ultralytics 8.0.228__py3-none-any.whl → 8.0.229__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = '8.0.228'
+__version__ = '8.0.229'
 
 from ultralytics.models import RTDETR, SAM, YOLO
 from ultralytics.models.fastsam import FastSAM

ultralytics/cfg/default.yaml

@@ -61,6 +61,7 @@ augment: False  # (bool) apply image augmentation to prediction sources
 agnostic_nms: False  # (bool) class-agnostic NMS
 classes:  # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3]
 retina_masks: False  # (bool) use high-resolution segmentation masks
+embed:  # (list[int], optional) return feature vectors/embeddings from given layers
 
 # Visualize settings ---------------------------------------------------------------------------------------------------
 show: False  # (bool) show predicted images and videos if environment allows

ultralytics/engine/model.py

@@ -94,7 +94,7 @@ class Model(nn.Module):
             self._load(model, task)
 
     def __call__(self, source=None, stream=False, **kwargs):
-        """Calls the 'predict' function with given arguments to perform object detection."""
+        """Calls the predict() method with given arguments to perform object detection."""
         return self.predict(source, stream, **kwargs)
 
     @staticmethod
@@ -201,6 +201,24 @@ class Model(nn.Module):
         self._check_is_pytorch_model()
         self.model.fuse()
 
+    def embed(self, source=None, stream=False, **kwargs):
+        """
+        Calls the predict() method and returns image embeddings.
+
+        Args:
+            source (str | int | PIL | np.ndarray): The source of the image to make predictions on.
+                Accepts all source types accepted by the YOLO model.
+            stream (bool): Whether to stream the predictions or not. Defaults to False.
+            **kwargs : Additional keyword arguments passed to the predictor.
+                Check the 'configuration' section in the documentation for all available options.
+
+        Returns:
+            (List[torch.Tensor]): A list of image embeddings.
+        """
+        if not kwargs.get('embed'):
+            kwargs['embed'] = [len(self.model.model) - 2]  # embed second-to-last layer if no indices passed
+        return self.predict(source, stream, **kwargs)
+
     def predict(self, source=None, stream=False, predictor=None, **kwargs):
         """
         Perform prediction using the YOLO model.

ultralytics/engine/predictor.py

@@ -134,7 +134,7 @@ class BasePredictor:
         """Runs inference on a given image using the specified model and arguments."""
         visualize = increment_path(self.save_dir / Path(self.batch[0][0]).stem,
                                    mkdir=True) if self.args.visualize and (not self.source_type.tensor) else False
-        return self.model(im, augment=self.args.augment, visualize=visualize)
+        return self.model(im, augment=self.args.augment, visualize=visualize, embed=self.args.embed, *args, **kwargs)
 
     def pre_transform(self, im):
         """
@@ -263,6 +263,9 @@ class BasePredictor:
                 # Inference
                 with profilers[1]:
                     preds = self.inference(im, *args, **kwargs)
+                    if self.args.embed:
+                        yield from [preds] if isinstance(preds, torch.Tensor) else preds  # yield embedding tensors
+                        continue
 
                 # Postprocess
                 with profilers[2]:

ultralytics/nn/autobackend.py

@@ -333,7 +333,7 @@ class AutoBackend(nn.Module):
 
         self.__dict__.update(locals())  # assign all variables to self
 
-    def forward(self, im, augment=False, visualize=False):
+    def forward(self, im, augment=False, visualize=False, embed=None):
         """
         Runs inference on the YOLOv8 MultiBackend model.
 
@@ -341,6 +341,7 @@ class AutoBackend(nn.Module):
             im (torch.Tensor): The image tensor to perform inference on.
             augment (bool): whether to perform data augmentation during inference, defaults to False
             visualize (bool): whether to visualize the output predictions, defaults to False
+            embed (list, optional): A list of feature vectors/embeddings to return.
 
         Returns:
             (tuple): Tuple containing the raw output tensor, and processed output for visualization (if visualize=True)
@@ -352,7 +353,7 @@ class AutoBackend(nn.Module):
             im = im.permute(0, 2, 3, 1)  # torch BCHW to numpy BHWC shape(1,320,192,3)
 
         if self.pt or self.nn_module:  # PyTorch
-            y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
+            y = self.model(im, augment=augment, visualize=visualize, embed=embed)
         elif self.jit:  # TorchScript
             y = self.model(im)
         elif self.dnn:  # ONNX OpenCV DNN

ultralytics/nn/tasks.py

@@ -41,7 +41,7 @@ class BaseModel(nn.Module):
             return self.loss(x, *args, **kwargs)
         return self.predict(x, *args, **kwargs)
 
-    def predict(self, x, profile=False, visualize=False, augment=False):
+    def predict(self, x, profile=False, visualize=False, augment=False, embed=None):
         """
         Perform a forward pass through the network.
 
@@ -50,15 +50,16 @@ class BaseModel(nn.Module):
             profile (bool):  Print the computation time of each layer if True, defaults to False.
             visualize (bool): Save the feature maps of the model if True, defaults to False.
             augment (bool): Augment image during prediction, defaults to False.
+            embed (list, optional): A list of feature vectors/embeddings to return.
 
