ultralytics 8.3.50__tar.gz → 8.3.52__tar.gz

{ultralytics-8.3.50/ultralytics.egg-info → ultralytics-8.3.52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.50
+Version: 8.3.52
 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>

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.50"
+__version__ = "8.3.52"
 
 import os
 

ultralytics-8.3.52/ultralytics/cfg/solutions/default.yaml

@@ -0,0 +1,22 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Configuration for Ultralytics Solutions: https://docs.ultralytics.com/solutions/
+
+# Object counting settings  --------------------------------------------------------------------------------------------
+region: # list[tuple[int, int]] object counting, queue or speed estimation region points.
+show_in: True # (bool) flag to display objects moving *into* the defined region
+show_out: True # (bool) flag to display objects moving *out of* the defined region
+
+# Heatmaps settings ----------------------------------------------------------------------------------------------------
+colormap: #  (int | str) colormap for heatmap, Only OPENCV supported colormaps can be used.
+
+# Workouts monitoring settings -----------------------------------------------------------------------------------------
+up_angle: 145.0 # (float) Workouts up_angle for counts, 145.0 is default value.
+down_angle: 90 # (float) Workouts down_angle for counts, 90 is default value. Y
+kpts: [6, 8, 10] # (list[int]) keypoints for workouts monitoring, i.e. for pushups kpts have values of [6, 8, 10].
+
+# Analytics settings ---------------------------------------------------------------------------------------------------
+analytics_type: "line" # (str) analytics type i.e "line", "pie", "bar" or "area" charts.
+json_file: # (str) parking system regions file path.
+
+# Security alarm system settings ---------------------------------------------------------------------------------------
+records: 5 # (int) Total detections count to send an email about security

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/engine/tuner.py

@@ -191,7 +191,7 @@ class Tuner:
             try:
                 # Train YOLO model with mutated hyperparameters (run in subprocess to avoid dataloader hang)
                 cmd = ["yolo", "train", *(f"{k}={v}" for k, v in train_args.items())]
-                return_code = subprocess.run(cmd, check=True).returncode
+                return_code = subprocess.run(" ".join(cmd), check=True, shell=True).returncode
                 ckpt_file = weights_dir / ("best.pt" if (weights_dir / "best.pt").exists() else "last.pt")
                 metrics = torch.load(ckpt_file)["train_metrics"]
                 assert return_code == 0, "training failed"

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/solutions/__init__.py

@@ -8,6 +8,7 @@ from .object_counter import ObjectCounter
 from .parking_management import ParkingManagement, ParkingPtsSelection
 from .queue_management import QueueManager
 from .region_counter import RegionCounter
+from .security_alarm import SecurityAlarm
 from .speed_estimation import SpeedEstimator
 from .streamlit_inference import inference
 from .trackzone import TrackZone
@@ -25,4 +26,5 @@ __all__ = (
     "inference",
     "RegionCounter",
     "TrackZone",
+    "SecurityAlarm",
 )

