dgenerate-ultralytics-headless 8.3.214__py3-none-any.whl → 8.3.248__py3-none-any.whl

ultralytics/nn/text_model.py

@@ -20,8 +20,7 @@ except ImportError:
 
 
 class TextModel(nn.Module):
-    """
-    Abstract base class for text encoding models.
+    """Abstract base class for text encoding models.
 
     This class defines the interface for text encoding models used in vision-language tasks. Subclasses must implement
     the tokenize and encode_text methods to provide text tokenization and encoding functionality.
@@ -47,11 +46,10 @@ class TextModel(nn.Module):
 
 
 class CLIP(TextModel):
-    """
-    Implements OpenAI's CLIP (Contrastive Language-Image Pre-training) text encoder.
+    """Implements OpenAI's CLIP (Contrastive Language-Image Pre-training) text encoder.
 
-    This class provides a text encoder based on OpenAI's CLIP model, which can convert text into feature vectors
-    that are aligned with corresponding image features in a shared embedding space.
+    This class provides a text encoder based on OpenAI's CLIP model, which can convert text into feature vectors that
+    are aligned with corresponding image features in a shared embedding space.
 
     Attributes:
         model (clip.model.CLIP): The loaded CLIP model.
@@ -71,20 +69,14 @@ class CLIP(TextModel):
     """
 
     def __init__(self, size: str, device: torch.device) -> None:
-        """
-        Initialize the CLIP text encoder.
+        """Initialize the CLIP text encoder.
 
-        This class implements the TextModel interface using OpenAI's CLIP model for text encoding. It loads
-        a pre-trained CLIP model of the specified size and prepares it for text encoding tasks.
+        This class implements the TextModel interface using OpenAI's CLIP model for text encoding. It loads a
+        pre-trained CLIP model of the specified size and prepares it for text encoding tasks.
 
         Args:
             size (str): Model size identifier (e.g., 'ViT-B/32').
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> import torch
-            >>> clip_model = CLIP("ViT-B/32", device=torch.device("cuda:0"))
-            >>> text_features = clip_model.encode_text(["a photo of a cat", "a photo of a dog"])
         """
         super().__init__()
         self.model, self.image_preprocess = clip.load(size, device=device)
@@ -92,12 +84,13 @@ class CLIP(TextModel):
         self.device = device
         self.eval()
 
-    def tokenize(self, texts: str | list[str]) -> torch.Tensor:
-        """
-        Convert input texts to CLIP tokens.
+    def tokenize(self, texts: str | list[str], truncate: bool = True) -> torch.Tensor:
+        """Convert input texts to CLIP tokens.
 
         Args:
             texts (str | list[str]): Input text or list of texts to tokenize.
+            truncate (bool, optional): Whether to trim texts that exceed CLIP's context length. Defaults to True to
+                avoid RuntimeError from overly long inputs while still allowing explicit opt-out.
 
         Returns:
             (torch.Tensor): Tokenized text tensor with shape (batch_size, context_length) ready for model processing.
@@ -106,13 +99,14 @@ class CLIP(TextModel):
             >>> model = CLIP("ViT-B/32", device="cpu")
             >>> tokens = model.tokenize("a photo of a cat")
             >>> print(tokens.shape)  # torch.Size([1, 77])
+            >>> strict_tokens = model.tokenize("a photo of a cat", truncate=False)  # Enforce strict length checks
+            >>> print(strict_tokens.shape)  # Same shape/content as tokens since prompt less than 77 tokens
         """
-        return clip.tokenize(texts).to(self.device)
+        return clip.tokenize(texts, truncate=truncate).to(self.device)
 
     @smart_inference_mode()
     def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
-        """
-        Encode tokenized texts into normalized feature vectors.
+        """Encode tokenized texts into normalized feature vectors.
 
         This method processes tokenized text inputs through the CLIP model to generate feature vectors, which are then
         normalized to unit length. These normalized vectors can be used for text-image similarity comparisons.
@@ -137,15 +131,14 @@ class CLIP(TextModel):
 
     @smart_inference_mode()
     def encode_image(self, image: Image.Image | torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
-        """
-        Encode preprocessed images into normalized feature vectors.
+        """Encode preprocessed images into normalized feature vectors.
 
