ultralytics 8.3.161__tar.gz → 8.3.163__tar.gz

{ultralytics-8.3.161/ultralytics.egg-info → ultralytics-8.3.163}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.161
+Version: 8.3.163
 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>
@@ -79,6 +79,14 @@ Requires-Dist: hub-sdk>=0.0.12; extra == "extra"
 Requires-Dist: ipython; extra == "extra"
 Requires-Dist: albumentations>=1.4.6; extra == "extra"
 Requires-Dist: faster-coco-eval>=1.6.7; extra == "extra"
+Provides-Extra: typing
+Requires-Dist: pandas-stubs; extra == "typing"
+Requires-Dist: scipy-stubs; extra == "typing"
+Requires-Dist: types-pillow; extra == "typing"
+Requires-Dist: types-psutil; extra == "typing"
+Requires-Dist: types-pyyaml; extra == "typing"
+Requires-Dist: types-requests; extra == "typing"
+Requires-Dist: types-shapely; extra == "typing"
 Dynamic: license-file
 
 <div align="center">

{ultralytics-8.3.161 → ultralytics-8.3.163}/pyproject.toml

@@ -117,6 +117,15 @@ extra = [
     "albumentations>=1.4.6", # training augmentations
     "faster-coco-eval>=1.6.7", # COCO mAP
 ]
+typing = [
+    "pandas-stubs",
+    "scipy-stubs",
+    "types-pillow",
+    "types-psutil",
+    "types-pyyaml",
+    "types-requests",
+    "types-shapely",
+]
 
 [project.urls]
 "Homepage" = "https://ultralytics.com"

{ultralytics-8.3.161 → ultralytics-8.3.163}/tests/conftest.py

@@ -56,11 +56,11 @@ def pytest_terminal_summary(terminalreporter, exitstatus, config):
     from ultralytics.utils import WEIGHTS_DIR
 
     # Remove files
-    models = [path for x in ["*.onnx", "*.torchscript"] for path in WEIGHTS_DIR.rglob(x)]
+    models = [path for x in {"*.onnx", "*.torchscript"} for path in WEIGHTS_DIR.rglob(x)]
     for file in ["decelera_portrait_min.mov", "bus.jpg", "yolo11n.onnx", "yolo11n.torchscript"] + models:
         Path(file).unlink(missing_ok=True)
 
     # Remove directories
-    models = [path for x in ["*.mlpackage", "*_openvino_model"] for path in WEIGHTS_DIR.rglob(x)]
+    models = [path for x in {"*.mlpackage", "*_openvino_model"} for path in WEIGHTS_DIR.rglob(x)]
     for directory in [WEIGHTS_DIR / "path with spaces", TMP.parents[1] / ".pytest_cache", TMP] + models:
         shutil.rmtree(directory, ignore_errors=True)

{ultralytics-8.3.161 → ultralytics-8.3.163}/tests/test_python.py

@@ -204,7 +204,7 @@ def test_track_stream(model):
 @pytest.mark.parametrize("task,model,data", TASK_MODEL_DATA)
 def test_val(task: str, model: str, data: str) -> None:
     """Test the validation mode of the YOLO model."""
-    for plots in [True, False]:  # Test both cases i.e. plots=True and plots=False
+    for plots in {True, False}:  # Test both cases i.e. plots=True and plots=False
         metrics = YOLO(model).val(data=data, imgsz=32, plots=plots)
         metrics.to_df()
         metrics.to_csv()
@@ -390,7 +390,7 @@ def test_cfg_init():
         check_dict_alignment({"a": 1}, {"b": 2})
     copy_default_cfg()
     (Path.cwd() / DEFAULT_CFG_PATH.name.replace(".yaml", "_copy.yaml")).unlink(missing_ok=False)
-    [smart_value(x) for x in ["none", "true", "false"]]
+    [smart_value(x) for x in {"none", "true", "false"}]
 
 
 def test_utils_init():