         Returns:
             (torch.Tensor): The last output of the model.
         """
         if augment:
             return self._predict_augment(x)
-        return self._predict_once(x, profile, visualize)
+        return self._predict_once(x, profile, visualize, embed)
 
-    def _predict_once(self, x, profile=False, visualize=False):
+    def _predict_once(self, x, profile=False, visualize=False, embed=None):
         """
         Perform a forward pass through the network.
 
@@ -66,11 +67,12 @@ class BaseModel(nn.Module):
             x (torch.Tensor): The input tensor to the model.
             profile (bool):  Print the computation time of each layer if True, defaults to False.
             visualize (bool): Save the feature maps of the model if True, defaults to False.
+            embed (list, optional): A list of feature vectors/embeddings to return.
 
         Returns:
             (torch.Tensor): The last output of the model.
         """
-        y, dt = [], []  # outputs
+        y, dt, embeddings = [], [], []  # outputs
         for m in self.model:
             if m.f != -1:  # if not from previous layer
                 x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
@@ -80,6 +82,10 @@ class BaseModel(nn.Module):
             y.append(x if m.i in self.save else None)  # save output
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
+            if embed and m.i in embed:
+                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
+                if m.i == max(embed):
+                    return torch.unbind(torch.cat(embeddings, 1), dim=0)
         return x
 
     def _predict_augment(self, x):
@@ -454,7 +460,7 @@ class RTDETRDetectionModel(DetectionModel):
         return sum(loss.values()), torch.as_tensor([loss[k].detach() for k in ['loss_giou', 'loss_class', 'loss_bbox']],
                                                    device=img.device)
 
-    def predict(self, x, profile=False, visualize=False, batch=None, augment=False):
+    def predict(self, x, profile=False, visualize=False, batch=None, augment=False, embed=None):
         """
         Perform a forward pass through the model.
 
@@ -464,11 +470,12 @@ class RTDETRDetectionModel(DetectionModel):
             visualize (bool, optional): If True, save feature maps for visualization. Defaults to False.
             batch (dict, optional): Ground truth data for evaluation. Defaults to None.
             augment (bool, optional): If True, perform data augmentation during inference. Defaults to False.
+            embed (list, optional): A list of feature vectors/embeddings to return.
 
         Returns:
             (torch.Tensor): Model's output tensor.
         """
-        y, dt = [], []  # outputs
+        y, dt, embeddings = [], [], []  # outputs
         for m in self.model[:-1]:  # except the head part
             if m.f != -1:  # if not from previous layer
                 x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
@@ -478,6 +485,10 @@ class RTDETRDetectionModel(DetectionModel):
             y.append(x if m.i in self.save else None)  # save output
             if visualize:
                 feature_visualization(x, m.type, m.i, save_dir=visualize)
+            if embed and m.i in embed:
+                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
+                if m.i == max(embed):
+                    return torch.unbind(torch.cat(embeddings, 1), dim=0)
         head = self.model[-1]
         x = head([y[j] for j in head.f], batch)  # head inference
         return x

ultralytics/solutions/heatmap.py

@@ -10,8 +10,7 @@ from ultralytics.utils.plotting import Annotator
 
 check_requirements('shapely>=2.0.0')
 
-from shapely.geometry import Polygon
-from shapely.geometry.point import Point
+from shapely.geometry import LineString, Point, Polygon
 
 
 class Heatmap:
@@ -23,6 +22,7 @@ class Heatmap:
         # Visual information
         self.annotator = None
         self.view_img = False
+        self.shape = 'circle'
 
         # Image information
         self.imw = None
@@ -38,17 +38,22 @@ class Heatmap:
         self.boxes = None
         self.track_ids = None
         self.clss = None
-        self.track_history = None
+        self.track_history = defaultdict(list)
 
-        # Counting info
+        # Region & Line Information
         self.count_reg_pts = None
-        self.count_region = None
+        self.counting_region = None
+        self.line_dist_thresh = 15
+        self.region_thickness = 5
+        self.region_color = (255, 0, 255)
+
+        # Object Counting Information
         self.in_counts = 0
         self.out_counts = 0
-        self.count_list = []
+        self.counting_list = []
         self.count_txt_thickness = 0
-        self.count_reg_color = (0, 255, 0)
-        self.region_thickness = 5
+        self.count_txt_color = (0, 0, 0)
+        self.count_color = (255, 255, 255)
 
         # Decay factor
         self.decay_factor = 0.99
@@ -64,9 +69,13 @@ class Heatmap:
                  view_img=False,
                  count_reg_pts=None,
                  count_txt_thickness=2,
+                 count_txt_color=(0, 0, 0),
+                 count_color=(255, 255, 255),
                  count_reg_color=(255, 0, 255),
                  region_thickness=5,
-                 decay_factor=0.99):
+                 line_dist_thresh=15,
+                 decay_factor=0.99,
+                 shape='circle'):
         """
         Configures the heatmap colormap, width, height and display parameters.
 
