ultralytics 8.3.11__tar.gz → 8.3.13__tar.gz

{ultralytics-8.3.11/ultralytics.egg-info → ultralytics-8.3.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.11
+Version: 8.3.13
 Summary: Ultralytics YOLO for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -72,10 +72,9 @@ Requires-Dist: keras; extra == "export"
 Requires-Dist: flatbuffers<100,>=23.5.26; platform_machine == "aarch64" and extra == "export"
 Requires-Dist: numpy==1.23.5; platform_machine == "aarch64" and extra == "export"
 Requires-Dist: h5py!=3.11.0; platform_machine == "aarch64" and extra == "export"
-Provides-Extra: explorer
-Requires-Dist: lancedb; extra == "explorer"
-Requires-Dist: duckdb<=0.9.2; extra == "explorer"
-Requires-Dist: streamlit; extra == "explorer"
+Provides-Extra: solutions
+Requires-Dist: shapely>=2.0.0; extra == "solutions"
+Requires-Dist: streamlit; extra == "solutions"
 Provides-Extra: logging
 Requires-Dist: comet; extra == "logging"
 Requires-Dist: tensorboard>=2.13.0; extra == "logging"

{ultralytics-8.3.11 → ultralytics-8.3.13}/pyproject.toml

@@ -107,10 +107,9 @@ export = [
     "numpy==1.23.5; platform_machine == 'aarch64'", # fix error: `np.bool` was a deprecated alias for the builtin `bool` when using TensorRT models on NVIDIA Jetson
     "h5py!=3.11.0; platform_machine == 'aarch64'", # fix h5py build issues due to missing aarch64 wheels in 3.11 release
 ]
-explorer = [
-    "lancedb", # vector search
-    "duckdb<=0.9.2", # SQL queries, duckdb==0.10.0 bug https://github.com/ultralytics/ultralytics/pull/8181
-    "streamlit", # visualizing with GUI
+solutions = [
+    "shapely>=2.0.0",    # shapely for point and polygon data matching
+    "streamlit",    # for live inference on web browser i.e `yolo streamlit-predict`
 ]
 logging = [
     "comet", # https://docs.ultralytics.com/integrations/comet/

{ultralytics-8.3.11 → ultralytics-8.3.13}/tests/test_cli.py

@@ -97,9 +97,12 @@ def test_mobilesam():
     # Source
     source = ASSETS / "zidane.jpg"
 
-    # Predict a segment based on a point prompt
+    # Predict a segment based on a 1D point prompt and 1D labels.
     model.predict(source, points=[900, 370], labels=[1])
 
+    # Predict a segment based on 3D points and 2D labels (multiple points per object).
+    model.predict(source, points=[[[900, 370], [1000, 100]]], labels=[[1, 1]])
+
     # Predict a segment based on a box prompt
     model.predict(source, bboxes=[439, 437, 524, 709], save=True)
 

{ultralytics-8.3.11 → ultralytics-8.3.13}/tests/test_cuda.py

@@ -127,9 +127,21 @@ def test_predict_sam():
     # Run inference with bboxes prompt
     model(SOURCE, bboxes=[439, 437, 524, 709], device=0)
 
-    # Run inference with points prompt
+    # Run inference with no labels
+    model(ASSETS / "zidane.jpg", points=[900, 370], device=0)
+
+    # Run inference with 1D points and 1D labels
     model(ASSETS / "zidane.jpg", points=[900, 370], labels=[1], device=0)
 
+    # Run inference with 2D points and 1D labels
+    model(ASSETS / "zidane.jpg", points=[[900, 370]], labels=[1], device=0)
+
+    # Run inference with multiple 2D points and 1D labels
+    model(ASSETS / "zidane.jpg", points=[[400, 370], [900, 370]], labels=[1, 1], device=0)
+
+    # Run inference with 3D points and 2D labels (multiple points per object)
+    model(ASSETS / "zidane.jpg", points=[[[900, 370], [1000, 100]]], labels=[[1, 1]], device=0)
+
     # Create SAMPredictor
     overrides = dict(conf=0.25, task="segment", mode="predict", imgsz=1024, model=WEIGHTS_DIR / "mobile_sam.pt")
     predictor = SAMPredictor(overrides=overrides)

