dgenerate-ultralytics-headless 8.3.143__py3-none-any.whl → 8.3.145__py3-none-any.whl

ultralytics/models/yolo/pose/val.py

@@ -1,6 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np
 import torch
@@ -26,18 +27,20 @@ class PoseValidator(DetectionValidator):
         metrics (PoseMetrics): Metrics object for pose evaluation.
 
     Methods:
-        preprocess: Preprocesses batch data for pose validation.
-        get_desc: Returns description of evaluation metrics.
-        init_metrics: Initializes pose metrics for the model.
-        _prepare_batch: Prepares a batch for processing.
-        _prepare_pred: Prepares and scales predictions for evaluation.
-        update_metrics: Updates metrics with new predictions.
-        _process_batch: Processes batch to compute IoU between detections and ground truth.
-        plot_val_samples: Plots validation samples with ground truth annotations.
-        plot_predictions: Plots model predictions.
-        save_one_txt: Saves detections to a text file.
-        pred_to_json: Converts predictions to COCO JSON format.
-        eval_json: Evaluates model using COCO JSON format.
+        preprocess: Preprocess batch by converting keypoints data to float and moving it to the device.
+        get_desc: Return description of evaluation metrics in string format.
+        init_metrics: Initialize pose estimation metrics for YOLO model.
+        _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.
+        update_metrics: Update metrics with new predictions and ground truth data.
+        _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.
+        pred_to_json: Convert YOLO predictions to COCO JSON format.
+        eval_json: Evaluate object detection model using COCO JSON format.
 
     Examples:
         >>> from ultralytics.models.yolo.pose import PoseValidator
@@ -82,13 +85,13 @@ class PoseValidator(DetectionValidator):
                 "See https://github.com/ultralytics/ultralytics/issues/4031."
             )
 
-    def preprocess(self, batch):
+    def preprocess(self, batch: Dict[str, Any]) -> Dict[str, Any]:
         """Preprocess batch by converting keypoints data to float and moving it to the device."""
         batch = super().preprocess(batch)
         batch["keypoints"] = batch["keypoints"].to(self.device).float()
         return batch
 
-    def get_desc(self):
+    def get_desc(self) -> str:
         """Return description of evaluation metrics in string format."""
         return ("%22s" + "%11s" * 10) % (
             "Class",
@@ -113,7 +116,7 @@ class PoseValidator(DetectionValidator):
         self.sigma = OKS_SIGMA if is_pose else np.ones(nkpt) / nkpt
         self.stats = dict(tp_p=[], tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])
 
-    def _prepare_batch(self, si, batch):
+    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.
 
@@ -122,7 +125,7 @@ class PoseValidator(DetectionValidator):
             batch (dict): Dictionary containing batch data with keys like 'keypoints', 'batch_idx', etc.
 
         Returns:
-            pbatch (dict): Prepared batch with keypoints scaled to original image dimensions.
+            (dict): Prepared batch with keypoints scaled to original image dimensions.
 
         Notes:
             This method extends the parent class's _prepare_batch method by adding keypoint processing.
@@ -138,7 +141,7 @@ class PoseValidator(DetectionValidator):
         pbatch["kpts"] = kpts
         return pbatch
 
-    def _prepare_pred(self, pred, pbatch):
+    def _prepare_pred(self, pred: torch.Tensor, pbatch: Dict[str, Any]) -> Tuple[torch.Tensor, torch.Tensor]:
         """
         Prepare and scale keypoints in predictions for pose processing.
 
@@ -155,6 +158,7 @@ class PoseValidator(DetectionValidator):
 
         Returns:
             predn (torch.Tensor): Processed prediction boxes scaled to original image dimensions.
+            pred_kpts (torch.Tensor): Predicted keypoints scaled to original image dimensions.
         """
         predn = super()._prepare_pred(pred, pbatch)
         nk = pbatch["kpts"].shape[1]
@@ -162,7 +166,7 @@ class PoseValidator(DetectionValidator):
         ops.scale_coords(pbatch["imgsz"], pred_kpts, pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"])
         return predn, pred_kpts
 
-    def update_metrics(self, preds, batch):
+    def update_metrics(self, preds: List[torch.Tensor], batch: Dict[str, Any]):
         """
         Update metrics with new predictions and ground truth data.
 