ultralytics-8.3.52/ultralytics/solutions/security_alarm.py

@@ -0,0 +1,141 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from ultralytics.solutions.solutions import LOGGER, BaseSolution
+from ultralytics.utils.plotting import Annotator, colors
+
+
+class SecurityAlarm(BaseSolution):
+    """
+    A class to manage security alarm functionalities for real-time monitoring.
+
+    This class extends the BaseSolution class and provides features to monitor
+    objects in a frame, send email notifications when specific thresholds are
+    exceeded for total detections, and annotate the output frame for visualization.
+
+    Attributes:
+       email_sent (bool): Flag to track if an email has already been sent for the current event.
+       records (int): Threshold for the number of detected objects to trigger an alert.
+
+    Methods:
+       authenticate: Sets up email server authentication for sending alerts.
+       send_email: Sends an email notification with details and an image attachment.
+       monitor: Monitors the frame, processes detections, and triggers alerts if thresholds are crossed.
+
+    Examples:
+        >>> security = SecurityAlarm()
+        >>> security.authenticate("abc@gmail.com", "1111222233334444", "xyz@gmail.com")
+        >>> frame = cv2.imread("frame.jpg")
+        >>> processed_frame = security.monitor(frame)
+    """
+
+    def __init__(self, **kwargs):
+        """Initializes the SecurityAlarm class with parameters for real-time object monitoring."""
+        super().__init__(**kwargs)
+        self.email_sent = False
+        self.records = self.CFG["records"]
+
+    def authenticate(self, from_email, password, to_email):
+        """
+        Authenticates the email server for sending alert notifications.
+
+        Args:
+            from_email (str): Sender's email address.
+            password (str): Password for the sender's email account.
+            to_email (str): Recipient's email address.
+
+        This method initializes a secure connection with the SMTP server
+        and logs in using the provided credentials.
+
+        Examples:
+            >>> alarm = SecurityAlarm()
+            >>> alarm.authenticate("sender@example.com", "password123", "recipient@example.com")
+        """
+        import smtplib
+
+        self.server = smtplib.SMTP("smtp.gmail.com: 587")
+        self.server.starttls()
+        self.server.login(from_email, password)
+        self.to_email = to_email
+        self.from_email = from_email
+
+    def send_email(self, im0, records=5):
+        """
+        Sends 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.
+            records (int): The number of detected objects to be included in the email message.
+
+        This method encodes the input image, composes the email message with
+        details about the detection, and sends it to the specified recipient.
+
+        Examples:
+            >>> alarm = SecurityAlarm()
+            >>> frame = cv2.imread("path/to/image.jpg")
+            >>> alarm.send_email(frame, records=10)
+        """
+        from email.mime.image import MIMEImage
+        from email.mime.multipart import MIMEMultipart
+        from email.mime.text import MIMEText
+
+        import cv2
+
+        img_bytes = cv2.imencode(".jpg", im0)[1].tobytes()  # Encode the image as JPEG
+
+        # Create the email
+        message = MIMEMultipart()
+        message["From"] = self.from_email
+        message["To"] = self.to_email
+        message["Subject"] = "Security Alert"
+
+        # Add the text message body
+        message_body = f"Ultralytics ALERT!!! " f"{records} objects have been detected!!"
+        message.attach(MIMEText(message_body, "plain"))
+
+        # Attach the image
+        image_attachment = MIMEImage(img_bytes, name="ultralytics.jpg")
+        message.attach(image_attachment)
+
+        # Send the email
+        try:
+            self.server.send_message(message)
+            LOGGER.info("✅ Email sent successfully!")
+        except Exception as e:
+            print(f"❌ Failed to send email: {e}")
+
+    def monitor(self, im0):
+        """
+        Monitors the frame, processes object detections, and triggers alerts if thresholds are exceeded.
+
+        Args:
+            im0 (numpy.ndarray): The input image or frame to be processed and annotated.
+
+        This method processes the input frame, extracts detections, annotates the frame
+        with bounding boxes, and sends an email notification if the number of detected objects
+        surpasses the specified threshold and an alert has not already been sent.
+
+        Returns:
+            (numpy.ndarray): The processed frame with annotations.
+
+        Examples:
+            >>> alarm = SecurityAlarm()
+            >>> frame = cv2.imread("path/to/image.jpg")
+            >>> processed_frame = alarm.monitor(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, cls in zip(self.boxes, self.clss):
+            # Draw bounding box
+            self.annotator.box_label(box, label=self.names[cls], color=colors(cls, True))
+
+        total_det = len(self.clss)
+        if total_det > self.records:  # Only send email If not sent before
+            if not self.email_sent:
+                self.send_email(im0, total_det)
+                self.email_sent = True
+
+        self.display_output(im0)  # display output with base class function
+
+        return im0  # return output image for more usage