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.11"
+__version__ = "8.3.13"
 
 import os
 
@@ -8,7 +8,6 @@ import os
 if not os.environ.get("OMP_NUM_THREADS"):
     os.environ["OMP_NUM_THREADS"] = "1"  # default for reduced CPU utilization during training
 
-from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import NAS, RTDETR, SAM, YOLO, FastSAM, YOLOWorld
 from ultralytics.utils import ASSETS, SETTINGS
 from ultralytics.utils.checks import check_yolo as checks
@@ -27,5 +26,4 @@ __all__ = (
     "checks",
     "download",
     "settings",
-    "Explorer",
 )

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/cfg/__init__.py

@@ -79,14 +79,11 @@ CLI_HELP_MSG = f"""
 
     4. Export a YOLO11n classification model to ONNX format at image size 224 by 128 (no TASK required)
         yolo export model=yolo11n-cls.pt format=onnx imgsz=224,128
-
-    5. Explore your datasets using semantic search and SQL with a simple GUI powered by Ultralytics Explorer API
-        yolo explorer data=data.yaml model=yolo11n.pt
     
-    6. Streamlit real-time webcam inference GUI
+    5. Streamlit real-time webcam inference GUI
         yolo streamlit-predict
         
-    7. Run special commands:
+    6. Run special commands:
         yolo help
         yolo checks
         yolo version
@@ -546,35 +543,6 @@ def handle_yolo_settings(args: List[str]) -> None:
         LOGGER.warning(f"WARNING ⚠️ settings error: '{e}'. Please see {url} for help.")
 
 
-def handle_explorer(args: List[str]):
-    """
-    Launches a graphical user interface that provides tools for interacting with and analyzing datasets using the
-    Ultralytics Explorer API. It checks for the required 'streamlit' package and informs the user that the Explorer
-    dashboard is loading.
-
-    Args:
-        args (List[str]): A list of optional command line arguments.
-
-    Examples:
-        ```bash
-        yolo explorer data=data.yaml model=yolo11n.pt
-        ```
-
-    Notes:
-        - Requires 'streamlit' package version 1.29.0 or higher.
-        - The function does not take any arguments or return any values.
-        - It is typically called from the command line interface using the 'yolo explorer' command.
-    """
-    checks.check_requirements("streamlit>=1.29.0")
-    LOGGER.info("💡 Loading Explorer dashboard...")
-    cmd = ["streamlit", "run", ROOT / "data/explorer/gui/dash.py", "--server.maxMessageSize", "2048"]
-    new = dict(parse_key_value_pair(a) for a in args)
-    check_dict_alignment(base={k: DEFAULT_CFG_DICT[k] for k in ["model", "data"]}, custom=new)
-    for k, v in new.items():
-        cmd += [k, v]
-    subprocess.run(cmd)
-
-
 def handle_streamlit_inference():
     """
     Open the Ultralytics Live Inference Streamlit app for real-time object detection.
@@ -715,7 +683,6 @@ def entrypoint(debug=""):
         "login": lambda: handle_yolo_hub(args),
         "logout": lambda: handle_yolo_hub(args),
         "copy-cfg": copy_default_cfg,
-        "explorer": lambda: handle_explorer(args[1:]),
         "streamlit-predict": lambda: handle_streamlit_inference(),
     }
     full_args_dict = {**DEFAULT_CFG_DICT, **{k: None for k in TASKS}, **{k: None for k in MODES}, **special}

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/cfg/solutions/default.yaml

@@ -14,3 +14,4 @@ up_angle: 145.0 # Workouts up_angle for counts, 145.0 is default value. You can
 down_angle: 90 # Workouts down_angle for counts, 90 is default value. You can change it for different workouts, based on position of keypoints.
 kpts: [6, 8, 10] # Keypoints for workouts monitoring, i.e. If you want to consider keypoints for pushups that have mostly values of [6, 8, 10].
 colormap: # Colormap for heatmap, Only OPENCV supported colormaps can be used. By default COLORMAP_PARULA will be used for visualization.
+analytics_type: "line" # Analytics type i.e "line", "pie", "bar" or "area" charts. By default, "line" analytics will be used for processing.