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.161"
+__version__ = "8.3.163"
 
 import os
 

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/data/augment.py

@@ -1805,6 +1805,8 @@ class CopyPaste(BaseMixTransform):
     def _transform(self, labels1, labels2={}):
         """Apply Copy-Paste augmentation to combine objects from another image into the current image."""
         im = labels1["img"]
+        if "mosaic_border" not in labels1:
+            im = im.copy()  # avoid modifying original non-mosaic image
         cls = labels1["cls"]
         h, w = im.shape[:2]
         instances = labels1.pop("instances")

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/data/converter.py

@@ -496,7 +496,7 @@ def convert_dota_to_yolo_obb(dota_root_path: str):
                 formatted_coords = [f"{coord:.6g}" for coord in normalized_coords]
                 g.write(f"{class_idx} {' '.join(formatted_coords)}\n")
 
-    for phase in ["train", "val"]:
+    for phase in {"train", "val"}:
         image_dir = dota_root_path / "images" / phase
         orig_label_dir = dota_root_path / "labels" / f"{phase}_original"
         save_dir = dota_root_path / "labels" / phase
@@ -684,7 +684,7 @@ def create_synthetic_coco_dataset():
     # Create synthetic images
     shutil.rmtree(dir / "labels" / "test2017", ignore_errors=True)  # Remove test2017 directory as not needed
     with ThreadPoolExecutor(max_workers=NUM_THREADS) as executor:
-        for subset in ["train2017", "val2017"]:
+        for subset in {"train2017", "val2017"}:
             subset_dir = dir / "images" / subset
             subset_dir.mkdir(parents=True, exist_ok=True)
 

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/data/split_dota.py

@@ -295,7 +295,7 @@ def split_trainval(
     for r in rates:
         crop_sizes.append(int(crop_size / r))
         gaps.append(int(gap / r))
-    for split in ["train", "val"]:
+    for split in {"train", "val"}:
         split_images_and_labels(data_root, save_dir, split, crop_sizes, gaps)
 
 

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/data/utils.py

@@ -214,8 +214,9 @@ def verify_image_label(args: Tuple) -> List:
                 else:
                     assert lb.shape[1] == 5, f"labels require 5 columns, {lb.shape[1]} columns detected"
                     points = lb[:, 1:]
-                assert points.max() <= 1, f"non-normalized or out of bounds coordinates {points[points > 1]}"
-                assert lb.min() >= 0, f"negative label values {lb[lb < 0]}"
+                # Coordinate points check with 1% tolerance
+                assert points.max() <= 1.01, f"non-normalized or out of bounds coordinates {points[points > 1.01]}"
+                assert lb.min() >= -0.01, f"negative class labels {lb[lb < -0.01]}"
 
                 # All labels
                 if single_cls:

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/engine/exporter.py

@@ -100,6 +100,7 @@ from ultralytics.utils.checks import (
     check_is_path_safe,
     check_requirements,
     check_version,
+    is_intel,
     is_sudo_available,
 )
 from ultralytics.utils.downloads import attempt_download_asset, get_github_assets, safe_download
@@ -107,7 +108,7 @@ from ultralytics.utils.export import export_engine, export_onnx
 from ultralytics.utils.files import file_size, spaces_in_path
 from ultralytics.utils.ops import Profile, nms_rotated
 from ultralytics.utils.patches import arange_patch
-from ultralytics.utils.torch_utils import TORCH_1_13, get_cpu_info, get_latest_opset, select_device
+from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_device
 
 
 def export_formats():
@@ -372,9 +373,9 @@ class Exporter:
             raise SystemError("TF.js exports are not currently supported on ARM64 Linux")
         # Recommend OpenVINO if export and Intel CPU
         if SETTINGS.get("openvino_msg"):
-            if "intel" in get_cpu_info().lower():
+            if is_intel():
                 LOGGER.info(
-                    "💡 ProTip: Export to OpenVINO format for best performance on Intel CPUs."
+                    "💡 ProTip: Export to OpenVINO format for best performance on Intel hardware."
                     " Learn more at https://docs.ultralytics.com/integrations/openvino/"
                 )
             SETTINGS["openvino_msg"] = False
@@ -573,7 +574,7 @@ class Exporter:
         """Export YOLO model to ONNX format."""
         requirements = ["onnx>=1.12.0,<1.18.0"]
         if self.args.simplify:
-            requirements += ["onnxslim>=0.1.56", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
+            requirements += ["onnxslim>=0.1.59", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
         check_requirements(requirements)
         import onnx  # noqa
 