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/utils/autobatch.py

@@ -77,18 +77,26 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch, max
         results = profile(img, model, n=1, device=device, max_num_obj=max_num_obj)
 
         # Fit a solution
-        y = [x[2] for x in results if x]  # memory [2]
-        p = np.polyfit(batch_sizes[: len(y)], y, deg=1)  # first degree polynomial fit
-        b = int((f * fraction - p[1]) / p[0])  # y intercept (optimal batch size)
+        xy = [
+            [x, y[2]]
+            for i, (x, y) in enumerate(zip(batch_sizes, results))
+            if y  # valid result
+            and isinstance(y[2], (int, float))  # is numeric
+            and 0 < y[2] < t  # between 0 and GPU limit
+            and (i == 0 or not results[i - 1] or y[2] > results[i - 1][2])  # first item or increasing memory
+        ]
+        fit_x, fit_y = zip(*xy) if xy else ([], [])
+        p = np.polyfit(np.log(fit_x), np.log(fit_y), deg=1)  # first-degree polynomial fit in log space
+        b = int(round(np.exp((np.log(f * fraction) - p[1]) / p[0])))  # y intercept (optimal batch size)
         if None in results:  # some sizes failed
             i = results.index(None)  # first fail index
             if b >= batch_sizes[i]:  # y intercept above failure point
                 b = batch_sizes[max(i - 1, 0)]  # select prior safe point
         if b < 1 or b > 1024:  # b outside of safe range
+            LOGGER.info(f"{prefix}WARNING ⚠️ batch={b} outside safe range, using default batch-size {batch_size}.")
             b = batch_size
-            LOGGER.info(f"{prefix}WARNING ⚠️ CUDA anomaly detected, using default batch-size {batch_size}.")
 
-        fraction = (np.polyval(p, b) + r + a) / t  # actual fraction predicted
+        fraction = (np.exp(np.polyval(p, np.log(b))) + r + a) / t  # predicted fraction
         LOGGER.info(f"{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅")
         return b
     except Exception as e:

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/utils/ops.py

@@ -75,8 +75,13 @@ def segment2box(segment, width=640, height=640):
         (np.ndarray): the minimum and maximum x and y values of the segment.
     """
     x, y = segment.T  # segment xy
-    x = x.clip(0, width)
-    y = y.clip(0, height)
+    # any 3 out of 4 sides are outside the image, clip coordinates first, https://github.com/ultralytics/ultralytics/pull/18294
+    if np.array([x.min() < 0, y.min() < 0, x.max() > width, y.max() > height]).sum() >= 3:
+        x = x.clip(0, width)
+        y = y.clip(0, height)
+    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
+    x = x[inside]
+    y = y[inside]
     return (
         np.array([x.min(), y.min(), x.max(), y.max()], dtype=segment.dtype)
         if any(x)

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics/utils/torch_utils.py

@@ -617,6 +617,32 @@ def convert_optimizer_state_dict_to_fp16(state_dict):
     return state_dict
 
 
+@contextmanager
+def cuda_memory_usage(device=None):
+    """
+    Monitor and manage CUDA memory usage.
+
+    This function checks if CUDA is available and, if so, empties the CUDA cache to free up unused memory.
+    It then yields a dictionary containing memory usage information, which can be updated by the caller.
+    Finally, it updates the dictionary with the amount of memory reserved by CUDA on the specified device.
+
+    Args:
+        device (torch.device, optional): The CUDA device to query memory usage for. Defaults to None.
+
+    Yields:
+        (dict): A dictionary with a key 'memory' initialized to 0, which will be updated with the reserved memory.
+    """
+    cuda_info = dict(memory=0)
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()
+        try:
+            yield cuda_info
+        finally:
+            cuda_info["memory"] = torch.cuda.memory_reserved(device)
+    else:
+        yield cuda_info
+
+
 def profile(input, ops, n=10, device=None, max_num_obj=0):
     """
     Ultralytics speed, memory and FLOPs profiler.
@@ -653,27 +679,31 @@ def profile(input, ops, n=10, device=None, max_num_obj=0):
                 flops = 0
 