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/engine/exporter.py

@@ -960,7 +960,15 @@ class Exporter:
         LOGGER.info(f"\n{prefix} starting export with Edge TPU compiler {ver}...")
         f = str(tflite_model).replace(".tflite", "_edgetpu.tflite")  # Edge TPU model
 
-        cmd = f'edgetpu_compiler -s -d -k 10 --out_dir "{Path(f).parent}" "{tflite_model}"'
+        cmd = (
+            "edgetpu_compiler "
+            f'--out_dir "{Path(f).parent}" '
+            "--show_operations "
+            "--search_delegate "
+            "--delegate_search_step 30 "
+            "--timeout_sec 180 "
+            f'"{tflite_model}"'
+        )
         LOGGER.info(f"{prefix} running '{cmd}'")
         subprocess.run(cmd, shell=True)
         self._add_tflite_metadata(f)

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/models/sam/predict.py

@@ -213,11 +213,14 @@ class Predictor(BasePredictor):
         Args:
             im (torch.Tensor): Preprocessed input image tensor with shape (N, C, H, W).
             bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
-            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2), in pixels.
-            labels (np.ndarray | List | None): Point prompt labels with shape (N,). 1 for foreground, 0 for background.
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
             masks (np.ndarray | None): Low-res masks from previous predictions with shape (N, H, W). For SAM, H=W=256.
             multimask_output (bool): Flag to return multiple masks for ambiguous prompts.
 
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
         Returns:
             (tuple): Tuple containing:
                 - np.ndarray: Output masks with shape (C, H, W), where C is the number of generated masks.
@@ -232,26 +235,7 @@ class Predictor(BasePredictor):
         """
         features = self.get_im_features(im) if self.features is None else self.features
 
-        src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
-        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
-        # Transform input prompts
-        if points is not None:
-            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
-            points = points[None] if points.ndim == 1 else points
-            # Assuming labels are all positive if users don't pass labels.
-            if labels is None:
-                labels = np.ones(points.shape[0])
-            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
-            points *= r
-            # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
-            points, labels = points[:, None, :], labels[:, None]
-        if bboxes is not None:
-            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
-            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes *= r
-        if masks is not None:
-            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
-
+        bboxes, points, labels, masks = self._prepare_prompts(im.shape[2:], bboxes, points, labels, masks)
         points = (points, labels) if points is not None else None
         # Embed prompts
         sparse_embeddings, dense_embeddings = self.model.prompt_encoder(points=points, boxes=bboxes, masks=masks)
@@ -269,6 +253,48 @@ class Predictor(BasePredictor):
         # `d` could be 1 or 3 depends on `multimask_output`.
         return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)
 
+    def _prepare_prompts(self, dst_shape, bboxes=None, points=None, labels=None, masks=None):
+        """
+        Prepares and transforms the input prompts for processing based on the destination shape.
+
+        Args:
+            dst_shape (tuple): The target shape (height, width) for the prompts.
+            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
+            masks (List | np.ndarray, Optional): Masks for the objects, where each mask is a 2D array.
+
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
+        Returns:
+            (tuple): A tuple containing transformed bounding boxes, points, labels, and masks.
+        """
+        src_shape = self.batch[1][0].shape[:2]
+        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
+        # Transform input prompts
+        if points is not None:
+            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
+            points = points[None] if points.ndim == 1 else points
+            # Assuming labels are all positive if users don't pass labels.
+            if labels is None:
+                labels = np.ones(points.shape[:-1])
+            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
+            assert (
+                points.shape[-2] == labels.shape[-1]
+            ), f"Number of points {points.shape[-2]} should match number of labels {labels.shape[-1]}."
+            points *= r
+            if points.ndim == 2:
+                # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
+                points, labels = points[:, None, :], labels[:, None]
+        if bboxes is not None:
+            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
+            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
+            bboxes *= r
+        if masks is not None:
+            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
+        return bboxes, points, labels, masks
+
     def generate(
         self,
         im,
@@ -686,34 +712,7 @@ class SAM2Predictor(Predictor):
         """
         features = self.get_im_features(im) if self.features is None else self.features
 