@@ -948,10 +949,10 @@ class Exporter:
                 "tf_keras",  # required by 'onnx2tf' package
                 "sng4onnx>=1.0.1",  # required by 'onnx2tf' package
                 "onnx_graphsurgeon>=0.3.26",  # required by 'onnx2tf' package
-                "ai-edge-litert>=1.2.0",  # required by 'onnx2tf' package
+                "ai-edge-litert>=1.2.0,<1.4.0",  # required by 'onnx2tf' package
                 "onnx>=1.12.0,<1.18.0",
                 "onnx2tf>=1.26.3",
-                "onnxslim>=0.1.56",
+                "onnxslim>=0.1.59",
                 "onnxruntime-gpu" if cuda else "onnxruntime",
                 "protobuf>=5",
             ),

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/engine/predictor.py

@@ -452,16 +452,16 @@ class BasePredictor:
         if self.args.show:
             self.show(str(p))
         if self.args.save:
-            self.save_predicted_images(str(self.save_dir / p.name), frame)
+            self.save_predicted_images(self.save_dir / p.name, frame)
 
         return string
 
-    def save_predicted_images(self, save_path: str = "", frame: int = 0):
+    def save_predicted_images(self, save_path: Path, frame: int = 0):
         """
         Save video predictions as mp4 or images as jpg at specified path.
 
         Args:
-            save_path (str): Path to save the results.
+            save_path (Path): Path to save the results.
             frame (int): Frame number for video mode.
         """
         im = self.plotted_img
@@ -469,7 +469,7 @@ class BasePredictor:
         # Save videos and streams
         if self.dataset.mode in {"stream", "video"}:
             fps = self.dataset.fps if self.dataset.mode == "video" else 30
-            frames_path = f"{save_path.split('.', 1)[0]}_frames/"
+            frames_path = self.save_dir / f"{save_path.stem}_frames"  # save frames to a separate directory
             if save_path not in self.vid_writer:  # new video
                 if self.args.save_frames:
                     Path(frames_path).mkdir(parents=True, exist_ok=True)
@@ -484,11 +484,11 @@ class BasePredictor:
             # Save video
             self.vid_writer[save_path].write(im)
             if self.args.save_frames:
-                cv2.imwrite(f"{frames_path}{frame}.jpg", im)
+                cv2.imwrite(f"{frames_path}/{save_path.stem}_{frame}.jpg", im)
 
         # Save images
         else:
-            cv2.imwrite(str(Path(save_path).with_suffix(".jpg")), im)  # save to JPG for best support
+            cv2.imwrite(str(save_path.with_suffix(".jpg")), im)  # save to JPG for best support
 
     def show(self, p: str = ""):
         """Display an image in a window."""

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/engine/tuner.py

@@ -21,10 +21,10 @@ import time
 from typing import Dict, List, Optional
 
 import numpy as np
-import torch
 
 from ultralytics.cfg import get_cfg, get_save_dir
 from ultralytics.utils import DEFAULT_CFG, LOGGER, YAML, callbacks, colorstr, remove_colorstr
+from ultralytics.utils.patches import torch_load
 from ultralytics.utils.plotting import plot_tune_results
 
 
@@ -198,7 +198,7 @@ class Tuner:
                 cmd = [*launch, "train", *(f"{k}={v}" for k, v in train_args.items())]
                 return_code = subprocess.run(cmd, check=True).returncode
                 ckpt_file = weights_dir / ("best.pt" if (weights_dir / "best.pt").exists() else "last.pt")
-                metrics = torch.load(ckpt_file)["train_metrics"]
+                metrics = torch_load(ckpt_file)["train_metrics"]
                 assert return_code == 0, "training failed"
 
             except Exception as e:

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/nas/model.py

@@ -8,6 +8,7 @@ import torch
 from ultralytics.engine.model import Model
 from ultralytics.utils import DEFAULT_CFG_DICT
 from ultralytics.utils.downloads import attempt_download_asset
+from ultralytics.utils.patches import torch_load
 from ultralytics.utils.torch_utils import model_info
 
 from .predict import NASPredictor
@@ -56,7 +57,7 @@ class NAS(Model):
 
         suffix = Path(weights).suffix
         if suffix == ".pt":
-            self.model = torch.load(attempt_download_asset(weights))
+            self.model = torch_load(attempt_download_asset(weights))
         elif suffix == "":
             self.model = super_gradients.training.models.get(weights, pretrained_weights="coco")
 

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/sam/modules/tiny_encoder.py

@@ -931,7 +931,7 @@ class TinyViT(nn.Module):
             if layer.downsample is not None:
                 layer.downsample.apply(lambda x: _set_lr_scale(x, lr_scales[i - 1]))
         assert i == depth
-        for m in [self.norm_head, self.head]:
+        for m in {self.norm_head, self.head}:
             m.apply(lambda x: _set_lr_scale(x, lr_scales[-1]))
 
         for k, p in self.named_parameters():

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/yolo/detect/val.py

@@ -71,7 +71,7 @@ class DetectionValidator(BaseValidator):
         """
         batch["img"] = batch["img"].to(self.device, non_blocking=True)
         batch["img"] = (batch["img"].half() if self.args.half else batch["img"].float()) / 255
-        for k in ["batch_idx", "cls", "bboxes"]:
+        for k in {"batch_idx", "cls", "bboxes"}:
             batch[k] = batch[k].to(self.device)
 
         return batch

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/yolo/world/train.py

@@ -153,7 +153,7 @@ class WorldTrainer(DetectionTrainer):
         cache_path = cache_dir / f"text_embeddings_{model.replace(':', '_').replace('/', '_')}.pt"
         if cache_path.exists():
             LOGGER.info(f"Reading existed cache from '{cache_path}'")
-            txt_map = torch.load(cache_path)
+            txt_map = torch.load(cache_path, map_location=self.device)
             if sorted(txt_map.keys()) == sorted(texts):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/yolo/world/train_world.py

@@ -1,9 +1,11 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
+from pathlib import Path
+
 from ultralytics.data import YOLOConcatDataset, build_grounding, build_yolo_dataset
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.world import WorldTrainer
-from ultralytics.utils import DEFAULT_CFG, LOGGER
+from ultralytics.utils import DATASETS_DIR, DEFAULT_CFG, LOGGER
 from ultralytics.utils.torch_utils import de_parallel
 
 
@@ -136,7 +138,7 @@ class WorldTrainerFromScratch(WorldTrainer):
             if d.get("minival") is None:  # for lvis dataset
                 continue
             d["minival"] = str(d["path"] / d["minival"])
-        for s in ["train", "val"]:
+        for s in {"train", "val"}:
             final_data[s] = [d["train" if s == "train" else val_split] for d in data[s]]
             # save grounding data if there's one
             grounding_data = data_yaml[s].get("grounding_data")
@@ -145,8 +147,14 @@ class WorldTrainerFromScratch(WorldTrainer):
             grounding_data = grounding_data if isinstance(grounding_data, list) else [grounding_data]
             for g in grounding_data:
                 assert isinstance(g, dict), f"Grounding data should be provided in dict format, but got {type(g)}"
+                for k in {"img_path", "json_file"}:
+                    path = Path(g[k])
+                    if not path.exists() and not path.is_absolute():
+                        g[k] = str((DATASETS_DIR / g[k]).resolve())  # path relative to DATASETS_DIR
             final_data[s] += grounding_data
-        data["val"] = data["val"][0]  # assign the first val dataset as currently only one validation set is supported
+        # assign the first val dataset as currently only one validation set is supported
+        data["val"] = data["val"][0]
+        final_data["val"] = final_data["val"][0]
         # NOTE: to make training work properly, set `nc` and `names`
         final_data["nc"] = data["val"]["nc"]
         final_data["names"] = data["val"]["names"]