-        This method processes preprocessed image inputs through the CLIP model to generate feature vectors, which are then
-        normalized to unit length. These normalized vectors can be used for text-image similarity comparisons.
+        This method processes preprocessed image inputs through the CLIP model to generate feature vectors, which are
+        then normalized to unit length. These normalized vectors can be used for text-image similarity comparisons.
 
         Args:
-            image (PIL.Image | torch.Tensor): Preprocessed image input. If a PIL Image is provided, it will be
-                converted to a tensor using the model's image preprocessing function.
+            image (PIL.Image | torch.Tensor): Preprocessed image input. If a PIL Image is provided, it will be converted
+                to a tensor using the model's image preprocessing function.
             dtype (torch.dtype, optional): Data type for output features.
 
         Returns:
@@ -169,8 +162,7 @@ class CLIP(TextModel):
 
 
 class MobileCLIP(TextModel):
-    """
-    Implement Apple's MobileCLIP text encoder for efficient text encoding.
+    """Implement Apple's MobileCLIP text encoder for efficient text encoding.
 
     This class implements the TextModel interface using Apple's MobileCLIP model, providing efficient text encoding
     capabilities for vision-language tasks with reduced computational requirements compared to standard CLIP models.
@@ -195,28 +187,16 @@ class MobileCLIP(TextModel):
     config_size_map = {"s0": "s0", "s1": "s1", "s2": "s2", "b": "b", "blt": "b"}
 
     def __init__(self, size: str, device: torch.device) -> None:
-        """
-        Initialize the MobileCLIP text encoder.
+        """Initialize the MobileCLIP text encoder.
 
         This class implements the TextModel interface using Apple's MobileCLIP model for efficient text encoding.
 
         Args:
             size (str): Model size identifier (e.g., 's0', 's1', 's2', 'b', 'blt').
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> import torch
-            >>> model = MobileCLIP("s0", device=torch.device("cpu"))
-            >>> tokens = model.tokenize(["a photo of a cat", "a photo of a dog"])
-            >>> features = model.encode_text(tokens)
         """
         try:
-            import warnings
-
-            # Suppress 'timm.models.layers is deprecated, please import via timm.layers' warning from mobileclip usage
-            with warnings.catch_warnings():
-                warnings.filterwarnings("ignore", category=FutureWarning)
-                import mobileclip
+            import mobileclip
         except ImportError:
             # Ultralytics fork preferred since Apple MobileCLIP repo has incorrect version of torchvision
             checks.check_requirements("git+https://github.com/ultralytics/mobileclip.git")
@@ -236,8 +216,7 @@ class MobileCLIP(TextModel):
         self.eval()
 
     def tokenize(self, texts: list[str]) -> torch.Tensor:
-        """
-        Convert input texts to MobileCLIP tokens.
+        """Convert input texts to MobileCLIP tokens.
 
         Args:
             texts (list[str]): List of text strings to tokenize.
@@ -253,8 +232,7 @@ class MobileCLIP(TextModel):
 
     @smart_inference_mode()
     def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
-        """
-        Encode tokenized texts into normalized feature vectors.
+        """Encode tokenized texts into normalized feature vectors.
 
         Args:
             texts (torch.Tensor): Tokenized text inputs.
@@ -276,8 +254,7 @@ class MobileCLIP(TextModel):
 
 
 class MobileCLIPTS(TextModel):
-    """
-    Load a TorchScript traced version of MobileCLIP.
+    """Load a TorchScript traced version of MobileCLIP.
 
     This class implements the TextModel interface using Apple's MobileCLIP model in TorchScript format, providing
     efficient text encoding capabilities for vision-language tasks with optimized inference performance.
@@ -299,19 +276,13 @@ class MobileCLIPTS(TextModel):
     """
 
     def __init__(self, device: torch.device):
-        """
-        Initialize the MobileCLIP TorchScript text encoder.
+        """Initialize the MobileCLIP TorchScript text encoder.
 
-        This class implements the TextModel interface using Apple's MobileCLIP model in TorchScript format for
-        efficient text encoding with optimized inference performance.
+        This class implements the TextModel interface using Apple's MobileCLIP model in TorchScript format for efficient
+        text encoding with optimized inference performance.
 