-        src_shape, dst_shape = self.batch[1][0].shape[:2], im.shape[2:]
-        r = 1.0 if self.segment_all else min(dst_shape[0] / src_shape[0], dst_shape[1] / src_shape[1])
-        # Transform input prompts
-        if points is not None:
-            points = torch.as_tensor(points, dtype=torch.float32, device=self.device)
-            points = points[None] if points.ndim == 1 else points
-            # Assuming labels are all positive if users don't pass labels.
-            if labels is None:
-                labels = torch.ones(points.shape[0])
-            labels = torch.as_tensor(labels, dtype=torch.int32, device=self.device)
-            points *= r
-            # (N, 2) --> (N, 1, 2), (N, ) --> (N, 1)
-            points, labels = points[:, None], labels[:, None]
-        if bboxes is not None:
-            bboxes = torch.as_tensor(bboxes, dtype=torch.float32, device=self.device)
-            bboxes = bboxes[None] if bboxes.ndim == 1 else bboxes
-            bboxes = bboxes.view(-1, 2, 2) * r
-            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
-            # NOTE: merge "boxes" and "points" into a single "points" input
-            # (where boxes are added at the beginning) to model.sam_prompt_encoder
-            if points is not None:
-                points = torch.cat([bboxes, points], dim=1)
-                labels = torch.cat([bbox_labels, labels], dim=1)
-            else:
-                points, labels = bboxes, bbox_labels
-        if masks is not None:
-            masks = torch.as_tensor(masks, dtype=torch.float32, device=self.device).unsqueeze(1)
-
+        bboxes, points, labels, masks = self._prepare_prompts(im.shape[2:], bboxes, points, labels, masks)
         points = (points, labels) if points is not None else None
 
         sparse_embeddings, dense_embeddings = self.model.sam_prompt_encoder(
@@ -737,6 +736,36 @@ class SAM2Predictor(Predictor):
         # `d` could be 1 or 3 depends on `multimask_output`.
         return pred_masks.flatten(0, 1), pred_scores.flatten(0, 1)
 
+    def _prepare_prompts(self, dst_shape, bboxes=None, points=None, labels=None, masks=None):
+        """
+        Prepares and transforms the input prompts for processing based on the destination shape.
+
+        Args:
+            dst_shape (tuple): The target shape (height, width) for the prompts.
+            bboxes (np.ndarray | List | None): Bounding boxes in XYXY format with shape (N, 4).
+            points (np.ndarray | List | None): Points indicating object locations with shape (N, 2) or (N, num_points, 2), in pixels.
+            labels (np.ndarray | List | None): Point prompt labels with shape (N,) or (N, num_points). 1 for foreground, 0 for background.
+            masks (List | np.ndarray, Optional): Masks for the objects, where each mask is a 2D array.
+
+        Raises:
+            AssertionError: If the number of points don't match the number of labels, in case labels were passed.
+
+        Returns:
+            (tuple): A tuple containing transformed bounding boxes, points, labels, and masks.
+        """
+        bboxes, points, labels, masks = super()._prepare_prompts(dst_shape, bboxes, points, labels, masks)
+        if bboxes is not None:
+            bboxes = bboxes.view(-1, 2, 2)
+            bbox_labels = torch.tensor([[2, 3]], dtype=torch.int32, device=bboxes.device).expand(len(bboxes), -1)
+            # NOTE: merge "boxes" and "points" into a single "points" input
+            # (where boxes are added at the beginning) to model.sam_prompt_encoder
+            if points is not None:
+                points = torch.cat([bboxes, points], dim=1)
+                labels = torch.cat([bbox_labels, labels], dim=1)
+            else:
+                points, labels = bboxes, bbox_labels
+        return bboxes, points, labels, masks
+
     def set_image(self, image):
         """
         Preprocesses and sets a single image for inference using the SAM2 model.

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/models/yolo/classify/train.py

@@ -8,7 +8,7 @@ from ultralytics.data import ClassificationDataset, build_dataloader
 from ultralytics.engine.trainer import BaseTrainer
 from ultralytics.models import yolo
 from ultralytics.nn.tasks import ClassificationModel
-from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK, colorstr
+from ultralytics.utils import DEFAULT_CFG, LOGGER, RANK
 from ultralytics.utils.plotting import plot_images, plot_results
 from ultralytics.utils.torch_utils import is_parallel, strip_optimizer, torch_distributed_zero_first
 
@@ -141,7 +141,6 @@ class ClassificationTrainer(BaseTrainer):
                     self.metrics = self.validator(model=f)
                     self.metrics.pop("fitness", None)
                     self.run_callbacks("on_fit_epoch_end")
-        LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}")
 
     def plot_training_samples(self, batch, ni):
         """Plots training samples with their annotations."""