@@ -224,7 +228,14 @@ class PoseValidator(DetectionValidator):
                     self.save_dir / "labels" / f"{Path(batch['im_file'][si]).stem}.txt",
                 )
 
-    def _process_batch(self, detections, gt_bboxes, gt_cls, pred_kpts=None, gt_kpts=None):
+    def _process_batch(
+        self,
+        detections: torch.Tensor,
+        gt_bboxes: torch.Tensor,
+        gt_cls: torch.Tensor,
+        pred_kpts: Optional[torch.Tensor] = None,
+        gt_kpts: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
         """
         Return correct prediction matrix by computing Intersection over Union (IoU) between detections and ground truth.
 
@@ -234,9 +245,9 @@ class PoseValidator(DetectionValidator):
             gt_bboxes (torch.Tensor): Tensor with shape (M, 4) representing ground truth bounding boxes, where each
                 box is of the format (x1, y1, x2, y2).
             gt_cls (torch.Tensor): Tensor with shape (M,) representing ground truth class indices.
-            pred_kpts (torch.Tensor | None): Optional tensor with shape (N, 51) representing predicted keypoints, where
+            pred_kpts (torch.Tensor, optional): Tensor with shape (N, 51) representing predicted keypoints, where
                 51 corresponds to 17 keypoints each having 3 values.
-            gt_kpts (torch.Tensor | None): Optional tensor with shape (N, 51) representing ground truth keypoints.
+            gt_kpts (torch.Tensor, optional): Tensor with shape (N, 51) representing ground truth keypoints.
 
         Returns:
             (torch.Tensor): A tensor with shape (N, 10) representing the correct prediction matrix for 10 IoU levels,
@@ -255,7 +266,7 @@ class PoseValidator(DetectionValidator):
 
         return self.match_predictions(detections[:, 5], gt_cls, iou)
 
-    def plot_val_samples(self, batch, ni):
+    def plot_val_samples(self, batch: Dict[str, Any], ni: int):
         """
         Plot and save validation set samples with ground truth bounding boxes and keypoints.
 
@@ -281,7 +292,7 @@ class PoseValidator(DetectionValidator):
             on_plot=self.on_plot,
         )
 
-    def plot_predictions(self, batch, preds, ni):
+    def plot_predictions(self, batch: Dict[str, Any], preds: List[torch.Tensor], ni: int):
         """
         Plot and save model predictions with bounding boxes and keypoints.
 
@@ -305,7 +316,14 @@ class PoseValidator(DetectionValidator):
             on_plot=self.on_plot,
         )  # pred
 
-    def save_one_txt(self, predn, pred_kpts, save_conf, shape, file):
+    def save_one_txt(
+        self,
+        predn: torch.Tensor,
+        pred_kpts: torch.Tensor,
+        save_conf: bool,
+        shape: Tuple[int, int],
+        file: Path,
+    ):
         """
         Save YOLO pose detections to a text file in normalized coordinates.
 
@@ -331,7 +349,7 @@ class PoseValidator(DetectionValidator):
             keypoints=pred_kpts,
         ).save_txt(file, save_conf=save_conf)
 
-    def pred_to_json(self, predn, filename):
+    def pred_to_json(self, predn: torch.Tensor, filename: str):
         """
         Convert YOLO predictions to COCO JSON format.
 
@@ -364,7 +382,7 @@ class PoseValidator(DetectionValidator):
                 }
             )
 
-    def eval_json(self, stats):
+    def eval_json(self, stats: Dict[str, Any]) -> Dict[str, Any]:
         """Evaluate object detection model using COCO JSON format."""
         if self.args.save_json and self.is_coco and len(self.jdict):
             anno_json = self.data["path"] / "annotations/person_keypoints_val2017.json"  # annotations

ultralytics/models/yolo/segment/predict.py

@@ -18,9 +18,9 @@ class SegmentationPredictor(DetectionPredictor):
         batch (list): Current batch of images being processed.
 
     Methods:
-        postprocess: Applies non-max suppression and processes detections.
-        construct_results: Constructs a list of result objects from predictions.
-        construct_result: Constructs a single result object from a prediction.
+        postprocess: Apply non-max suppression and process segmentation detections.
+        construct_results: Construct a list of result objects from predictions.
+        construct_result: Construct a single result object from a prediction.
 
     Examples:
         >>> from ultralytics.utils import ASSETS
@@ -38,7 +38,7 @@ class SegmentationPredictor(DetectionPredictor):
         prediction results.
 
         Args:
-            cfg (dict): Configuration for the predictor. Defaults to Ultralytics DEFAULT_CFG.
+            cfg (dict): 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.
         """
@@ -56,7 +56,7 @@ class SegmentationPredictor(DetectionPredictor):
 
         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.
+                Each Results object includes both bounding boxes and segmentation masks.
 