@@ -78,27 +87,55 @@ class Heatmap:
             view_img (bool): Flag indicating frame display
             count_reg_pts (list): Object counting region points
             count_txt_thickness (int): Text thickness for object counting display
+            count_txt_color (RGB color): count text color value
+            count_color (RGB color): count text background color value
             count_reg_color (RGB color): Color of object counting region
             region_thickness (int): Object counting Region thickness
+            line_dist_thresh (int): Euclidean Distance threshold for line counter
             decay_factor (float): value for removing heatmap area after object passed
+            shape (str): Heatmap shape, rect or circle shape supported
         """
         self.imw = imw
         self.imh = imh
-        self.colormap = colormap
         self.heatmap_alpha = heatmap_alpha
         self.view_img = view_img
+        self.colormap = colormap
 
-        self.heatmap = np.zeros((int(self.imw), int(self.imh)), dtype=np.float32)  # Heatmap new frame
-
+        # Region and line selection
         if count_reg_pts is not None:
-            self.track_history = defaultdict(list)
-            self.count_reg_pts = count_reg_pts
-            self.count_region = Polygon(self.count_reg_pts)
 
-        self.count_txt_thickness = count_txt_thickness  # Counting text thickness
-        self.count_reg_color = count_reg_color
+            if len(count_reg_pts) == 2:
+                print('Line Counter Initiated.')
+                self.count_reg_pts = count_reg_pts
+                self.counting_region = LineString(count_reg_pts)
+
+            elif len(count_reg_pts) == 4:
+                print('Region Counter Initiated.')
+                self.count_reg_pts = count_reg_pts
+                self.counting_region = Polygon(self.count_reg_pts)
+
+            else:
+                print('Region or line points Invalid, 2 or 4 points supported')
+                print('Using Line Counter Now')
+                self.counting_region = Polygon([(20, 400), (1260, 400)])  # dummy points
+
+        # Heatmap new frame
+        self.heatmap = np.zeros((int(self.imw), int(self.imh)), dtype=np.float32)
+
+        self.count_txt_thickness = count_txt_thickness
+        self.count_txt_color = count_txt_color
+        self.count_color = count_color
+        self.region_color = count_reg_color
         self.region_thickness = region_thickness
         self.decay_factor = decay_factor
+        self.line_dist_thresh = line_dist_thresh
+        self.shape = shape
+
+        # shape of heatmap, if not selected
+        if self.shape not in ['circle', 'rect']:
+            print("Unknown shape value provided, 'circle' & 'rect' supported")
+            print('Using Circular shape now')
+            self.shape = 'circle'
 
     def extract_results(self, tracks):
         """
@@ -128,13 +165,26 @@ class Heatmap:
         self.annotator = Annotator(self.im0, self.count_txt_thickness, None)
 
         if self.count_reg_pts is not None:
+
             # Draw counting region
             self.annotator.draw_region(reg_pts=self.count_reg_pts,
-                                       color=self.count_reg_color,
+                                       color=self.region_color,
                                        thickness=self.region_thickness)
 
             for box, cls, track_id in zip(self.boxes, self.clss, self.track_ids):
-                self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += 1
+
+                if self.shape == 'circle':
+                    center = (int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2))
+                    radius = min(int(box[2]) - int(box[0]), int(box[3]) - int(box[1])) // 2
+
+                    y, x = np.ogrid[0:self.heatmap.shape[0], 0:self.heatmap.shape[1]]
+                    mask = (x - center[0]) ** 2 + (y - center[1]) ** 2 <= radius ** 2
+
+                    self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += \
+                        (2 * mask[int(box[1]):int(box[3]), int(box[0]):int(box[2])])
+
+                else:
+                    self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += 2
 
                 # Store tracking hist
                 track_line = self.track_history[track_id]
@@ -143,16 +193,39 @@ class Heatmap:
                     track_line.pop(0)
 
                 # Count objects
-                if self.count_region.contains(Point(track_line[-1])):
-                    if track_id not in self.count_list:
-                        self.count_list.append(track_id)
-                        if box[0] < self.count_region.centroid.x:
-                            self.out_counts += 1
-                        else:
-                            self.in_counts += 1
+                if len(self.count_reg_pts) == 4:
+                    if self.counting_region.contains(Point(track_line[-1])):
+                        if track_id not in self.counting_list:
+                            self.counting_list.append(track_id)
+                            if box[0] < self.counting_region.centroid.x:
+                                self.out_counts += 1
+                            else:
+                                self.in_counts += 1
+
+                elif len(self.count_reg_pts) == 2:
+                    distance = Point(track_line[-1]).distance(self.counting_region)
+                    if distance < self.line_dist_thresh:
+                        if track_id not in self.counting_list:
+                            self.counting_list.append(track_id)
+                            if box[0] < self.counting_region.centroid.x:
+                                self.out_counts += 1
+                            else:
+                                self.in_counts += 1
         else:
             for box, cls in zip(self.boxes, self.clss):
-                self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += 1
+
+                if self.shape == 'circle':
+                    center = (int((box[0] + box[2]) // 2), int((box[1] + box[3]) // 2))
+                    radius = min(int(box[2]) - int(box[0]), int(box[3]) - int(box[1])) // 2
+
+                    y, x = np.ogrid[0:self.heatmap.shape[0], 0:self.heatmap.shape[1]]
+                    mask = (x - center[0]) ** 2 + (y - center[1]) ** 2 <= radius ** 2
+
+                    self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += \
+                        (2 * mask[int(box[1]):int(box[3]), int(box[0]):int(box[2])])
+
+                else:
+                    self.heatmap[int(box[1]):int(box[3]), int(box[0]):int(box[2])] += 2
 
