ultralytics 8.3.88__py3-none-any.whl → 8.3.90__py3-none-any.whl

ultralytics/solutions/instance_segmentation.py

@@ -1,4 +1,4 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from ultralytics.solutions.solutions import BaseSolution, SolutionAnnotator, SolutionResults
 from ultralytics.utils.plotting import colors
@@ -13,9 +13,15 @@ class InstanceSegmentation(BaseSolution):
 
     Attributes:
         model (str): The segmentation model to use for inference.
+        line_width (int): Width of the bounding box and text lines.
+        names (Dict[int, str]): Dictionary mapping class indices to class names.
+        clss (List[int]): List of detected class indices.
+        track_ids (List[int]): List of track IDs for detected instances.
+        masks (List[numpy.ndarray]): List of segmentation masks for detected instances.
 
     Methods:
-        process: Processes the input image to perform instance segmentation and annotate results.
+        process: Process the input image to perform instance segmentation and annotate results.
+        extract_tracks: Extract tracks including bounding boxes, classes, and masks from model predictions.
 
     Examples:
         >>> segmenter = InstanceSegmentation()
@@ -26,7 +32,7 @@ class InstanceSegmentation(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes 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.
@@ -37,7 +43,7 @@ class InstanceSegmentation(BaseSolution):
 
     def process(self, im0):
         """
-        Performs instance segmentation on the input image and annotates the results.
+        Perform instance segmentation on the input image and annotate the results.
 
         Args:
             im0 (numpy.ndarray): The input image for segmentation.

ultralytics/solutions/object_blurrer.py

@@ -34,7 +34,7 @@ class ObjectBlurrer(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes 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.
@@ -49,7 +49,7 @@ class ObjectBlurrer(BaseSolution):
 
     def process(self, im0):
         """
-        Applies 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.

ultralytics/solutions/object_counter.py

@@ -127,7 +127,7 @@ class ObjectCounter(BaseSolution):
 
     def display_counts(self, plot_im):
         """
-        Displays object counts on the input image or frame.
+        Display object counts on the input image or frame.
 
         Args:
             plot_im (numpy.ndarray): The image or frame to display counts on.
@@ -148,7 +148,7 @@ class ObjectCounter(BaseSolution):
 
     def process(self, im0):
         """
-        Processes input data (frames or object tracks) and updates object counts.
+        Process input data (frames or object tracks) and update object counts.
 
         This method initializes the counting region, extracts tracks, draws bounding boxes and regions, updates
         object counts, and displays the results on the input image.

ultralytics/solutions/object_cropper.py

@@ -32,7 +32,7 @@ class ObjectCropper(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes the ObjectCropper class for cropping objects from detected bounding boxes.
+        Initialize the ObjectCropper class for cropping objects from detected bounding boxes.
 
         Args:
             **kwargs (Any): Keyword arguments passed to the parent class and used for configuration.
@@ -53,7 +53,7 @@ class ObjectCropper(BaseSolution):
 
     def process(self, im0):
         """
-        Crops detected objects from the input image and saves them as separate images.
+        Crop detected objects from the input image and save them as separate images.
 
         Args:
             im0 (numpy.ndarray): The input image containing detected objects.

ultralytics/solutions/parking_management.py

@@ -47,7 +47,7 @@ class ParkingPtsSelection:
     """
 
     def __init__(self):
-        """Initializes the ParkingPtsSelection class, setting up UI and properties for parking zone point selection."""
+        """Initialize the ParkingPtsSelection class, setting up UI and properties for parking zone point selection."""
         try:  # check if tkinter installed
             import tkinter as tk
             from tkinter import filedialog, messagebox
@@ -106,7 +106,7 @@ class ParkingPtsSelection:
         self.canvas_max_width, self.canvas_max_height = 1280, 720
 