             try:
+                mem = 0
                 for _ in range(n):
-                    t[0] = time_sync()
-                    y = m(x)
-                    t[1] = time_sync()
-                    try:
-                        (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward()
-                        t[2] = time_sync()
-                    except Exception:  # no backward method
-                        # print(e)  # for debug
-                        t[2] = float("nan")
+                    with cuda_memory_usage(device) as cuda_info:
+                        t[0] = time_sync()
+                        y = m(x)
+                        t[1] = time_sync()
+                        try:
+                            (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward()
+                            t[2] = time_sync()
+                        except Exception:  # no backward method
+                            # print(e)  # for debug
+                            t[2] = float("nan")
+                    mem += cuda_info["memory"] / 1e9  # (GB)
                     tf += (t[1] - t[0]) * 1000 / n  # ms per op forward
                     tb += (t[2] - t[1]) * 1000 / n  # ms per op backward
                     if max_num_obj:  # simulate training with predictions per image grid (for AutoBatch)
-                        torch.randn(
-                            x.shape[0],
-                            max_num_obj,
-                            int(sum((x.shape[-1] / s) * (x.shape[-2] / s) for s in m.stride.tolist())),
-                            device=device,
-                            dtype=torch.float32,
-                        )
-                mem = torch.cuda.memory_reserved() / 1e9 if torch.cuda.is_available() else 0  # (GB)
+                        with cuda_memory_usage(device) as cuda_info:
+                            torch.randn(
+                                x.shape[0],
+                                max_num_obj,
+                                int(sum((x.shape[-1] / s) * (x.shape[-2] / s) for s in m.stride.tolist())),
+                                device=device,
+                                dtype=torch.float32,
+                            )
+                        mem += cuda_info["memory"] / 1e9  # (GB)
                 s_in, s_out = (tuple(x.shape) if isinstance(x, torch.Tensor) else "list" for x in (x, y))  # shapes
                 p = sum(x.numel() for x in m.parameters()) if isinstance(m, nn.Module) else 0  # parameters
                 LOGGER.info(f"{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}")

{ultralytics-8.3.50 → ultralytics-8.3.52/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.50
+Version: 8.3.52
 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>

{ultralytics-8.3.50 → ultralytics-8.3.52}/ultralytics.egg-info/SOURCES.txt

@@ -204,6 +204,7 @@ ultralytics/solutions/object_counter.py
 ultralytics/solutions/parking_management.py
 ultralytics/solutions/queue_management.py
 ultralytics/solutions/region_counter.py
+ultralytics/solutions/security_alarm.py
 ultralytics/solutions/solutions.py
 ultralytics/solutions/speed_estimation.py
 ultralytics/solutions/streamlit_inference.py

ultralytics-8.3.50/ultralytics/cfg/solutions/default.yaml

@@ -1,19 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Configuration for Ultralytics Solutions
-
-# Object counting settings
-region: # Object counting, queue or speed estimation region points. Default region points are [(20, 400), (1080, 400), (1080, 360), (20, 360)]
-show_in: True # Flag to display objects moving *into* the defined region
-show_out: True # Flag to display objects moving *out of* the defined region
-
-# Heatmaps settings
-colormap: # Colormap for heatmap, Only OPENCV supported colormaps can be used. By default COLORMAP_PARULA will be used for visualization.
-
-# Workouts monitoring settings
-up_angle: 145.0 # Workouts up_angle for counts, 145.0 is default value. You can adjust it for different workouts, based on position of keypoints.
-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].
-
-# Analytics settings
-analytics_type: "line" # Analytics type i.e "line", "pie", "bar" or "area" charts. By default, "line" analytics will be used for processing.
-json_file: # parking system regions file path.