         Args:
             device (torch.device): Device to load the model on.
-
-        Examples:
-            >>> model = MobileCLIPTS(device=torch.device("cpu"))
-            >>> tokens = model.tokenize(["a photo of a cat", "a photo of a dog"])
-            >>> features = model.encode_text(tokens)
         """
         super().__init__()
         from ultralytics.utils.downloads import attempt_download_asset
@@ -320,26 +291,29 @@ class MobileCLIPTS(TextModel):
         self.tokenizer = clip.clip.tokenize
         self.device = device
 
-    def tokenize(self, texts: list[str]) -> torch.Tensor:
-        """
-        Convert input texts to MobileCLIP tokens.
+    def tokenize(self, texts: list[str], truncate: bool = True) -> torch.Tensor:
+        """Convert input texts to MobileCLIP tokens.
 
         Args:
             texts (list[str]): List of text strings to tokenize.
+            truncate (bool, optional): Whether to trim texts that exceed the tokenizer context length. Defaults to True,
+                matching CLIP's behavior to prevent runtime failures on long captions.
 
         Returns:
             (torch.Tensor): Tokenized text inputs with shape (batch_size, sequence_length).
 
         Examples:
-            >>> model = MobileCLIPTS("cpu")
+            >>> model = MobileCLIPTS(device=torch.device("cpu"))
             >>> tokens = model.tokenize(["a photo of a cat", "a photo of a dog"])
+            >>> strict_tokens = model.tokenize(
+            ...     ["a very long caption"], truncate=False
+            ... )  # RuntimeError if exceeds 77-token
         """
-        return self.tokenizer(texts).to(self.device)
+        return self.tokenizer(texts, truncate=truncate).to(self.device)
 
     @smart_inference_mode()
     def encode_text(self, texts: torch.Tensor, dtype: torch.dtype = torch.float32) -> torch.Tensor:
-        """
-        Encode tokenized texts into normalized feature vectors.
+        """Encode tokenized texts into normalized feature vectors.
 
         Args:
             texts (torch.Tensor): Tokenized text inputs.
@@ -360,8 +334,7 @@ class MobileCLIPTS(TextModel):
 
 
 def build_text_model(variant: str, device: torch.device = None) -> TextModel:
-    """
-    Build a text encoding model based on the specified variant.
+    """Build a text encoding model based on the specified variant.
 
     Args:
         variant (str): Model variant in format "base:size" (e.g., "clip:ViT-B/32" or "mobileclip:s0").

ultralytics/solutions/__init__.py

@@ -19,23 +19,23 @@ from .trackzone import TrackZone
 from .vision_eye import VisionEye
 
 __all__ = (
-    "ObjectCounter",
-    "ObjectCropper",
-    "ObjectBlurrer",
     "AIGym",
-    "RegionCounter",
-    "SecurityAlarm",
+    "Analytics",
+    "DistanceCalculation",
     "Heatmap",
+    "Inference",
     "InstanceSegmentation",
-    "VisionEye",
-    "SpeedEstimator",
-    "DistanceCalculation",
-    "QueueManager",
+    "ObjectBlurrer",
+    "ObjectCounter",
+    "ObjectCropper",
     "ParkingManagement",
     "ParkingPtsSelection",
-    "Analytics",
-    "Inference",
-    "TrackZone",
+    "QueueManager",
+    "RegionCounter",
     "SearchApp",
+    "SecurityAlarm",
+    "SpeedEstimator",
+    "TrackZone",
+    "VisionEye",
     "VisualAISearch",
 )

ultralytics/solutions/ai_gym.py

@@ -7,14 +7,13 @@ from ultralytics.solutions.solutions import BaseSolution, SolutionAnnotator, Sol
 
 
 class AIGym(BaseSolution):
-    """
-    A class to manage gym steps of people in a real-time video stream based on their poses.
+    """A class to manage gym steps of people in a real-time video stream based on their poses.
 
     This class extends BaseSolution to monitor workouts using YOLO pose estimation models. It tracks and counts
     repetitions of exercises based on predefined angle thresholds for up and down positions.
 
     Attributes:
-        states (dict[float, int, str]): Stores per-track angle, count, and stage for workout monitoring.
+        states (dict[int, dict[str, float | int | str]]): Per-track angle, rep count, and stage for workout monitoring.
         up_angle (float): Angle threshold for considering the 'up' position of an exercise.
         down_angle (float): Angle threshold for considering the 'down' position of an exercise.
         kpts (list[int]): Indices of keypoints used for angle calculation.
@@ -32,12 +31,11 @@ class AIGym(BaseSolution):
     """
 
     def __init__(self, **kwargs: Any) -> None:
-        """
-        Initialize AIGym for workout monitoring using pose estimation and predefined angles.
+        """Initialize AIGym for workout monitoring using pose estimation and predefined angles.
 