         # Normalize, apply colormap to heatmap and combine with original image
         heatmap_normalized = cv2.normalize(self.heatmap, None, 0, 255, cv2.NORM_MINMAX)
@@ -161,7 +234,11 @@ class Heatmap:
         if self.count_reg_pts is not None:
             incount_label = 'InCount : ' + f'{self.in_counts}'
             outcount_label = 'OutCount : ' + f'{self.out_counts}'
-            self.annotator.count_labels(in_count=incount_label, out_count=outcount_label)
+            self.annotator.count_labels(in_count=incount_label,
+                                        out_count=outcount_label,
+                                        count_txt_size=self.count_txt_thickness,
+                                        txt_color=self.count_txt_color,
+                                        color=self.count_color)
 
         im0_with_heatmap = cv2.addWeighted(self.im0, 1 - self.heatmap_alpha, heatmap_colored, self.heatmap_alpha, 0)
 

ultralytics/solutions/object_counter.py

@@ -9,8 +9,7 @@ from ultralytics.utils.plotting import Annotator, colors
 
 check_requirements('shapely>=2.0.0')
 
-from shapely.geometry import Polygon
-from shapely.geometry.point import Point
+from shapely.geometry import LineString, Point, Polygon
 
 
 class ObjectCounter:
@@ -23,10 +22,12 @@ class ObjectCounter:
         self.is_drawing = False
         self.selected_point = None
 
-        # Region Information
-        self.reg_pts = None
+        # Region & Line Information
+        self.reg_pts = [(20, 400), (1260, 400)]
+        self.line_dist_thresh = 15
         self.counting_region = None
-        self.region_color = (255, 255, 255)
+        self.region_color = (255, 0, 255)
+        self.region_thickness = 5
 
         # Image and annotation Information
         self.im0 = None
@@ -40,11 +41,15 @@ class ObjectCounter:
         self.in_counts = 0
         self.out_counts = 0
         self.counting_list = []
+        self.count_txt_thickness = 0
+        self.count_txt_color = (0, 0, 0)
+        self.count_color = (255, 255, 255)
 
         # Tracks info
         self.track_history = defaultdict(list)
         self.track_thickness = 2
         self.draw_tracks = False
+        self.track_color = (0, 255, 0)
 
         # Check if environment support imshow
         self.env_check = check_imshow(warn=True)
@@ -52,11 +57,17 @@ class ObjectCounter:
     def set_args(self,
                  classes_names,
                  reg_pts,
-                 region_color=None,
+                 count_reg_color=(255, 0, 255),
                  line_thickness=2,
                  track_thickness=2,
                  view_img=False,
-                 draw_tracks=False):
+                 draw_tracks=False,
+                 count_txt_thickness=2,
+                 count_txt_color=(0, 0, 0),
+                 count_color=(255, 255, 255),
+                 track_color=(0, 255, 0),
+                 region_thickness=5,
+                 line_dist_thresh=15):
         """
         Configures the Counter's image, bounding box line thickness, and counting region points.
 
@@ -65,18 +76,43 @@ class ObjectCounter:
             view_img (bool): Flag to control whether to display the video stream.
             reg_pts (list): Initial list of points defining the counting region.
             classes_names (dict): Classes names
-            region_color (tuple): color for region line
             track_thickness (int): Track thickness
             draw_tracks (Bool): draw tracks
+            count_txt_thickness (int): Text thickness for object counting display
+            count_txt_color (RGB color): count text color value
+            count_color (RGB color): count text background color value
+            count_reg_color (RGB color): Color of object counting region
+            track_color (RGB color): color for tracks
+            region_thickness (int): Object counting Region thickness
+            line_dist_thresh (int): Euclidean Distance threshold for line counter
         """
         self.tf = line_thickness
         self.view_img = view_img
         self.track_thickness = track_thickness
         self.draw_tracks = draw_tracks
-        self.reg_pts = reg_pts
-        self.counting_region = Polygon(self.reg_pts)
+
+        # Region and line selection
+        if len(reg_pts) == 2:
+            print('Line Counter Initiated.')
+            self.reg_pts = reg_pts
+            self.counting_region = LineString(self.reg_pts)
+        elif len(reg_pts) == 4:
+            print('Region Counter Initiated.')
+            self.reg_pts = reg_pts
+            self.counting_region = Polygon(self.reg_pts)
+        else:
+            print('Invalid Region points provided, region_points can be 2 or 4')
+            print('Using Line Counter Now')
+            self.counting_region = LineString(self.reg_pts)
+
         self.names = classes_names
-        self.region_color = region_color if region_color else self.region_color
+        self.track_color = track_color
+        self.count_txt_thickness = count_txt_thickness
+        self.count_txt_color = count_txt_color
+        self.count_color = count_color
+        self.region_color = count_reg_color
+        self.region_thickness = region_thickness
+        self.line_dist_thresh = line_dist_thresh
 
     def mouse_event_for_region(self, event, x, y, flags, params):
         """
@@ -113,11 +149,14 @@ class ObjectCounter:
         clss = tracks[0].boxes.cls.cpu().tolist()
         track_ids = tracks[0].boxes.id.int().cpu().tolist()
 