         Examples:
             >>> predictor = SegmentationPredictor(overrides=dict(model="yolo11n-seg.pt"))

ultralytics/models/yolo/segment/train.py

@@ -1,6 +1,8 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from copy import copy
+from pathlib import Path
+from typing import Dict, Optional, Union
 
 from ultralytics.models import yolo
 from ultralytics.nn.tasks import SegmentationModel
@@ -25,7 +27,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         >>> trainer.train()
     """
 
-    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+    def __init__(self, cfg=DEFAULT_CFG, overrides: Optional[Dict] = None, _callbacks=None):
         """
         Initialize a SegmentationTrainer object.
 
@@ -33,7 +35,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         functionality. It sets the task to 'segment' and prepares the trainer for training segmentation models.
 
         Args:
-            cfg (dict): Configuration dictionary with default training settings. Defaults to DEFAULT_CFG.
+            cfg (dict): Configuration dictionary with default training settings.
             overrides (dict, optional): Dictionary of parameter overrides for the default configuration.
             _callbacks (list, optional): List of callback functions to be executed during training.
 
@@ -48,13 +50,15 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         overrides["task"] = "segment"
         super().__init__(cfg, overrides, _callbacks)
 
-    def get_model(self, cfg=None, weights=None, verbose=True):
+    def get_model(
+        self, cfg: Optional[Union[Dict, str]] = None, weights: Optional[Union[str, Path]] = None, verbose: bool = True
+    ):
         """
         Initialize and return a SegmentationModel with specified configuration and weights.
 
         Args:
-            cfg (dict | str | None): Model configuration. Can be a dictionary, a path to a YAML file, or None.
-            weights (str | Path | None): Path to pretrained weights file.
+            cfg (dict | str, optional): Model configuration. Can be a dictionary, a path to a YAML file, or None.
+            weights (str | Path, optional): Path to pretrained weights file.
             verbose (bool): Whether to display model information during initialization.
 
         Returns:
@@ -78,7 +82,7 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
             self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks
         )
 
-    def plot_training_samples(self, batch, ni):
+    def plot_training_samples(self, batch: Dict, ni: int):
         """
         Plot training sample images with labels, bounding boxes, and masks.
 
@@ -119,5 +123,5 @@ class SegmentationTrainer(yolo.detect.DetectionTrainer):
         )
 
     def plot_metrics(self):
-        """Plots training/val metrics."""
+        """Plot training/validation metrics."""
         plot_results(file=self.csv, segment=True, on_plot=self.on_plot)  # save results.png

ultralytics/models/yolo/segment/val.py

@@ -69,7 +69,7 @@ class SegmentationValidator(DetectionValidator):
         self.plot_masks = []
         if self.args.save_json:
             check_requirements("pycocotools>=2.0.6")
-        # more accurate vs faster
+        # More accurate vs faster
         self.process = ops.process_mask_native if self.args.save_json or self.args.save_txt else ops.process_mask
         self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])
 
@@ -247,7 +247,7 @@ class SegmentationValidator(DetectionValidator):
         Returns:
             (torch.Tensor): A correct prediction matrix of shape (N, 10), where 10 represents different IoU levels.
 
-        Note:
+        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.
 

ultralytics/models/yolo/world/train.py

@@ -2,6 +2,7 @@
 
 import itertools
 from pathlib import Path
+from typing import Any, Dict, List, Optional
 
 import torch
 
@@ -12,8 +13,8 @@ from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.torch_utils import de_parallel
 
 
-def on_pretrain_routine_end(trainer):
-    """Callback to set up model classes and text encoder at the end of the pretrain routine."""
+def on_pretrain_routine_end(trainer) -> None:
+    """Set up model classes and text encoder at the end of the pretrain routine."""
     if RANK in {-1, 0}:
         # Set class names for evaluation
         names = [name.split("/", 1)[0] for name in list(trainer.test_loader.dataset.data["names"].values())]
@@ -22,45 +23,54 @@ def on_pretrain_routine_end(trainer):
 
 class WorldTrainer(DetectionTrainer):
     """
-    A class to fine-tune a world model on a close-set dataset.
+    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.
+    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
+    accelerate training with multi-modal data.
 