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/models/yolo/yoloe/train.py

@@ -217,7 +217,7 @@ class YOLOETrainerFromScratch(YOLOETrainer, WorldTrainerFromScratch):
         cache_path = cache_dir / f"text_embeddings_{model.replace(':', '_').replace('/', '_')}.pt"
         if cache_path.exists():
             LOGGER.info(f"Reading existed cache from '{cache_path}'")
-            txt_map = torch.load(cache_path)
+            txt_map = torch.load(cache_path, map_location=self.device)
             if sorted(txt_map.keys()) == sorted(texts):
                 return txt_map
         LOGGER.info(f"Caching text embeddings to '{cache_path}'")

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/nn/tasks.py

@@ -80,6 +80,7 @@ from ultralytics.utils.loss import (
     v8SegmentationLoss,
 )
 from ultralytics.utils.ops import make_divisible
+from ultralytics.utils.patches import torch_load
 from ultralytics.utils.plotting import feature_visualization
 from ultralytics.utils.torch_utils import (
     fuse_conv_and_bn,
@@ -248,6 +249,8 @@ class BaseModel(torch.nn.Module):
                     m.forward = m.forward_fuse
                 if isinstance(m, v10Detect):
                     m.fuse()  # remove one2many head
+                if isinstance(m, YOLOEDetect) and hasattr(self, "pe"):
+                    m.fuse(self.pe.to(next(self.model.parameters()).device))
             self.info(verbose=verbose)
 
         return self
@@ -1441,9 +1444,9 @@ def torch_safe_load(weight, safe_only=False):
                 safe_pickle.Unpickler = SafeUnpickler
                 safe_pickle.load = lambda file_obj: SafeUnpickler(file_obj).load()
                 with open(file, "rb") as f:
-                    ckpt = torch.load(f, pickle_module=safe_pickle)
+                    ckpt = torch_load(f, pickle_module=safe_pickle)
             else:
-                ckpt = torch.load(file, map_location="cpu")
+                ckpt = torch_load(file, map_location="cpu")
 
     except ModuleNotFoundError as e:  # e.name is missing module name
         if e.name == "models":
@@ -1469,7 +1472,7 @@ def torch_safe_load(weight, safe_only=False):
             f"run a command with an official Ultralytics model, i.e. 'yolo predict model=yolo11n.pt'"
         )
         check_requirements(e.name)  # install missing module
-        ckpt = torch.load(file, map_location="cpu")
+        ckpt = torch_load(file, map_location="cpu")
 
     if not isinstance(ckpt, dict):
         # File is likely a YOLO instance saved with i.e. torch.save(model, "saved_model.pt")

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/solutions/region_counter.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-from typing import Any, List, Tuple
+from typing import Any, Dict, List, Tuple
 
 import numpy as np
 
@@ -26,6 +26,7 @@ class RegionCounter(BaseSolution):
     Methods:
         add_region: Add a new counting region with specified attributes.
         process: Process video frames to count objects in each region.
+        initialize_regions: Initialize zones to count the objects in each one. Zones could be multiple as well.
 
     Examples:
         Initialize a RegionCounter and add a counting region
@@ -42,12 +43,12 @@ class RegionCounter(BaseSolution):
             "name": "Default Region",
             "polygon": None,
             "counts": 0,
-            "dragging": False,
             "region_color": (255, 255, 255),
             "text_color": (0, 0, 0),
         }
         self.region_counts = {}
         self.counting_regions = []
+        self.initialize_regions()
 
     def add_region(
         self,
@@ -55,7 +56,7 @@ class RegionCounter(BaseSolution):
         polygon_points: List[Tuple],
         region_color: Tuple[int, int, int],
         text_color: Tuple[int, int, int],
-    ) -> None:
+    ) -> Dict[str, Any]:
         """
         Add a new region to the counting list based on the provided template with specific attributes.
 