+        # Annotator Init and region drawing
         self.annotator = Annotator(self.im0, self.tf, self.names)
-        self.annotator.draw_region(reg_pts=self.reg_pts, color=(0, 255, 0))
+        self.annotator.draw_region(reg_pts=self.reg_pts, color=self.region_color, thickness=self.region_thickness)
 
+        # Extract tracks
         for box, track_id, cls in zip(boxes, track_ids, clss):
-            self.annotator.box_label(box, label=self.names[cls], color=colors(int(cls), True))  # Draw bounding box
+            self.annotator.box_label(box, label=str(track_id) + ':' + self.names[cls],
+                                     color=colors(int(cls), True))  # Draw bounding box
 
             # Draw Tracks
             track_line = self.track_history[track_id]
@@ -125,28 +164,45 @@ class ObjectCounter:
             if len(track_line) > 30:
                 track_line.pop(0)
 
+            # Draw track trails
             if self.draw_tracks:
                 self.annotator.draw_centroid_and_tracks(track_line,
-                                                        color=(0, 255, 0),
+                                                        color=self.track_color,
                                                         track_thickness=self.track_thickness)
 
             # Count objects
-            if self.counting_region.contains(Point(track_line[-1])):
-                if track_id not in self.counting_list:
-                    self.counting_list.append(track_id)
-                    if box[0] < self.counting_region.centroid.x:
-                        self.out_counts += 1
-                    else:
-                        self.in_counts += 1
-
-        incount_label = 'InCount : ' + f'{self.in_counts}'
+            if len(self.reg_pts) == 4:
+                if self.counting_region.contains(Point(track_line[-1])):
+                    if track_id not in self.counting_list:
+                        self.counting_list.append(track_id)
+                        if box[0] < self.counting_region.centroid.x:
+                            self.out_counts += 1
+                        else:
+                            self.in_counts += 1
+
+            elif len(self.reg_pts) == 2:
+                distance = Point(track_line[-1]).distance(self.counting_region)
+                if distance < self.line_dist_thresh:
+                    if track_id not in self.counting_list:
+                        self.counting_list.append(track_id)
+                        if box[0] < self.counting_region.centroid.x:
+                            self.out_counts += 1
+                        else:
+                            self.in_counts += 1
+
+        incount_label = 'In Count : ' + f'{self.in_counts}'
         outcount_label = 'OutCount : ' + f'{self.out_counts}'
-        self.annotator.count_labels(in_count=incount_label, out_count=outcount_label)
+        self.annotator.count_labels(in_count=incount_label,
+                                    out_count=outcount_label,
+                                    count_txt_size=self.count_txt_thickness,
+                                    txt_color=self.count_txt_color,
+                                    color=self.count_color)
 
         if self.env_check and self.view_img:
             cv2.namedWindow('Ultralytics YOLOv8 Object Counter')
-            cv2.setMouseCallback('Ultralytics YOLOv8 Object Counter', self.mouse_event_for_region,
-                                 {'region_points': self.reg_pts})
+            if len(self.reg_pts) == 4:  # only add mouse event If user drawn region
+                cv2.setMouseCallback('Ultralytics YOLOv8 Object Counter', self.mouse_event_for_region,
+                                     {'region_points': self.reg_pts})
             cv2.imshow('Ultralytics YOLOv8 Object Counter', self.im0)
             # Break Window
             if cv2.waitKey(1) & 0xFF == ord('q'):
@@ -161,6 +217,7 @@ class ObjectCounter:
             tracks (list): List of tracks obtained from the object tracking process.
         """
         self.im0 = im0  # store image
+
         if tracks[0].boxes.id is None:
             return
         self.extract_and_process_tracks(tracks)

ultralytics/utils/plotting.py

@@ -260,19 +260,41 @@ class Annotator:
 
     # Object Counting Annotator
     def draw_region(self, reg_pts=None, color=(0, 255, 0), thickness=5):
-        # Draw region line
+        """
+        Draw region line
+        Args:
+            reg_pts (list): Region Points (for line 2 points, for region 4 points)
+            color (tuple): Region Color value
+            thickness (int): Region area thickness value
+        """
         cv2.polylines(self.im, [np.array(reg_pts, dtype=np.int32)], isClosed=True, color=color, thickness=thickness)
 
     def draw_centroid_and_tracks(self, track, color=(255, 0, 255), track_thickness=2):
-        # Draw region line
+        """
+        Draw centroid point and track trails
+        Args:
+            track (list): object tracking points for trails display
+            color (tuple): tracks line color
+            track_thickness (int): track line thickness value
+        """
         points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
         cv2.polylines(self.im, [points], isClosed=False, color=color, thickness=track_thickness)
         cv2.circle(self.im, (int(track[-1][0]), int(track[-1][1])), track_thickness * 2, color, -1)
 