     def upload_image(self):
-        """Uploads and displays an image on the canvas, resizing it to fit within specified dimensions."""
+        """Upload and display an image on the canvas, resizing it to fit within specified dimensions."""
         from PIL import Image, ImageTk  # scope because ImageTk requires tkinter package
 
         self.image = Image.open(self.filedialog.askopenfilename(filetypes=[("Image Files", "*.png *.jpg *.jpeg")]))
@@ -130,7 +130,7 @@ class ParkingPtsSelection:
         self.rg_data.clear(), self.current_box.clear()
 
     def on_canvas_click(self, event):
-        """Handles mouse clicks to add points for bounding boxes on the canvas."""
+        """Handle mouse clicks to add points for bounding boxes on the canvas."""
         self.current_box.append((event.x, event.y))
         self.canvas.create_oval(event.x - 3, event.y - 3, event.x + 3, event.y + 3, fill="red")
         if len(self.current_box) == 4:
@@ -139,12 +139,12 @@ class ParkingPtsSelection:
             self.current_box.clear()
 
     def draw_box(self, box):
-        """Draws a bounding box on the canvas using the provided coordinates."""
+        """Draw a bounding box on the canvas using the provided coordinates."""
         for i in range(4):
             self.canvas.create_line(box[i], box[(i + 1) % 4], fill="blue", width=2)
 
     def remove_last_bounding_box(self):
-        """Removes the last bounding box from the list and redraws the canvas."""
+        """Remove the last bounding box from the list and redraw the canvas."""
         if not self.rg_data:
             self.messagebox.showwarning("Warning", "No bounding boxes to remove.")
             return
@@ -152,14 +152,14 @@ class ParkingPtsSelection:
         self.redraw_canvas()
 
     def redraw_canvas(self):
-        """Redraws the canvas with the image and all bounding boxes."""
+        """Redraw the canvas with the image and all bounding boxes."""
         self.canvas.delete("all")
         self.canvas.create_image(0, 0, anchor=self.tk.NW, image=self.canvas_image)
         for box in self.rg_data:
             self.draw_box(box)
 
     def save_to_json(self):
-        """Saves the selected parking zone points to a JSON file with scaled coordinates."""
+        """Save the selected parking zone points to a JSON file with scaled coordinates."""
         scale_w, scale_h = self.imgw / self.canvas.winfo_width(), self.imgh / self.canvas.winfo_height()
         data = [{"points": [(int(x * scale_w), int(y * scale_h)) for x, y in box]} for box in self.rg_data]
 
@@ -198,7 +198,7 @@ class ParkingManagement(BaseSolution):
     """
 
     def __init__(self, **kwargs):
-        """Initializes the parking management system with a YOLO model and visualization settings."""
+        """Initialize the parking management system with a YOLO model and visualization settings."""
         super().__init__(**kwargs)
 
         self.json_file = self.CFG["json_file"]  # Load JSON data
@@ -217,7 +217,7 @@ class ParkingManagement(BaseSolution):
 
     def process(self, im0):
         """
-        Processes the input image for parking lot management and visualization.
+        Process the input image for parking lot management and visualization.
 
         This function analyzes the input image, extracts tracks, and determines the occupancy status of parking
         regions defined in the JSON file. It annotates the image with occupied and available parking spots,

ultralytics/solutions/queue_management.py

@@ -45,7 +45,7 @@ class QueueManager(BaseSolution):
 
     def process(self, im0):
         """
-        Processes the queue management for a single frame of video.
+        Process queue management for a single frame of video.
 
         Args:
             im0 (numpy.ndarray): Input image for processing, typically a frame from a video stream.

ultralytics/solutions/region_counter.py

@@ -42,7 +42,7 @@ class RegionCounter(BaseSolution):
 
     def add_region(self, name, polygon_points, region_color, text_color):
         """
-        Adds a new region to the counting list based on the provided template with specific attributes.
+        Add a new region to the counting list based on the provided template with specific attributes.
 