ultralytics-8.3.13/ultralytics/solutions/analytics.py

@@ -0,0 +1,194 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from itertools import cycle
+
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+from matplotlib.backends.backend_agg import FigureCanvasAgg as FigureCanvas
+from matplotlib.figure import Figure
+
+from ultralytics.solutions.solutions import BaseSolution  # Import a parent class
+
+
+class Analytics(BaseSolution):
+    """A class to create and update various types of charts (line, bar, pie, area) for visual analytics."""
+
+    def __init__(self, **kwargs):
+        """Initialize the Analytics class with various chart types."""
+        super().__init__(**kwargs)
+
+        self.type = self.CFG["analytics_type"]  # extract type of analytics
+        self.x_label = "Classes" if self.type in {"bar", "pie"} else "Frame#"
+        self.y_label = "Total Counts"
+
+        # Predefined data
+        self.bg_color = "#00F344"  # background color of frame
+        self.fg_color = "#111E68"  # foreground color of frame
+        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 = (19.2, 10.8)  # Set output image size 1920 * 1080
+        self.color_cycle = cycle(["#DD00BA", "#042AFF", "#FF4447", "#7D24FF", "#BD00FF"])
+
+        self.total_counts = 0  # count variable for storing total counts i.e for line
+        self.clswise_count = {}  # dictionary for classwise counts
+
+        # Ensure line and area chart
+        if self.type in {"line", "area"}:
+            self.lines = {}
+            self.fig = Figure(facecolor=self.bg_color, figsize=figsize)
+            self.canvas = FigureCanvas(self.fig)  # Set common axis properties
+            self.ax = self.fig.add_subplot(111, facecolor=self.bg_color)
+            if self.type == "line":
+                (self.line,) = self.ax.plot([], [], color="cyan", linewidth=self.line_width)
+        elif self.type in {"bar", "pie"}:
+            # Initialize bar or pie plot
+            self.fig, self.ax = plt.subplots(figsize=figsize, facecolor=self.bg_color)
+            self.canvas = FigureCanvas(self.fig)  # Set common axis properties
+            self.ax.set_facecolor(self.bg_color)
+            self.color_mapping = {}
+            self.ax.axis("equal") if type == "pie" else None  # Ensure pie chart is circular
+
+    def process_data(self, im0, frame_number):
+        """
+        Process the image data, run object tracking.
+
+        Args:
+            im0 (ndarray): Input image for processing.
+            frame_number (int): Video frame # for plotting the data.
+        """
+        self.extract_tracks(im0)  # Extract tracks
+
+        if self.type == "line":
+            for box in self.boxes:
+                self.total_counts += 1
+            im0 = self.update_graph(frame_number=frame_number)
+            self.total_counts = 0
+        elif self.type == "pie" or self.type == "bar" or self.type == "area":
+            self.clswise_count = {}
+            for box, cls in zip(self.boxes, self.clss):
+                if self.names[int(cls)] in self.clswise_count:
+                    self.clswise_count[self.names[int(cls)]] += 1
+                else:
+                    self.clswise_count[self.names[int(cls)]] = 1
+            im0 = self.update_graph(frame_number=frame_number, count_dict=self.clswise_count, plot=self.type)
+        else:
+            raise ModuleNotFoundError(f"{self.type} chart is not supported ❌")
+        return im0
+
+    def update_graph(self, frame_number, count_dict=None, plot="line"):
+        """
+        Update the graph (line or area) with new data for single or multiple classes.
+
+        Args:
+            frame_number (int): The current frame number.
+            count_dict (dict, 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 i.e. line, bar or area.
+        """
+        if count_dict is None:
+            # Single line update
+            x_data = np.append(self.line.get_xdata(), float(frame_number))
+            y_data = np.append(self.line.get_ydata(), float(self.total_counts))
+
+            if len(x_data) > self.max_points:
+                x_data, y_data = x_data[-self.max_points :], y_data[-self.max_points :]
+
+            self.line.set_data(x_data, y_data)
+            self.line.set_label("Counts")
+            self.line.set_color("#7b0068")  # Pink color
+            self.line.set_marker("*")
+            self.line.set_markersize(self.line_width * 5)
+        else:
+            labels = list(count_dict.keys())
+            counts = list(count_dict.values())
+            if plot == "area":
