on open-set datasets.
+    """A class extending the WorldTrainer for training a world model from scratch on open-set datasets.
 
     This trainer specializes in handling mixed datasets including both object detection and grounding datasets,
     supporting training YOLO-World models with combined vision-language capabilities.
@@ -53,11 +52,10 @@ class WorldTrainerFromScratch(WorldTrainer):
     """
 
     def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
-        """
-        Initialize a WorldTrainerFromScratch object.
+        """Initialize a WorldTrainerFromScratch object.
 
-        This initializes a trainer for YOLO-World models from scratch, supporting mixed datasets including both
-        object detection and grounding datasets for vision-language capabilities.
+        This initializes a trainer for YOLO-World models from scratch, supporting mixed datasets including both object
+        detection and grounding datasets for vision-language capabilities.
 
         Args:
             cfg (dict): Configuration dictionary with default parameters for model training.
@@ -87,11 +85,10 @@ class WorldTrainerFromScratch(WorldTrainer):
         super().__init__(cfg, overrides, _callbacks)
 
     def build_dataset(self, img_path, mode="train", batch=None):
-        """
-        Build YOLO Dataset for training or validation.
+        """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.
+        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.
@@ -122,11 +119,10 @@ class WorldTrainerFromScratch(WorldTrainer):
         return YOLOConcatDataset(datasets) if len(datasets) > 1 else datasets[0]
 
     def get_dataset(self):
-        """
-        Get train and validation paths from data dictionary.
+        """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.
+        Processes the data configuration to extract paths for training and validation datasets, handling both YOLO
+        detection datasets and grounding datasets.
 
         Returns:
             train_path (str): Train dataset path.
@@ -187,8 +183,7 @@ class WorldTrainerFromScratch(WorldTrainer):
         pass
 
     def final_eval(self):
-        """
-        Perform final evaluation and validation for the YOLO-World model.
+        """Perform final evaluation and validation for the YOLO-World model.
 
         Configures the validator with appropriate dataset and split information before running evaluation.
 

ultralytics/models/yolo/yoloe/predict.py

@@ -9,11 +9,10 @@ from ultralytics.models.yolo.segment import SegmentationPredictor
 
 
 class YOLOEVPDetectPredictor(DetectionPredictor):
-    """
-    A mixin class for YOLO-EVP (Enhanced Visual Prompting) predictors.
+    """A mixin class for YOLO-EVP (Enhanced Visual Prompting) predictors.
 
-    This mixin provides common functionality for YOLO models that use visual prompting, including
-    model setup, prompt handling, and preprocessing transformations.
+    This mixin provides common functionality for YOLO models that use visual prompting, including model setup, prompt
+    handling, and preprocessing transformations.
 
     Attributes:
         model (torch.nn.Module): The YOLO model for inference.
@@ -29,8 +28,7 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
     """
 
     def setup_model(self, model, verbose: bool = True):
-        """
-        Set up the model for prediction.
+        """Set up the model for prediction.
 
         Args:
             model (torch.nn.Module): Model to load or use.
@@ -40,21 +38,19 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         self.done_warmup = True
 
     def set_prompts(self, prompts):
-        """
-        Set the visual prompts for the model.
+        """Set the visual prompts for the model.
 
         Args:
-            prompts (dict): Dictionary containing class indices and bounding boxes or masks.
-                Must include a 'cls' key with class indices.
+            prompts (dict): Dictionary containing class indices and bounding boxes or masks. Must include a 'cls' key
+                with class indices.
         """
         self.prompts = prompts
 
     def pre_transform(self, im):
-        """
-        Preprocess images and prompts before inference.
+        """Preprocess images and prompts before inference.
 
-        This method applies letterboxing to the input image and transforms the visual prompts
-        (bounding boxes or masks) accordingly.
+        This method applies letterboxing to the input image and transforms the visual prompts (bounding boxes or masks)
+        accordingly.
 
         Args:
             im (list): List containing a single input image.
@@ -94,8 +90,7 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         return img
 
     def _process_single_image(self, dst_shape, src_shape, category, bboxes=None, masks=None):
-        """
-        Process a single image by resizing bounding boxes or masks and generating visuals.
+        """Process a single image by resizing bounding boxes or masks and generating visuals.
 
         Args:
             dst_shape (tuple): The target shape (height, width) of the image.
@@ -131,8 +126,7 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         return LoadVisualPrompt().get_visuals(category, dst_shape, bboxes, masks)
 
     def inference(self, im, *args, **kwargs):
-        """
-        Run inference with visual prompts.
+        """Run inference with visual prompts.
 
         Args:
             im (torch.Tensor): Input image tensor.
@@ -145,13 +139,12 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
         return super().inference(im, vpe=self.prompts, *args, **kwargs)
 
     def get_vpe(self, source):
-        """
-        Process the source to get the visual prompt embeddings (VPE).
+        """Process the source to get the visual prompt embeddings (VPE).
 
         Args:
-            source (str | Path | int | PIL.Image | np.ndarray | torch.Tensor | list | tuple): The source
-                of the image to make predictions on. Accepts various types including file paths, URLs, PIL
-                images, numpy arrays, and torch tensors.
+            source (str | Path | int | PIL.Image | np.ndarray | torch.Tensor | list | tuple): The source of the image to
+                make predictions on. Accepts various types including file paths, URLs, PIL images, numpy arrays, and
+                torch tensors.
 
         Returns:
             (torch.Tensor): The visual prompt embeddings (VPE) from the model.