         Args:
-            **kwargs (Any): Keyword arguments passed to the parent class constructor.
-                model (str): Model name or path, defaults to "yolo11n-pose.pt".
+            **kwargs (Any): Keyword arguments passed to the parent class constructor including:
+                - model (str): Model name or path, defaults to "yolo11n-pose.pt".
         """
         kwargs["model"] = kwargs.get("model", "yolo11n-pose.pt")
         super().__init__(**kwargs)
@@ -49,22 +47,18 @@ class AIGym(BaseSolution):
         self.kpts = self.CFG["kpts"]  # User selected kpts of workouts storage for further usage
 
     def process(self, im0) -> SolutionResults:
-        """
-        Monitor workouts using Ultralytics YOLO Pose Model.
+        """Monitor workouts using Ultralytics YOLO Pose Model.
 
-        This function processes an input image to track and analyze human poses for workout monitoring. It uses
-        the YOLO Pose model to detect keypoints, estimate angles, and count repetitions based on predefined
-        angle thresholds.
+        This function processes an input image to track and analyze human poses for workout monitoring. It uses the YOLO
+        Pose model to detect keypoints, estimate angles, and count repetitions based on predefined angle thresholds.
 
         Args:
             im0 (np.ndarray): Input image for processing.
 
         Returns:
-            (SolutionResults): Contains processed image `plot_im`,
-                'workout_count' (list of completed reps),
-                'workout_stage' (list of current stages),
-                'workout_angle' (list of angles), and
-                'total_tracks' (total number of tracked individuals).
+            (SolutionResults): Contains processed image `plot_im`, 'workout_count' (list of completed reps),
+                'workout_stage' (list of current stages), 'workout_angle' (list of angles), and 'total_tracks' (total
+                number of tracked individuals).
 
         Examples:
             >>> gym = AIGym()

ultralytics/solutions/analytics.py

@@ -9,14 +9,14 @@ import cv2
 import numpy as np
 
 from ultralytics.solutions.solutions import BaseSolution, SolutionResults  # Import a parent class
+from ultralytics.utils import plt_settings
 
 
 class Analytics(BaseSolution):
-    """
-    A class for creating and updating various types of charts for visual analytics.
+    """A class for creating and updating various types of charts for visual analytics.
 
-    This class extends BaseSolution to provide functionality for generating line, bar, pie, and area charts
-    based on object detection and tracking data.
+    This class extends BaseSolution to provide functionality for generating line, bar, pie, and area charts based on
+    object detection and tracking data.
 
     Attributes:
         type (str): The type of analytics chart to generate ('line', 'bar', 'pie', or 'area').
@@ -47,6 +47,7 @@ class Analytics(BaseSolution):
         >>> cv2.imshow("Analytics", results.plot_im)
     """
 
+    @plt_settings()
     def __init__(self, **kwargs: Any) -> None:
         """Initialize Analytics class with various chart types for visual data representation."""
         super().__init__(**kwargs)
@@ -55,7 +56,7 @@ class Analytics(BaseSolution):
         from matplotlib.backends.backend_agg import FigureCanvasAgg
         from matplotlib.figure import Figure
 
-        self.type = self.CFG["analytics_type"]  # type of analytics i.e "line", "pie", "bar" or "area" charts.
+        self.type = self.CFG["analytics_type"]  # Chart type: "line", "pie", "bar", or "area".
         self.x_label = "Classes" if self.type in {"bar", "pie"} else "Frame#"
         self.y_label = "Total Counts"
 
@@ -65,10 +66,10 @@ class Analytics(BaseSolution):
         self.title = "Ultralytics Solutions"  # window name
         self.max_points = 45  # maximum points to be drawn on window
         self.fontsize = 25  # text font size for display
-        figsize = self.CFG["figsize"]  # set output image size i.e (12.8, 7.2) -> w = 1280, h = 720
+        figsize = self.CFG["figsize"]  # Output size, e.g. (12.8, 7.2) -> 1280x720.
         self.color_cycle = cycle(["#DD00BA", "#042AFF", "#FF4447", "#7D24FF", "#BD00FF"])
 