     Attributes:
-        clip (module): The CLIP module for text-image understanding.
-        text_model (module): The text encoder model from CLIP.
+        text_embeddings (Dict[str, torch.Tensor] | None): Cached text embeddings for category names to accelerate
+            training.
         model (WorldModel): The YOLO World model being trained.
-        data (dict): Dataset configuration containing class information.
-        args (dict): Training arguments and configuration.
+        data (Dict[str, Any]): Dataset configuration containing class information.
+        args (Any): Training arguments and configuration.
+
+    Methods:
+        get_model: Return WorldModel initialized with specified config and weights.
+        build_dataset: Build YOLO Dataset for training or validation.
+        set_text_embeddings: Set text embeddings for datasets to accelerate training.
+        generate_text_embeddings: Generate text embeddings for a list of text samples.
+        preprocess_batch: Preprocess a batch of images and text for YOLOWorld training.
 
     Examples:
-        >>> from ultralytics.models.yolo.world import WorldModel
+        Initialize and train a YOLO World model
+        >>> from ultralytics.models.yolo.world import WorldTrainer
         >>> args = dict(model="yolov8s-world.pt", data="coco8.yaml", epochs=3)
         >>> trainer = WorldTrainer(overrides=args)
         >>> trainer.train()
     """
 
-    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+    def __init__(self, cfg=DEFAULT_CFG, overrides: Optional[Dict[str, Any]] = None, _callbacks=None):
         """
         Initialize a WorldTrainer object with given arguments.
 
         Args:
-            cfg (dict): Configuration for the trainer.
-            overrides (dict, optional): Configuration overrides.
-            _callbacks (list, optional): List of callback functions.
+            cfg (Dict[str, Any]): Configuration for the trainer.
+            overrides (Dict[str, Any], optional): Configuration overrides.
+            _callbacks (List[Any], optional): List of callback functions.
         """
         if overrides is None:
             overrides = {}
         super().__init__(cfg, overrides, _callbacks)
         self.text_embeddings = None
 
-    def get_model(self, cfg=None, weights=None, verbose=True):
+    def get_model(self, cfg=None, weights: Optional[str] = None, verbose: bool = True) -> WorldModel:
         """
         Return WorldModel initialized with specified config and weights.
 
         Args:
-            cfg (Dict | str, optional): Model configuration.
+            cfg (Dict[str, Any] | str, optional): Model configuration.
             weights (str, optional): Path to pretrained weights.
             verbose (bool): Whether to display model info.
 
@@ -81,7 +91,7 @@ class WorldTrainer(DetectionTrainer):
 
         return model
 
-    def build_dataset(self, img_path, mode="train", batch=None):
+    def build_dataset(self, img_path: str, mode: str = "train", batch: Optional[int] = None):
         """
         Build YOLO Dataset for training or validation.
 
@@ -91,7 +101,7 @@ class WorldTrainer(DetectionTrainer):
             batch (int, optional): Size of batches, this is for `rect`.
 
         Returns:
-            (Dataset): YOLO dataset configured for training or validation.
+            (Any): YOLO dataset configured for training or validation.
         """
         gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
         dataset = build_yolo_dataset(
@@ -101,7 +111,7 @@ class WorldTrainer(DetectionTrainer):
             self.set_text_embeddings([dataset], batch)  # cache text embeddings to accelerate training
         return dataset
 
-    def set_text_embeddings(self, datasets, batch):
+    def set_text_embeddings(self, datasets: List[Any], batch: Optional[int]) -> None:
         """
         Set text embeddings for datasets to accelerate training by caching category names.
 
@@ -109,7 +119,7 @@ class WorldTrainer(DetectionTrainer):
         for these categories to improve training efficiency.
 
         Args:
-            datasets (List[Dataset]): List of datasets from which to extract category names.
+            datasets (List[Any]): List of datasets from which to extract category names.
             batch (int | None): Batch size used for processing.
 
         Notes:
@@ -127,7 +137,7 @@ class WorldTrainer(DetectionTrainer):
             )
         self.text_embeddings = text_embeddings
 
-    def generate_text_embeddings(self, texts, batch, cache_dir):
+    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.
 
@@ -137,7 +147,7 @@ class WorldTrainer(DetectionTrainer):
             cache_dir (Path): Directory to save/load cached embeddings.
 