-    def count_labels(self, in_count=0, out_count=0, color=(255, 255, 255), txt_color=(0, 0, 0)):
+    def count_labels(self, in_count=0, out_count=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0)):
+        """
+        Plot counts for object counter
+        Args:
+            in_count (int): in count value
+            out_count (int): out count value
+            count_txt_size (int): text size for counts display
+            color (tuple): background color of counts display
+            txt_color (tuple): text color of counts display
+        """
+        self.tf = count_txt_size
         tl = self.tf or round(0.002 * (self.im.shape[0] + self.im.shape[1]) / 2) + 1
         tf = max(tl - 1, 1)
-        gap = int(24 * tl)  # Calculate the gap between in_count and out_count based on line_thickness
+        gap = int(24 * tl)  # gap between in_count and out_count based on line_thickness
 
         # Get text size for in_count and out_count
         t_size_in = cv2.getTextSize(str(in_count), 0, fontScale=tl / 2, thickness=tf)[0]
@@ -306,14 +328,13 @@ class Annotator:
                     thickness=self.tf,
                     lineType=cv2.LINE_AA)
 
-    # AI GYM Annotator
-    def estimate_pose_angle(self, a, b, c):
+    @staticmethod
+    def estimate_pose_angle(a, b, c):
         """Calculate the pose angle for object
         Args:
             a (float) : The value of pose point a
             b (float): The value of pose point b
             c (float): The value o pose point c
-
         Returns:
             angle (degree): Degree value of angle between three points
         """
@@ -325,7 +346,15 @@ class Annotator:
         return angle
 
     def draw_specific_points(self, keypoints, indices=[2, 5, 7], shape=(640, 640), radius=2):
-        """Draw specific keypoints for gym steps counting."""
+        """
+        Draw specific keypoints for gym steps counting.
+
+        Args:
+            keypoints (list): list of keypoints data to be plotted
+            indices (list): keypoints ids list to be plotted
+            shape (tuple): imgsz for model inference
+            radius (int): Keypoint radius value
+        """
         nkpts, ndim = keypoints.shape
         nkpts == 17 and ndim == 3
         for i, k in enumerate(keypoints):
@@ -340,8 +369,17 @@ class Annotator:
         return self.im
 
     def plot_angle_and_count_and_stage(self, angle_text, count_text, stage_text, center_kpt, line_thickness=2):
-        """Plot the pose angle, count value and step stage."""
-        angle_text, count_text, stage_text = f' {angle_text:.2f}', 'Steps : ' + f'{count_text}', f' {stage_text}'
+        """
+        Plot the pose angle, count value and step stage.
+
+        Args:
+            angle_text (str): angle value for workout monitoring
+            count_text (str): counts value for workout monitoring
+            stage_text (str): stage decision for workout monitoring
+            center_kpt (int): centroid pose index for workout monitoring
+            line_thickness (int): thickness for text display
+        """
+        angle_text, count_text, stage_text = (f' {angle_text:.2f}', 'Steps : ' + f'{count_text}', f' {stage_text}')
         font_scale = 0.6 + (line_thickness / 10.0)
 
         # Draw angle
@@ -378,18 +416,38 @@ class Annotator:
         cv2.putText(self.im, stage_text, stage_text_position, 0, font_scale, (0, 0, 0), line_thickness)
 
     def seg_bbox(self, mask, mask_color=(255, 0, 255), det_label=None, track_label=None):
-        """Function for drawing segmented object in bounding box shape."""
+        """
+        Function for drawing segmented object in bounding box shape.
+
+        Args:
+            mask (list): masks data list for instance segmentation area plotting
+            mask_color (tuple): mask foreground color
+            det_label (str): Detection label text
+            track_label (str): Tracking label text
+        """
         cv2.polylines(self.im, [np.int32([mask])], isClosed=True, color=mask_color, thickness=2)
 
         label = f'Track ID: {track_label}' if track_label else det_label
         text_size, _ = cv2.getTextSize(label, 0, 0.7, 1)
+
         cv2.rectangle(self.im, (int(mask[0][0]) - text_size[0] // 2 - 10, int(mask[0][1]) - text_size[1] - 10),
                       (int(mask[0][0]) + text_size[0] // 2 + 5, int(mask[0][1] + 5)), mask_color, -1)
+
         cv2.putText(self.im, label, (int(mask[0][0]) - text_size[0] // 2, int(mask[0][1]) - 5), 0, 0.7, (255, 255, 255),
                     2)
 
     def visioneye(self, box, center_point, color=(235, 219, 11), pin_color=(255, 0, 255), thickness=2, pins_radius=10):
-        """Function for pinpoint human-vision eye mapping and plotting."""
+        """
+        Function for pinpoint human-vision eye mapping and plotting.
+
+        Args:
+            box (list): Bounding box coordinates
+            center_point (tuple): center point for vision eye view
+            color (tuple): object centroid and line color value
+            pin_color (tuple): visioneye point color value
+            thickness (int): int value for line thickness
+            pins_radius (int): visioneye point radius value
+        """
         center_bbox = int((box[0] + box[2]) / 2), int((box[1] + box[3]) / 2)
         cv2.circle(self.im, center_point, pins_radius, pin_color, -1)
         cv2.circle(self.im, center_bbox, pins_radius, color, -1)