-        self.total_counts = 0  # count variable for storing total counts i.e. for line
+        self.total_counts = 0  # Stores total counts for line charts.
         self.clswise_count = {}  # dictionary for class-wise counts
         self.update_every = kwargs.get("update_every", 30)  # Only update graph every 30 frames by default
         self.last_plot_im = None  # Cache of the last rendered chart
@@ -92,8 +93,7 @@ class Analytics(BaseSolution):
                 self.ax.axis("equal")
 
     def process(self, im0: np.ndarray, frame_number: int) -> SolutionResults:
-        """
-        Process image data and run object tracking to update analytics charts.
+        """Process image data and run object tracking to update analytics charts.
 
         Args:
             im0 (np.ndarray): Input image for processing.
@@ -104,7 +104,7 @@ class Analytics(BaseSolution):
                 and 'classwise_count' (dict, per-class object count).
 
         Raises:
-            ModuleNotFoundError: If an unsupported chart type is specified.
+            ValueError: If an unsupported chart type is specified.
 
         Examples:
             >>> analytics = Analytics(analytics_type="line")
@@ -131,21 +131,20 @@ class Analytics(BaseSolution):
                 )
             plot_im = self.last_plot_im
         else:
-            raise ModuleNotFoundError(f"{self.type} chart is not supported ❌")
+            raise ValueError(f"Unsupported analytics_type='{self.type}'. Supported types: line, bar, pie, area.")
 
-        # return output dictionary with summary for more usage
+        # Return results for downstream use.
         return SolutionResults(plot_im=plot_im, total_tracks=len(self.track_ids), classwise_count=self.clswise_count)
 
     def update_graph(
         self, frame_number: int, count_dict: dict[str, int] | None = None, plot: str = "line"
     ) -> np.ndarray:
-        """
-        Update the graph with new data for single or multiple classes.
+        """Update the graph with new data for single or multiple classes.
 
         Args:
             frame_number (int): The current frame number.
-            count_dict (dict[str, int], optional): Dictionary with class names as keys and counts as values for
-                multiple classes. If None, updates a single line graph.
+            count_dict (dict[str, int], optional): Dictionary with class names as keys and counts as values for multiple
+                classes. If None, updates a single line graph.
             plot (str): Type of the plot. Options are 'line', 'bar', 'pie', or 'area'.
 
         Returns:

ultralytics/solutions/config.py

@@ -10,12 +10,11 @@ import cv2
 
 @dataclass
 class SolutionConfig:
-    """
-    Manages configuration parameters for Ultralytics Vision AI solutions.
+    """Manages configuration parameters for Ultralytics Vision AI solutions.
 
-    The SolutionConfig class serves as a centralized configuration container for all the
-    Ultralytics solution modules: https://docs.ultralytics.com/solutions/#solutions.
-    It leverages Python `dataclass` for clear, type-safe, and maintainable parameter definitions.
+    The SolutionConfig class serves as a centralized configuration container for all the Ultralytics solution modules:
+    https://docs.ultralytics.com/solutions/#solutions. It leverages Python `dataclass` for clear, type-safe, and
+    maintainable parameter definitions.
 
     Attributes:
         source (str, optional): Path to the input source (video, RTSP, etc.). Only usable with Solutions CLI.
@@ -36,7 +35,7 @@ class SolutionConfig:
         vision_point (tuple[int, int]): Reference point for directional tracking or perspective drawing.
         crop_dir (str): Directory path to save cropped detection images.
         json_file (str): Path to a JSON file containing data for parking areas.
-        line_width (int): Width for visual display i.e. bounding boxes, keypoints, counts.
+        line_width (int): Width for visual display, e.g. bounding boxes, keypoints, and counts.
         records (int): Number of detection records to send email alerts.
         fps (float): Frame rate (Frames Per Second) for speed estimation calculation.
         max_hist (int): Maximum number of historical points or states stored per tracked object for speed estimation.

ultralytics/solutions/distance_calculation.py

@@ -10,15 +10,14 @@ from ultralytics.utils.plotting import colors
 
 
 class DistanceCalculation(BaseSolution):
-    """
-    A class to calculate distance between two objects in a real-time video stream based on their tracks.
+    """A class to calculate distance between two objects in a real-time video stream based on their tracks.
 