         Args:
             name (str): Name assigned to the new region.
@@ -63,7 +63,7 @@ class RegionCounter(BaseSolution):
 
     def process(self, im0):
         """
-        Processes the input frame to detect and count objects within each defined region.
+        Process the input frame to detect and count objects within each defined region.
 
         Args:
             im0 (np.ndarray): Input image frame where objects and regions are annotated.

ultralytics/solutions/security_alarm.py

@@ -21,9 +21,9 @@ class SecurityAlarm(BaseSolution):
         from_email (str): Sender's email address for alerts.
 
     Methods:
-        authenticate: Sets up email server authentication for sending alerts.
-        send_email: Sends an email notification with details and an image attachment.
-        process: Monitors the frame, processes detections, and triggers alerts if thresholds are crossed.
+        authenticate: Set up email server authentication for sending alerts.
+        send_email: Send an email notification with details and an image attachment.
+        process: Monitor the frame, process detections, and trigger alerts if thresholds are crossed.
 
     Examples:
         >>> security = SecurityAlarm()
@@ -34,7 +34,7 @@ class SecurityAlarm(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes the SecurityAlarm class with parameters for real-time object monitoring.
+        Initialize the SecurityAlarm class with parameters for real-time object monitoring.
 
         Args:
             **kwargs (Any): Additional keyword arguments passed to the parent class.
@@ -48,7 +48,7 @@ class SecurityAlarm(BaseSolution):
 
     def authenticate(self, from_email, password, to_email):
         """
-        Authenticates the email server for sending alert notifications.
+        Authenticate the email server for sending alert notifications.
 
         Args:
             from_email (str): Sender's email address.
@@ -71,7 +71,7 @@ class SecurityAlarm(BaseSolution):
 
     def send_email(self, im0, records=5):
         """
-        Sends an email notification with an image attachment indicating the number of objects detected.
+        Send an email notification with an image attachment indicating the number of objects detected.
 
         Args:
             im0 (numpy.ndarray): The input image or frame to be attached to the email.
@@ -116,7 +116,7 @@ class SecurityAlarm(BaseSolution):
 
     def process(self, im0):
         """
-        Monitors the frame, processes object detections, and triggers alerts if thresholds are exceeded.
+        Monitor the frame, process object detections, and trigger alerts if thresholds are exceeded.
 
         Args:
             im0 (numpy.ndarray): The input image or frame to be processed and annotated.

ultralytics/solutions/solutions.py

@@ -86,13 +86,13 @@ class BaseSolution:
         # Load Model and store classes names
         if self.CFG["model"] is None:
             self.CFG["model"] = "yolo11n.pt"
-        self.model = YOLO(self.CFG["model"], verbose=self.CFG["verbose"])
+        self.model = YOLO(self.CFG["model"])
         self.names = self.model.names
         self.classes = self.CFG["classes"]
 
         self.track_add_args = {  # Tracker additional arguments for advance configuration
-            k: self.CFG[k] for k in ["iou", "conf", "device", "max_det", "half", "tracker", "device"]
-        }
+            k: self.CFG[k] for k in ["iou", "conf", "device", "max_det", "half", "tracker", "device", "verbose"]
+        }  # verbose must be passed to track method; setting it False in YOLO still logs the track information.
 
         if is_cli and self.CFG["source"] is None:
             d_s = "solutions_ci_demo.mp4" if "-pose" not in self.CFG["model"] else "solution_ci_pose_demo.mp4"
@@ -193,7 +193,10 @@ class BaseSolution:
 
     def __call__(self, *args, **kwargs):
         """Allow instances to be called like a function with flexible arguments."""
-        return self.process(*args, **kwargs)  # Call the subclass-specific process method
+        result = self.process(*args, **kwargs)  # Call the subclass-specific process method
+        if self.CFG["verbose"]:  # extract verbose value to display the output logs if True
+            LOGGER.info(f"🚀 Results: {result}")
+        return result
 
 
 class SolutionAnnotator(Annotator):

ultralytics/solutions/speed_estimation.py

@@ -40,7 +40,7 @@ class SpeedEstimator(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes the SpeedEstimator object with speed estimation parameters and data structures.
+        Initialize the SpeedEstimator object with speed estimation parameters and data structures.
 