{ultralytics-8.0.228.dist-info → ultralytics-8.0.229.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.0.228
+Version: 8.0.229
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Home-page: https://github.com/ultralytics/ultralytics
 Author: Ultralytics

{ultralytics-8.0.228.dist-info → ultralytics-8.0.229.dist-info}/RECORD

@@ -1,8 +1,8 @@
-ultralytics/__init__.py,sha256=0ZRVYelXCSx1Ikbi9p1qb3Fpj3B7aKu1bXGw-UUX6co,463
+ultralytics/__init__.py,sha256=EhwYUqe_mS7jZksFDr-yyVHPSPorRPpkiAZ_w0K_MzU,463
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=GszkldmONF8PI1J1o4TqNzq1Btzk8R7Y3_susNMHvpA,19859
-ultralytics/cfg/default.yaml,sha256=arCmsoPF88mHt0KAuDl3CxN4CbcjXqAXR_sOK9m06YQ,7738
+ultralytics/cfg/default.yaml,sha256=-ejbKAG_xK9bke-Yr5w-1wcwHeA5vZ1FyOgBi27aShQ,7822
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=TJhOiAm1QOsQnDkg1eEGYlaylgkvKLzBUdQ5gzyi_pY,2856
 ultralytics/cfg/datasets/DOTAv2.yaml,sha256=SmSpmbz_wRT8HMmPqsHpjep_b-nvckTutoEwVpGaUZM,1149
 ultralytics/cfg/datasets/GlobalWheat2020.yaml,sha256=Wd9spwO4HV48REvgqDUX-kM5a8rxceFalxkcvWDnJZI,1981
@@ -56,8 +56,8 @@ ultralytics/data/loaders.py,sha256=yDI0Xtb6IxpkU-fxdlPiBOY1FYDPEPDahre0rcgy2T8,2
 ultralytics/data/utils.py,sha256=1vKuCYOA_haro4tjzVSgOgwvdyEXw4UKmfYyPtfwXis,29699
 ultralytics/engine/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8grmQDTs,42
 ultralytics/engine/exporter.py,sha256=8bttk0XZMo8tstnVdGBVPhGnPnirOor28xDLHQP4cz4,51226
-ultralytics/engine/model.py,sha256=1cmagS8BskMzOay9uDlFIvS5m58GB2kxZoYnUfxIAbU,19236
-ultralytics/engine/predictor.py,sha256=tgwQ58bziem5rZXucVyK0LP5fzvAgJtICBaN7kLUM9s,17548
+ultralytics/engine/model.py,sha256=L1irDV83yBT2aWu053ukhsFGh5hZlsqKyJb_9-d5D0I,20107
+ultralytics/engine/predictor.py,sha256=C6ZmZu5q8-6stuk1vE1P-E9LoPaO_85xo645SjemchA,17777
 ultralytics/engine/results.py,sha256=2GND_qGa8W8qJTyaSSt3qoPBqAS2JA5CDAB4y6wwdh8,23417
 ultralytics/engine/trainer.py,sha256=G7WN1rKd-rasJ0cFdZu8cj795z_5o1mI_7eX6p54X3k,33886
 ultralytics/engine/tuner.py,sha256=_9MAsXQwDtmDznqb6_cgk1DIo8FTwLgM3OTEifCxRp0,11715
@@ -115,8 +115,8 @@ ultralytics/models/yolo/segment/predict.py,sha256=yUs60HFBn7PZ3mErtUAnT69ijPBzFd
 ultralytics/models/yolo/segment/train.py,sha256=o1q4ZTmZlSwUbFIFaT_T7LvYaKOLq_QXxB-z61YwHx8,2276
 ultralytics/models/yolo/segment/val.py,sha256=DT-z-XnxP77nTIu2VfmGlpUyeBnDmIszT4vpP7mkGNA,11956
 ultralytics/nn/__init__.py,sha256=7T_GW3YsPg1kA-74UklF2UcabcRyttRZYrCOXiNnJqU,555
-ultralytics/nn/autobackend.py,sha256=eFn23VKky5qEwXpAcK3VXJwC_kiXsFKVQcbO2C38v60,26957
-ultralytics/nn/tasks.py,sha256=wiT7k194SU8Ckb3hICaOwyQ5tdSyT5qbug0VlnW5kyA,36609
+ultralytics/nn/autobackend.py,sha256=BRiDYbLrsIOF9DHoVB-IbLUZ1NOtzBdSy9xb420c2FQ,27022
+ultralytics/nn/tasks.py,sha256=djDmgi5PFpUwuNhuxbUpCqZvtHfADvaBycGqY110pIo,37466
 ultralytics/nn/modules/__init__.py,sha256=vrndehuJuLdA3UMHgByPUSR8rz32naUN0LIZoPzF7YQ,1698
 ultralytics/nn/modules/block.py,sha256=_A24bZ1xSWvrvqk5RODeobBZL6ReI6ICk-vwilERTZs,14475
 ultralytics/nn/modules/conv.py,sha256=z_OQka9s5h0p3k1yWrq7SHg1BsA6PfN5lDSQubW2I_k,12774