-    This class extends BaseSolution to provide functionality for selecting objects and calculating the distance
-    between them in a video stream using YOLO object detection and tracking.
+    This class extends BaseSolution to provide functionality for selecting objects and calculating the distance between
+    them in a video stream using YOLO object detection and tracking.
 
     Attributes:
         left_mouse_count (int): Counter for left mouse button clicks.
-        selected_boxes (dict[int, list[float]]): Dictionary to store selected bounding boxes and their track IDs.
+        selected_boxes (dict[int, Any]): Dictionary to store selected bounding boxes keyed by track ID.
         centroids (list[list[int]]): List to store centroids of selected bounding boxes.
 
     Methods:
@@ -43,8 +42,7 @@ class DistanceCalculation(BaseSolution):
         self.centroids: list[list[int]] = []  # Store centroids of selected objects
 
     def mouse_event_for_distance(self, event: int, x: int, y: int, flags: int, param: Any) -> None:
-        """
-        Handle mouse events to select regions in a real-time video stream for distance calculation.
+        """Handle mouse events to select regions in a real-time video stream for distance calculation.
 
         Args:
             event (int): Type of mouse event (e.g., cv2.EVENT_MOUSEMOVE, cv2.EVENT_LBUTTONDOWN).
@@ -69,18 +67,17 @@ class DistanceCalculation(BaseSolution):
             self.left_mouse_count = 0
 
     def process(self, im0) -> SolutionResults:
-        """
-        Process a video frame and calculate the distance between two selected bounding boxes.
+        """Process a video frame and calculate the distance between two selected bounding boxes.
 
-        This method extracts tracks from the input frame, annotates bounding boxes, and calculates the distance
-        between two user-selected objects if they have been chosen.
+        This method extracts tracks from the input frame, annotates bounding boxes, and calculates the distance between
+        two user-selected objects if they have been chosen.
 
         Args:
             im0 (np.ndarray): The input image frame to process.
 
         Returns:
-            (SolutionResults): Contains processed image `plot_im`, `total_tracks` (int) representing the total number
-                of tracked objects, and `pixels_distance` (float) representing the distance between selected objects
+            (SolutionResults): Contains processed image `plot_im`, `total_tracks` (int) representing the total number of
+                tracked objects, and `pixels_distance` (float) representing the distance between selected objects
                 in pixels.
 
         Examples:

ultralytics/solutions/heatmap.py

@@ -12,8 +12,7 @@ from ultralytics.solutions.solutions import SolutionAnnotator, SolutionResults
 
 
 class Heatmap(ObjectCounter):
-    """
-    A class to draw heatmaps in real-time video streams based on object tracks.
+    """A class to draw heatmaps in real-time video streams based on object tracks.
 
     This class extends the ObjectCounter class to generate and visualize heatmaps of object movements in video
     streams. It uses tracked object positions to create a cumulative heatmap effect over time.
@@ -36,8 +35,7 @@ class Heatmap(ObjectCounter):
     """
 
     def __init__(self, **kwargs: Any) -> None:
-        """
-        Initialize the Heatmap class for real-time video stream heatmap generation based on object tracks.
+        """Initialize the Heatmap class for real-time video stream heatmap generation based on object tracks.
 
         Args:
             **kwargs (Any): Keyword arguments passed to the parent ObjectCounter class.
@@ -53,8 +51,7 @@ class Heatmap(ObjectCounter):
         self.heatmap = None
 
     def heatmap_effect(self, box: list[float]) -> None:
-        """
-        Efficiently calculate heatmap area and effect location for applying colormap.
+        """Efficiently calculate heatmap area and effect location for applying colormap.
 
         Args:
             box (list[float]): Bounding box coordinates [x0, y0, x1, y1].
@@ -75,18 +72,15 @@ class Heatmap(ObjectCounter):
         self.heatmap[y0:y1, x0:x1][within_radius] += 2
 
     def process(self, im0: np.ndarray) -> SolutionResults:
-        """
-        Generate heatmap for each frame using Ultralytics tracking.
+        """Generate heatmap for each frame using Ultralytics tracking.
 
         Args:
             im0 (np.ndarray): Input image array for processing.
 