         Args:
             **kwargs (Any): Additional keyword arguments passed to the parent class.
@@ -56,7 +56,7 @@ class SpeedEstimator(BaseSolution):
 
     def process(self, im0):
         """
-        Processes an input frame to estimate object speeds based on tracking data.
+        Process an input frame to estimate object speeds based on tracking data.
 
         Args:
             im0 (np.ndarray): Input image for processing with shape (H, W, C) for RGB images.

ultralytics/solutions/streamlit_inference.py

@@ -29,7 +29,7 @@ class Inference:
         iou (float): IoU threshold for non-maximum suppression.
         org_frame (Any): Container for the original frame to be displayed.
         ann_frame (Any): Container for the annotated frame to be displayed.
-        vid_file_name (Union[str, int]): Name of the uploaded video file or webcam index.
+        vid_file_name (str | int): Name of the uploaded video file or webcam index.
         selected_ind (List[int]): List of selected class indices for detection.
 
     Methods:
@@ -46,7 +46,7 @@ class Inference:
 
     def __init__(self, **kwargs: Any):
         """
-        Initializes the Inference class, checking Streamlit requirements and setting up the model path.
+        Initialize the Inference class, checking Streamlit requirements and setting up the model path.
 
         Args:
             **kwargs (Any): Additional keyword arguments for model configuration.
@@ -92,7 +92,7 @@ class Inference:
         self.st.markdown(sub_title_cfg, unsafe_allow_html=True)
 
     def sidebar(self):
-        """Configures the Streamlit sidebar for model and inference settings."""
+        """Configure the Streamlit sidebar for model and inference settings."""
         with self.st.sidebar:  # Add Ultralytics LOGO
             logo = "https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Original.svg"
             self.st.image(logo, width=250)
@@ -113,7 +113,7 @@ class Inference:
         self.ann_frame = col2.empty()  # Container for annotated frame
 
     def source_upload(self):
-        """Handles video file uploads through the Streamlit interface."""
+        """Handle video file uploads through the Streamlit interface."""
         self.vid_file_name = ""
         if self.source == "video":
             vid_file = self.st.sidebar.file_uploader("Upload Video File", type=["mp4", "mov", "avi", "mkv"])
@@ -126,7 +126,7 @@ class Inference:
             self.vid_file_name = 0  # Use webcam index 0
 
     def configure(self):
-        """Configures the model and loads selected classes for inference."""
+        """Configure the model and load selected classes for inference."""
         # Add dropdown menu for model selection
         available_models = [x.replace("yolo", "YOLO") for x in GITHUB_ASSETS_STEMS if x.startswith("yolo11")]
         if self.model_path:  # If user provided the custom model, insert model without suffix as *.pt is added later
@@ -146,7 +146,7 @@ class Inference:
             self.selected_ind = list(self.selected_ind)
 
     def inference(self):
-        """Performs real-time object detection inference on video or webcam feed."""
+        """Perform real-time object detection inference on video or webcam feed."""
         self.web_ui()  # Initialize the web interface
         self.sidebar()  # Create the sidebar
         self.source_upload()  # Upload the video source

ultralytics/solutions/trackzone.py

@@ -16,9 +16,16 @@ class TrackZone(BaseSolution):
 
     Attributes:
         region (np.ndarray): The polygonal region for tracking, represented as a convex hull of points.
+        line_width (int): Width of the lines used for drawing bounding boxes and region boundaries.
+        names (List[str]): List of class names that the model can detect.
+        boxes (List[np.ndarray]): Bounding boxes of tracked objects.
+        track_ids (List[int]): Unique identifiers for each tracked object.
+        clss (List[int]): Class indices of tracked objects.
 