@@ -125,8 +125,8 @@ ultralytics/nn/modules/transformer.py,sha256=R7K_3r4aTlvghiTTRzh69NmNzlO_1Siiifb
 ultralytics/nn/modules/utils.py,sha256=q-qfebnMD2iqZyTslZTHsZYW7hyrX62VRgUmHX683-U,3436
 ultralytics/solutions/__init__.py,sha256=mHtJuK4hwF8cuV-VHDc7tp6u6D1gHz2Z7JI8grmQDTs,42
 ultralytics/solutions/ai_gym.py,sha256=YnBeC8Vf3-ai4OQIebEXl5yDho6uRspY2XVL8Ipr-h8,6235
-ultralytics/solutions/heatmap.py,sha256=eK4qk4HMEvIYTW77HsTK4Z_vopvWZuFCmp84_v18TY0,6669
-ultralytics/solutions/object_counter.py,sha256=n3JpYcFVlqHGxtnFUQn0gLBdaOxqdJpghmgRUPa9Cq4,6576
+ultralytics/solutions/heatmap.py,sha256=BKsFF3GbtWGHKCfIWXOcu54dZArRf8b1rIq6dAZLzeQ,10310
+ultralytics/solutions/object_counter.py,sha256=-hEmw93gSz_cqZyHPp7w9nNLBXlPSLeP8pBj2cvNNi8,9338
 ultralytics/trackers/__init__.py,sha256=dR9unDaRBd6MgMnTKxqJZ0KsJ8BeFGg-LTYQvC7BnIY,227
 ultralytics/trackers/basetrack.py,sha256=Vbs76Zue_jYdJFudztTJaUnGgMMUwVqoa0BSOhyBh0o,3580
 ultralytics/trackers/bot_sort.py,sha256=orTkrMj2yHfEQVKaQVWbguTx98S2gvLnaOB0D2JN1Gc,8602
@@ -149,7 +149,7 @@ ultralytics/utils/loss.py,sha256=pYkQu-11idOM_6MDXrRS7PgJRlEH8qTxhYgOr4a_aq4,257
 ultralytics/utils/metrics.py,sha256=g_NgGDG5pFchoB0u6JxuTavLtrARphvfQEfY2KUksJc,47438
 ultralytics/utils/ops.py,sha256=h2nRGf6pAwO3muXx0SWi0p-ROrglQtGng0C_coDPhgQ,31297
 ultralytics/utils/patches.py,sha256=V3ARuy0sg-_yn6nzL7iOWSzR_RzFOuzsICy4P6qUegc,2233
-ultralytics/utils/plotting.py,sha256=mPy98up1uX1g1fNesQ4OG2XZx70aiEuGzgCk7b9hQa8,39543
+ultralytics/utils/plotting.py,sha256=iy5r40PLPueacuEQn6N1fS-FtvW_MCqs1-vwbPxciQ8,41662
 ultralytics/utils/tal.py,sha256=WxW_J5QC8oYAXKDy_huJC3mijBtpWG7UR145IAXO5_I,13675
 ultralytics/utils/torch_utils.py,sha256=09M6zCz66_rR5NdbryDDiyT6-BUxKJ4l3OZCRHnfCkM,24553
 ultralytics/utils/triton.py,sha256=opbB1ndgwfmUJzyvUH9vvMe2SrDW6FqmFxKEeNDaALQ,3932
@@ -165,9 +165,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=qIN0gJipB1f3Di7bw0Rb28jLYoCzJSWSqF
 ultralytics/utils/callbacks/raytune.py,sha256=PGZvW_haVq8Cqha3GgvL7iBMAaxfn8_3u_IIdYCNMPo,608
 ultralytics/utils/callbacks/tensorboard.py,sha256=XXnpkIJrI_A_68JLRvYvRMHzekn-US1uIcru7vRs_e0,2896
 ultralytics/utils/callbacks/wb.py,sha256=x_j4ZH4Klp0_Ld13f0UezFluUTS5Ovfgk9hcjwqeruU,6762
-ultralytics-8.0.228.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.0.228.dist-info/METADATA,sha256=qci4P37ud8A4_W5pNWqZMVrwnfuBQaiGYNK8u_238tI,32271
-ultralytics-8.0.228.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-ultralytics-8.0.228.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.0.228.dist-info/top_level.txt,sha256=aNSJehhoYKycM3X4Tj38Q-BrmWFFm3hFuEXfPIR89eI,784
-ultralytics-8.0.228.dist-info/RECORD,,
+ultralytics-8.0.229.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.0.229.dist-info/METADATA,sha256=Vol7oXlFIUdEVAb6xjU8dcFfrILh9PPSRMwyoGgarLs,32271
+ultralytics-8.0.229.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+ultralytics-8.0.229.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.0.229.dist-info/top_level.txt,sha256=aNSJehhoYKycM3X4Tj38Q-BrmWFFm3hFuEXfPIR89eI,784
+ultralytics-8.0.229.dist-info/RECORD,,