         Returns:
-            (SolutionResults): Contains processed image `plot_im`,
-                'in_count' (int, count of objects entering the region),
-                'out_count' (int, count of objects exiting the region),
-                'classwise_count' (dict, per-class object count), and
-                'total_tracks' (int, total number of tracked objects).
+            (SolutionResults): Contains processed image `plot_im`, 'in_count' (int, count of objects entering the
+                region), 'out_count' (int, count of objects exiting the region), 'classwise_count' (dict, per-class
+                object count), and 'total_tracks' (int, total number of tracked objects).
         """
         if not self.initialized:
             self.heatmap = np.zeros_like(im0, dtype=np.float32) * 0.99

ultralytics/solutions/instance_segmentation.py

@@ -7,8 +7,7 @@ from ultralytics.solutions.solutions import BaseSolution, SolutionResults
 
 
 class InstanceSegmentation(BaseSolution):
-    """
-    A class to manage instance segmentation in images or video streams.
+    """A class to manage instance segmentation in images or video streams.
 
     This class extends the BaseSolution class and provides functionality for performing instance segmentation, including
     drawing segmented masks with bounding boxes and labels.
@@ -36,12 +35,11 @@ class InstanceSegmentation(BaseSolution):
     """
 
     def __init__(self, **kwargs: Any) -> None:
-        """
-        Initialize the InstanceSegmentation class for detecting and annotating segmented instances.
+        """Initialize the InstanceSegmentation class for detecting and annotating segmented instances.
 
         Args:
-            **kwargs (Any): Keyword arguments passed to the BaseSolution parent class.
-                model (str): Model name or path, defaults to "yolo11n-seg.pt".
+            **kwargs (Any): Keyword arguments passed to the BaseSolution parent class including:
+                - model (str): Model name or path, defaults to "yolo11n-seg.pt".
         """
         kwargs["model"] = kwargs.get("model", "yolo11n-seg.pt")
         super().__init__(**kwargs)
@@ -51,8 +49,7 @@ class InstanceSegmentation(BaseSolution):
         self.show_boxes = self.CFG.get("show_boxes", True)
 
     def process(self, im0) -> SolutionResults:
-        """
-        Perform instance segmentation on the input image and annotate the results.
+        """Perform instance segmentation on the input image and annotate the results.
 
         Args:
             im0 (np.ndarray): The input image for segmentation.

ultralytics/solutions/object_blurrer.py

@@ -10,8 +10,7 @@ from ultralytics.utils.plotting import colors
 
 
 class ObjectBlurrer(BaseSolution):
-    """
-    A class to manage the blurring of detected objects in a real-time video stream.
+    """A class to manage the blurring of detected objects in a real-time video stream.
 
     This class extends the BaseSolution class and provides functionality for blurring objects based on detected bounding
     boxes. The blurred areas are updated directly in the input image, allowing for privacy preservation or other effects.
@@ -34,12 +33,11 @@ class ObjectBlurrer(BaseSolution):
     """
 
     def __init__(self, **kwargs: Any) -> None:
-        """
-        Initialize the ObjectBlurrer class for applying a blur effect to objects detected in video streams or images.
+        """Initialize the ObjectBlurrer class for applying a blur effect to objects detected in video streams or images.
 
         Args:
-            **kwargs (Any): Keyword arguments passed to the parent class and for configuration.
-                blur_ratio (float): Intensity of the blur effect (0.1-1.0, default=0.5).
+            **kwargs (Any): Keyword arguments passed to the parent class and for configuration including:
+                - blur_ratio (float): Intensity of the blur effect (0.1-1.0, default=0.5).
         """
         super().__init__(**kwargs)
         blur_ratio = self.CFG["blur_ratio"]
@@ -49,11 +47,10 @@ class ObjectBlurrer(BaseSolution):
         self.blur_ratio = int(blur_ratio * 100)
 
     def process(self, im0) -> SolutionResults:
-        """
-        Apply a blurring effect to detected objects in the input image.
+        """Apply a blurring effect to detected objects in the input image.
 
-        This method extracts tracking information, applies blur to regions corresponding to detected objects,
-        and annotates the image with bounding boxes.
+        This method extracts tracking information, applies blur to regions corresponding to detected objects, and
+        annotates the image with bounding boxes.
 
         Args:
             im0 (np.ndarray): The input image containing detected objects.