     Methods:
         process: Processes each frame of the video, applying region-based tracking.
+        extract_tracks: Extracts tracking information from the input frame.
+        display_output: Displays the processed output.
 
     Examples:
         >>> tracker = TrackZone()
@@ -29,7 +36,7 @@ class TrackZone(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes the TrackZone class for tracking objects within a defined region in video streams.
+        Initialize the TrackZone class for tracking objects within a defined region in video streams.
 
         Args:
             **kwargs (Any): Additional keyword arguments passed to the parent class.
@@ -40,7 +47,7 @@ class TrackZone(BaseSolution):
 
     def process(self, im0):
         """
-        Processes the input frame to track objects within a defined region.
+        Process the input frame to track objects within a defined region.
 
         This method initializes the annotator, creates a mask for the specified region, extracts tracks
         only from the masked area, and updates tracking information. Objects outside the region are ignored.

ultralytics/solutions/vision_eye.py

@@ -13,10 +13,10 @@ class VisionEye(BaseSolution):
     mapping vision points, and annotating results with bounding boxes and labels.
 
     Attributes:
-        vision_point (Tuple[int, int]): Coordinates where vision will view objects and draw tracks, default is (30, 30).
+        vision_point (Tuple[int, int]): Coordinates (x, y) where vision will view objects and draw tracks.
 
     Methods:
-        process: Processes the input image to detect objects, annotate them, and apply vision mapping.
+        process: Process the input image to detect objects, annotate them, and apply vision mapping.
 
     Examples:
         >>> vision_eye = VisionEye()
@@ -27,7 +27,7 @@ class VisionEye(BaseSolution):
 
     def __init__(self, **kwargs):
         """
-        Initializes the VisionEye class for detecting objects and applying vision mapping.
+        Initialize the VisionEye class for detecting objects and applying vision mapping.
 
         Args:
             **kwargs (Any): Keyword arguments passed to the parent class and for configuring vision_point.
@@ -38,7 +38,7 @@ class VisionEye(BaseSolution):
 
     def process(self, im0):
         """
-        Performs object detection, vision mapping, and annotation on the input image.
+        Perform object detection, vision mapping, and annotation on the input image.
 
         Args:
             im0 (numpy.ndarray): The input image for detection and annotation.

ultralytics/trackers/basetrack.py

@@ -67,7 +67,7 @@ class BaseTrack:
 
     def __init__(self):
         """
-        Initializes a new track with a unique ID and foundational tracking attributes.
+        Initialize a new track with a unique ID and foundational tracking attributes.
 
         Examples:
             Initialize a new track

ultralytics/trackers/bot_sort.py

@@ -28,14 +28,14 @@ class BOTrack(STrack):
         covariance (np.ndarray): The covariance matrix of the Kalman filter.
 
     Methods:
-        update_features(feat): Update features vector and smooth it using exponential moving average.
-        predict(): Predicts the mean and covariance using Kalman filter.
-        re_activate(new_track, frame_id, new_id): Reactivates a track with updated features and optionally new ID.
-        update(new_track, frame_id): Update the YOLOv8 instance with new track and frame ID.
+        update_features: Update features vector and smooth it using exponential moving average.
+        predict: Predict the mean and covariance using Kalman filter.
+        re_activate: Reactivate a track with updated features and optionally new ID.
+        update: Update the track with new detection and frame ID.
         tlwh: Property that gets the current position in tlwh format `(top left x, top left y, width, height)`.
-        multi_predict(stracks): Predicts the mean and covariance of multiple object tracks using shared Kalman filter.
-        convert_coords(tlwh): Converts tlwh bounding box coordinates to xywh format.
-        tlwh_to_xywh(tlwh): Convert bounding box to xywh format `(center x, center y, width, height)`.
+        multi_predict: Predict the mean and covariance of multiple object tracks using shared Kalman filter.
+        convert_coords: Convert tlwh bounding box coordinates to xywh format.
+        tlwh_to_xywh: Convert bounding box to xywh format `(center x, center y, width, height)`.
 