+                color_cycle = cycle(["#DD00BA", "#042AFF", "#FF4447", "#7D24FF", "#BD00FF"])
+                # Multiple lines or area update
+                x_data = self.ax.lines[0].get_xdata() if self.ax.lines else np.array([])
+                y_data_dict = {key: np.array([]) for key in count_dict.keys()}
+                if self.ax.lines:
+                    for line, key in zip(self.ax.lines, count_dict.keys()):
+                        y_data_dict[key] = line.get_ydata()
+
+                x_data = np.append(x_data, float(frame_number))
+                max_length = len(x_data)
+                for key in count_dict.keys():
+                    y_data_dict[key] = np.append(y_data_dict[key], float(count_dict[key]))
+                    if len(y_data_dict[key]) < max_length:
+                        y_data_dict[key] = np.pad(y_data_dict[key], (0, max_length - len(y_data_dict[key])), "constant")
+                if len(x_data) > self.max_points:
+                    x_data = x_data[1:]
+                    for key in count_dict.keys():
+                        y_data_dict[key] = y_data_dict[key][1:]
+
+                self.ax.clear()
+                for key, y_data in y_data_dict.items():
+                    color = next(color_cycle)
+                    self.ax.fill_between(x_data, y_data, color=color, alpha=0.7)
+                    self.ax.plot(
+                        x_data,
+                        y_data,
+                        color=color,
+                        linewidth=self.line_width,
+                        marker="o",
+                        markersize=self.line_width * 5,
+                        label=f"{key} Data Points",
+                    )
+            if plot == "bar":
+                self.ax.clear()  # clear bar data
+                for label in labels:  # Map labels to colors
+                    if label not in self.color_mapping:
+                        self.color_mapping[label] = next(self.color_cycle)
+                colors = [self.color_mapping[label] for label in labels]
+                bars = self.ax.bar(labels, counts, color=colors)
+                for bar, count in zip(bars, counts):
+                    self.ax.text(
+                        bar.get_x() + bar.get_width() / 2,
+                        bar.get_height(),
+                        str(count),
+                        ha="center",
+                        va="bottom",
+                        color=self.fg_color,
+                    )
+                # Create the legend using labels from the bars
+                for bar, label in zip(bars, labels):
+                    bar.set_label(label)  # Assign label to each bar
+                self.ax.legend(loc="upper left", fontsize=13, facecolor=self.fg_color, edgecolor=self.fg_color)
+            if plot == "pie":
+                total = sum(counts)
+                percentages = [size / total * 100 for size in counts]
+                start_angle = 90
+                self.ax.clear()
+
+                # Create pie chart and create legend labels with percentages
+                wedges, autotexts = self.ax.pie(
+                    counts, labels=labels, startangle=start_angle, textprops={"color": self.fg_color}, autopct=None
+                )
+                legend_labels = [f"{label} ({percentage:.1f}%)" for label, percentage in zip(labels, percentages)]
+
+                # Assign the legend using the wedges and manually created labels
+                self.ax.legend(wedges, legend_labels, title="Classes", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
+                self.fig.subplots_adjust(left=0.1, right=0.75)  # Adjust layout to fit the legend
+
+        # Common plot settings
+        self.ax.set_facecolor("#f0f0f0")  # Set to light gray or any other color you like
+        self.ax.set_title(self.title, color=self.fg_color, fontsize=self.fontsize)
+        self.ax.set_xlabel(self.x_label, color=self.fg_color, fontsize=self.fontsize - 3)
+        self.ax.set_ylabel(self.y_label, color=self.fg_color, fontsize=self.fontsize - 3)
+
+        # Add and format legend
+        legend = self.ax.legend(loc="upper left", fontsize=13, facecolor=self.bg_color, edgecolor=self.bg_color)
+        for text in legend.get_texts():
+            text.set_color(self.fg_color)
+
+        # Redraw graph, update view, capture, and display the updated plot
+        self.ax.relim()
+        self.ax.autoscale_view()
+        self.canvas.draw()
+        im0 = np.array(self.canvas.renderer.buffer_rgba())
+        im0 = cv2.cvtColor(im0[:, :, :3], cv2.COLOR_RGBA2BGR)
+        self.display_output(im0)
+
+        return im0  # Return the image