         Returns:
-            (dict): Dictionary mapping text samples to their embeddings.
+            (Dict[str, torch.Tensor]): Dictionary mapping text samples to their embeddings.
         """
         model = "clip:ViT-B/32"
         cache_path = cache_dir / f"text_embeddings_{model.replace(':', '_').replace('/', '_')}.pt"
@@ -153,7 +163,7 @@ class WorldTrainer(DetectionTrainer):
         torch.save(txt_map, cache_path)
         return txt_map
 
-    def preprocess_batch(self, batch):
+    def preprocess_batch(self, batch: Dict[str, Any]) -> Dict[str, Any]:
         """Preprocess a batch of images and text for YOLOWorld training."""
         batch = DetectionTrainer.preprocess_batch(self, batch)
 

ultralytics/models/yolo/world/train_world.py

@@ -18,6 +18,14 @@ class WorldTrainerFromScratch(WorldTrainer):
         cfg (dict): Configuration dictionary with default parameters for model training.
         overrides (dict): Dictionary of parameter overrides to customize the configuration.
         _callbacks (list): List of callback functions to be executed during different stages of training.
+        data (dict): Final processed data configuration containing train/val paths and metadata.
+        training_data (dict): Dictionary mapping training dataset paths to their configurations.
+
+    Methods:
+        build_dataset: Build YOLO Dataset for training or validation with mixed dataset support.
+        get_dataset: Get train and validation paths from data dictionary.
+        plot_training_labels: Skip label plotting for YOLO-World training.
+        final_eval: Perform final evaluation and validation for the YOLO-World model.
 
     Examples:
         >>> from ultralytics.models.yolo.world.train_world import WorldTrainerFromScratch
@@ -111,8 +119,8 @@ class WorldTrainerFromScratch(WorldTrainer):
         handling both YOLO detection datasets and grounding datasets.
 
         Returns:
-            (str): Train dataset path.
-            (str): Validation dataset path.
+            train_path (str): Train dataset path.
+            val_path (str): Validation dataset path.
 
         Raises:
             AssertionError: If train or validation datasets are not found, or if validation has multiple datasets.
@@ -159,7 +167,7 @@ class WorldTrainerFromScratch(WorldTrainer):
         return final_data
 
     def plot_training_labels(self):
-        """Do not plot labels for YOLO-World training."""
+        """Skip label plotting for YOLO-World training."""
         pass
 
     def final_eval(self):

ultralytics/models/yolo/yoloe/predict.py

@@ -18,23 +18,23 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
     Attributes:
         model (torch.nn.Module): The YOLO model for inference.
         device (torch.device): Device to run the model on (CPU or CUDA).
-        prompts (dict): Visual prompts containing class indices and bounding boxes or masks.
+        prompts (dict | torch.Tensor): Visual prompts containing class indices and bounding boxes or masks.
 
     Methods:
         setup_model: Initialize the YOLO model and set it to evaluation mode.
-        set_return_vpe: Set whether to return visual prompt embeddings.
         set_prompts: Set the visual prompts for the model.
         pre_transform: Preprocess images and prompts before inference.
         inference: Run inference with visual prompts.
+        get_vpe: Process source to get visual prompt embeddings.
     """
 
-    def setup_model(self, model, verbose=True):
+    def setup_model(self, model, verbose: bool = True):
         """
-        Sets up the model for prediction.
+        Set up the model for prediction.
 
         Args:
             model (torch.nn.Module): Model to load or use.
-            verbose (bool): If True, provides detailed logging.
+            verbose (bool, optional): If True, provides detailed logging.
         """
         super().setup_model(model, verbose=verbose)
         self.done_warmup = True
@@ -95,17 +95,17 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
 
     def _process_single_image(self, dst_shape, src_shape, category, bboxes=None, masks=None):
         """
-        Processes 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.
             src_shape (tuple): The original shape (height, width) of the image.
             category (str): The category of the image for visual prompts.
-            bboxes (list | np.ndarray, optional): A list of bounding boxes in the format [x1, y1, x2, y2]. Defaults to None.
-            masks (np.ndarray, optional): A list of masks corresponding to the image. Defaults to None.
+            bboxes (list | np.ndarray, optional): A list of bounding boxes in the format [x1, y1, x2, y2].
+            masks (np.ndarray, optional): A list of masks corresponding to the image.
 
         Returns:
-            visuals: The processed visuals for the image.
+            (torch.Tensor): The processed visuals for the image.
 
         Raises:
             ValueError: If neither `bboxes` nor `masks` are provided.
@@ -146,7 +146,7 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
 
     def get_vpe(self, source):
         """
-        Processes 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
@@ -164,6 +164,6 @@ class YOLOEVPDetectPredictor(DetectionPredictor):
 
 
 class YOLOEVPSegPredictor(YOLOEVPDetectPredictor, SegmentationPredictor):
-    """Predictor for YOLOE VP segmentation."""
+    """Predictor for YOLO-EVP segmentation tasks combining detection and segmentation capabilities."""
 
     pass