     Examples:
         Create a BOTrack instance and update its features
@@ -87,7 +87,7 @@ class BOTrack(STrack):
         self.smooth_feat /= np.linalg.norm(self.smooth_feat)
 
     def predict(self):
-        """Predicts the object's future state using the Kalman filter to update its mean and covariance."""
+        """Predict the object's future state using the Kalman filter to update its mean and covariance."""
         mean_state = self.mean.copy()
         if self.state != TrackState.Tracked:
             mean_state[6] = 0
@@ -96,20 +96,20 @@ class BOTrack(STrack):
         self.mean, self.covariance = self.kalman_filter.predict(mean_state, self.covariance)
 
     def re_activate(self, new_track, frame_id, new_id=False):
-        """Reactivates a track with updated features and optionally assigns a new ID."""
+        """Reactivate a track with updated features and optionally assign a new ID."""
         if new_track.curr_feat is not None:
             self.update_features(new_track.curr_feat)
         super().re_activate(new_track, frame_id, new_id)
 
     def update(self, new_track, frame_id):
-        """Updates the YOLOv8 instance with new track information and the current frame ID."""
+        """Update the track with new detection information and the current frame ID."""
         if new_track.curr_feat is not None:
             self.update_features(new_track.curr_feat)
         super().update(new_track, frame_id)
 
     @property
     def tlwh(self):
-        """Returns the current bounding box position in `(top left x, top left y, width, height)` format."""
+        """Return the current bounding box position in `(top left x, top left y, width, height)` format."""
         if self.mean is None:
             return self._tlwh.copy()
         ret = self.mean[:4].copy()
@@ -118,7 +118,7 @@ class BOTrack(STrack):
 
     @staticmethod
     def multi_predict(stracks):
-        """Predicts the mean and covariance for multiple object tracks using a shared Kalman filter."""
+        """Predict the mean and covariance for multiple object tracks using a shared Kalman filter."""
         if len(stracks) <= 0:
             return
         multi_mean = np.asarray([st.mean.copy() for st in stracks])
@@ -133,7 +133,7 @@ class BOTrack(STrack):
             stracks[i].covariance = cov
 
     def convert_coords(self, tlwh):
-        """Converts tlwh bounding box coordinates to xywh format."""
+        """Convert tlwh bounding box coordinates to xywh format."""
         return self.tlwh_to_xywh(tlwh)
 
     @staticmethod
@@ -156,10 +156,11 @@ class BOTSORT(BYTETracker):
         args (Any): Parsed command-line arguments containing tracking parameters.
 
     Methods:
-        get_kalmanfilter(): Returns an instance of KalmanFilterXYWH for object tracking.
-        init_track(dets, scores, cls, img): Initialize track with detections, scores, and classes.
-        get_dists(tracks, detections): Get distances between tracks and detections using IoU and (optionally) ReID.
-        multi_predict(tracks): Predict and track multiple objects with YOLOv8 model.
+        get_kalmanfilter: Return an instance of KalmanFilterXYWH for object tracking.
+        init_track: Initialize track with detections, scores, and classes.
+        get_dists: Get distances between tracks and detections using IoU and (optionally) ReID.
+        multi_predict: Predict and track multiple objects with YOLOv8 model.
+        reset: Reset the BOTSORT tracker to its initial state.
 
     Examples:
         Initialize BOTSORT and process detections
@@ -173,7 +174,7 @@ class BOTSORT(BYTETracker):
 
     def __init__(self, args, frame_rate=30):
         """
-        Initialize YOLOv8 object with ReID module and GMC algorithm.
+        Initialize BOTSORT object with ReID module and GMC algorithm.
 