ultralytics-8.3.13/ultralytics/solutions/distance_calculation.py

@@ -0,0 +1,82 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import math
+
+import cv2
+
+from ultralytics.solutions.solutions import BaseSolution  # Import a parent class
+from ultralytics.utils.plotting import Annotator, colors
+
+
+class DistanceCalculation(BaseSolution):
+    """A class to calculate distance between two objects in a real-time video stream based on their tracks."""
+
+    def __init__(self, **kwargs):
+        """Initializes the DistanceCalculation class with the given parameters."""
+        super().__init__(**kwargs)
+
+        # Mouse event information
+        self.left_mouse_count = 0
+        self.selected_boxes = {}
+
+    def mouse_event_for_distance(self, event, x, y, flags, param):
+        """
+        Handles mouse events to select regions in a real-time video stream.
+
+        Args:
+            event (int): Type of mouse event (e.g., cv2.EVENT_MOUSEMOVE, cv2.EVENT_LBUTTONDOWN, etc.).
+            x (int): X-coordinate of the mouse pointer.
+            y (int): Y-coordinate of the mouse pointer.
+            flags (int): Flags associated with the event (e.g., cv2.EVENT_FLAG_CTRLKEY, cv2.EVENT_FLAG_SHIFTKEY, etc.).
+            param (dict): Additional parameters passed to the function.
+        """
+        if event == cv2.EVENT_LBUTTONDOWN:
+            self.left_mouse_count += 1
+            if self.left_mouse_count <= 2:
+                for box, track_id in zip(self.boxes, self.track_ids):
+                    if box[0] < x < box[2] and box[1] < y < box[3] and track_id not in self.selected_boxes:
+                        self.selected_boxes[track_id] = box
+
+        elif event == cv2.EVENT_RBUTTONDOWN:
+            self.selected_boxes = {}
+            self.left_mouse_count = 0
+
+    def calculate(self, im0):
+        """
+        Processes the video frame and calculates the distance between two bounding boxes.
+
+        Args:
+            im0 (ndarray): The image frame.
+
+        Returns:
+            (ndarray): The processed image frame.
+        """
+        self.annotator = Annotator(im0, line_width=self.line_width)  # Initialize annotator
+        self.extract_tracks(im0)  # Extract tracks
+
+        # Iterate over bounding boxes, track ids and classes index
+        for box, track_id, cls in zip(self.boxes, self.track_ids, self.clss):
+            self.annotator.box_label(box, color=colors(int(cls), True), label=self.names[int(cls)])
+
+            if len(self.selected_boxes) == 2:
+                for trk_id in self.selected_boxes.keys():
+                    if trk_id == track_id:
+                        self.selected_boxes[track_id] = box
+
+        if len(self.selected_boxes) == 2:
+            # Store user selected boxes in centroids list
+            self.centroids.extend(
+                [[int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2)] for box in self.selected_boxes.values()]
+            )
+            # Calculate pixels distance
+            pixels_distance = math.sqrt(
+                (self.centroids[0][0] - self.centroids[1][0]) ** 2 + (self.centroids[0][1] - self.centroids[1][1]) ** 2
+            )
+            self.annotator.plot_distance_and_line(pixels_distance, self.centroids)
+
+        self.centroids = []
+
+        self.display_output(im0)  # display output with base class function
+        cv2.setMouseCallback("Ultralytics Solutions", self.mouse_event_for_distance)
+
+        return im0  # return output image for more usage

{ultralytics-8.3.11 → ultralytics-8.3.13}/ultralytics/solutions/object_counter.py

@@ -112,13 +112,13 @@ class ObjectCounter(BaseSolution):
         # Iterate over bounding boxes, track ids and classes index
         for box, track_id, cls in zip(self.boxes, self.track_ids, self.clss):
             # Draw bounding box and counting region
-            self.annotator.box_label(box, label=self.names[cls], color=colors(track_id, True))
+            self.annotator.box_label(box, label=self.names[cls], color=colors(cls, True))
             self.store_tracking_history(track_id, box)  # Store track history
             self.store_classwise_counts(cls)  # store classwise counts in dict
 
             # Draw tracks of objects
             self.annotator.draw_centroid_and_tracks(
-                self.track_line, color=colors(int(track_id), True), track_thickness=self.line_width
+                self.track_line, color=colors(int(cls), True), track_thickness=self.line_width
             )
 
             # store previous position of track for object counting