         Args:
             args (object): Parsed command-line arguments containing tracking parameters.
@@ -195,7 +196,7 @@ class BOTSORT(BYTETracker):
         self.gmc = GMC(method=args.gmc_method)
 
     def get_kalmanfilter(self):
-        """Returns an instance of KalmanFilterXYWH for predicting and updating object states in the tracking process."""
+        """Return an instance of KalmanFilterXYWH for predicting and updating object states in the tracking process."""
         return KalmanFilterXYWH()
 
     def init_track(self, dets, scores, cls, img=None):
@@ -209,7 +210,7 @@ class BOTSORT(BYTETracker):
             return [BOTrack(xyxy, s, c) for (xyxy, s, c) in zip(dets, scores, cls)]  # detections
 
     def get_dists(self, tracks, detections):
-        """Calculates distances between tracks and detections using IoU and optionally ReID embeddings."""
+        """Calculate distances between tracks and detections using IoU and optionally ReID embeddings."""
         dists = matching.iou_distance(tracks, detections)
         dists_mask = dists > self.proximity_thresh
 
@@ -224,10 +225,10 @@ class BOTSORT(BYTETracker):
         return dists
 
     def multi_predict(self, tracks):
-        """Predicts the mean and covariance of multiple object tracks using a shared Kalman filter."""
+        """Predict the mean and covariance of multiple object tracks using a shared Kalman filter."""
         BOTrack.multi_predict(tracks)
 
     def reset(self):
-        """Resets the BOTSORT tracker to its initial state, clearing all tracked objects and internal states."""
+        """Reset the BOTSORT tracker to its initial state, clearing all tracked objects and internal states."""
         super().reset()
         self.gmc.reset_params()

ultralytics/trackers/byte_tracker.py

@@ -17,7 +17,7 @@ class STrack(BaseTrack):
     and predictions based on Kalman filter.
 
     Attributes:
-        shared_kalman (KalmanFilterXYAH): Shared Kalman filter that is used across all STrack instances for prediction.
+        shared_kalman (KalmanFilterXYAH): Shared Kalman filter used across all STrack instances for prediction.
         _tlwh (np.ndarray): Private attribute to store top-left corner coordinates and width and height of bounding box.
         kalman_filter (KalmanFilterXYAH): Instance of Kalman filter used for this particular object track.
         mean (np.ndarray): Mean state estimate vector.
@@ -236,9 +236,9 @@ class BYTETracker:
     """
     BYTETracker: A tracking algorithm built on top of YOLOv8 for object detection and tracking.
 
-    Responsible for initializing, updating, and managing the tracks for detected objects in a video sequence.
-    It maintains the state of tracked, lost, and removed tracks over frames, utilizes Kalman filtering for predicting
-    the new object locations, and performs data association.
+    This class encapsulates the functionality for initializing, updating, and managing the tracks for detected objects in a
+    video sequence. It maintains the state of tracked, lost, and removed tracks over frames, utilizes Kalman filtering for
+    predicting the new object locations, and performs data association.
 
     Attributes:
         tracked_stracks (List[STrack]): List of successfully activated tracks.

ultralytics/trackers/track.py

@@ -25,6 +25,7 @@ def on_predict_start(predictor: object, persist: bool = False) -> None:
 
     Raises:
         AssertionError: If the tracker_type is not 'bytetrack' or 'botsort'.
+        ValueError: If the task is 'classify' as classification doesn't support tracking.
 
     Examples:
         Initialize trackers for a predictor object:
@@ -47,7 +48,7 @@ def on_predict_start(predictor: object, persist: bool = False) -> None:
     for _ in range(predictor.dataset.bs):
         tracker = TRACKER_MAP[cfg.tracker_type](args=cfg, frame_rate=30)
         trackers.append(tracker)
-        if predictor.dataset.mode != "stream":  # only need one tracker for other modes.
+        if predictor.dataset.mode != "stream":  # only need one tracker for other modes
             break
     predictor.trackers = trackers
     predictor.vid_path = [None] * predictor.dataset.bs  # for determining when to reset tracker on new video