@@ -64,6 +65,9 @@ class RegionCounter(BaseSolution):
             polygon_points (List[Tuple]): List of (x, y) coordinates defining the region's polygon.
             region_color (Tuple[int, int, int]): BGR color for region visualization.
             text_color (Tuple[int, int, int]): BGR color for the text within the region.
+
+        Returns:
+            (Dict[str, any]): Returns a dictionary including the region information i.e. name, region_color etc.
         """
         region = self.region_template.copy()
         region.update(
@@ -75,6 +79,17 @@ class RegionCounter(BaseSolution):
             }
         )
         self.counting_regions.append(region)
+        return region
+
+    def initialize_regions(self):
+        """Initialize regions only once."""
+        if self.region is None:
+            self.initialize_region()
+        if not isinstance(self.region, dict):  # Ensure self.region is initialized and structured as a dictionary
+            self.region = {"Region#01": self.region}
+        for i, (name, pts) in enumerate(self.region.items()):
+            region = self.add_region(name, pts, colors(i, True), (255, 255, 255))
+            region["prepared_polygon"] = self.prep(region["polygon"])
 
     def process(self, im0: np.ndarray) -> SolutionResults:
         """
@@ -90,39 +105,21 @@ class RegionCounter(BaseSolution):
         self.extract_tracks(im0)
         annotator = SolutionAnnotator(im0, line_width=self.line_width)
 
-        # Ensure self.region is initialized and structured as a dictionary
-        if not isinstance(self.region, dict):
-            self.region = {"Region#01": self.region or self.initialize_region()}
-
-        # Draw only valid regions
-        for idx, (region_name, reg_pts) in enumerate(self.region.items(), start=1):
-            color = colors(idx, True)
-            annotator.draw_region(reg_pts, color, self.line_width * 2)
-            self.add_region(region_name, reg_pts, color, annotator.get_txt_color())
-
-        # Prepare regions for containment check (only process valid ones)
-        for region in self.counting_regions:
-            if "prepared_polygon" not in region:
-                region["prepared_polygon"] = self.prep(region["polygon"])
-
-        # Convert bounding boxes to NumPy array for center points
-        boxes_np = np.array([((box[0] + box[2]) / 2, (box[1] + box[3]) / 2) for box in self.boxes], dtype=np.float32)
-        points = [self.Point(pt) for pt in boxes_np]  # Convert centers to Point objects
-
-        # Process bounding boxes & check containment
-        if points:
-            for point, cls, track_id, box, conf in zip(points, self.clss, self.track_ids, self.boxes, self.confs):
-                annotator.box_label(box, label=self.adjust_box_label(cls, conf, track_id), color=colors(track_id, True))
-
-                for region in self.counting_regions:
-                    if region["prepared_polygon"].contains(point):
-                        region["counts"] += 1
-                        self.region_counts[region["name"]] = region["counts"]
+        for box, cls, track_id, conf in zip(self.boxes, self.clss, self.track_ids, self.confs):
+            annotator.box_label(box, label=self.adjust_box_label(cls, conf, track_id), color=colors(track_id, True))
+            center = self.Point(((box[0] + box[2]) / 2, (box[1] + box[3]) / 2))
+            for region in self.counting_regions:
+                if region["prepared_polygon"].contains(center):
+                    region["counts"] += 1
+                    self.region_counts[region["name"]] = region["counts"]
 
         # Display region counts
         for region in self.counting_regions:
+            x1, y1, x2, y2 = map(int, region["polygon"].bounds)
+            pts = [(x1, y1), (x2, y1), (x2, y2), (x1, y2)]
+            annotator.draw_region(pts, region["region_color"], self.line_width * 2)
             annotator.text_label(
-                region["polygon"].bounds,
+                [x1, y1, x2, y2],
                 label=str(region["counts"]),
                 color=region["region_color"],
                 txt_color=region["text_color"],

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/solutions/solutions.py

@@ -115,7 +115,7 @@ class BaseSolution:
         self.device = self.CFG["device"]
 
         self.track_add_args = {  # Tracker additional arguments for advance configuration
-            k: self.CFG[k] for k in ["iou", "conf", "device", "max_det", "half", "tracker"]
+            k: self.CFG[k] for k in {"iou", "conf", "device", "max_det", "half", "tracker"}
         }  # verbose must be passed to track method; setting it False in YOLO still logs the track information.
 
         if is_cli and self.CFG["source"] is None:

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/__init__.py

@@ -25,7 +25,7 @@ import torch
 import tqdm
 
 from ultralytics import __version__
-from ultralytics.utils.patches import imread, imshow, imwrite, torch_load, torch_save  # for patches
+from ultralytics.utils.patches import imread, imshow, imwrite, torch_save  # for patches
 
 # PyTorch Multi-GPU DDP Constants
 RANK = int(os.getenv("RANK", -1))
@@ -1593,7 +1593,6 @@ TESTS_RUNNING = is_pytest_running() or is_github_action_running()
 set_sentry()
 
 # Apply monkey patches
-torch.load = torch_load
 torch.save = torch_save
 if WINDOWS:
     # Apply cv2 patches for non-ASCII and non-UTF characters in image paths

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/checks.py

@@ -896,6 +896,27 @@ def is_rockchip():
         return False
 
 
+def is_intel():
+    """
+    Check if the system has Intel hardware (CPU or GPU).
+
+    Returns:
+        (bool): True if Intel hardware is detected, False otherwise.
+    """
+    from ultralytics.utils.torch_utils import get_cpu_info
+
+    # Check CPU
+    if "intel" in get_cpu_info().lower():
+        return True
+
+    # Check GPU via xpu-smi
+    try:
+        result = subprocess.run(["xpu-smi", "discovery"], capture_output=True, text=True, timeout=5)
+        return "intel" in result.stdout.lower()
+    except (subprocess.TimeoutExpired, FileNotFoundError, subprocess.SubprocessError):
+        return False
+
+
 def is_sudo_available() -> bool:
     """
     Check if the sudo command is available in the environment.

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/metrics.py

@@ -488,7 +488,7 @@ class ConfusionMatrix(DataExportMixin):
         if ticklabels != "auto":
             ax.set_xticklabels(ticklabels, fontsize=tick_fontsize, rotation=90, ha="center")
             ax.set_yticklabels(ticklabels, fontsize=tick_fontsize)
-        for s in ["left", "right", "bottom", "top", "outline"]:
+        for s in {"left", "right", "bottom", "top", "outline"}:
             if s != "outline":
                 ax.spines[s].set_visible(False)  # Confusion matrix plot don't have outline
             cbar.ax.spines[s].set_visible(False)
@@ -1006,6 +1006,7 @@ class DetMetrics(SimpleClass, DataExportMixin):
             save_dir=save_dir,
             names=self.names,
             on_plot=on_plot,
+            prefix="Box",
         )[2:]
         self.box.nc = len(self.names)
         self.box.update(results)
@@ -1135,7 +1136,7 @@ class SegmentMetrics(DetMetrics):
         Returns:
             (Dict[str, np.ndarray]): Dictionary containing concatenated statistics arrays.
         """
-        stats = DetMetrics.process(self, on_plot=on_plot)  # process box stats
+        stats = DetMetrics.process(self, save_dir, plot, on_plot=on_plot)  # process box stats
         results_mask = ap_per_class(
             stats["tp_m"],
             stats["conf"],
@@ -1270,7 +1271,7 @@ class PoseMetrics(DetMetrics):
         Returns:
             (Dict[str, np.ndarray]): Dictionary containing concatenated statistics arrays.
         """
-        stats = DetMetrics.process(self, on_plot=on_plot)  # process box stats
+        stats = DetMetrics.process(self, save_dir, plot, on_plot=on_plot)  # process box stats
         results_pose = ap_per_class(
             stats["tp_p"],
             stats["conf"],

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/patches.py

@@ -90,7 +90,6 @@ def imshow(winname: str, mat: np.ndarray) -> None:
 
 
 # PyTorch functions ----------------------------------------------------------------------------------------------------
-_torch_load = torch.load  # copy to avoid recursion errors
 _torch_save = torch.save
 
 
@@ -116,7 +115,7 @@ def torch_load(*args, **kwargs):
     if TORCH_1_13 and "weights_only" not in kwargs:
         kwargs["weights_only"] = False
 
-    return _torch_load(*args, **kwargs)
+    return torch.load(*args, **kwargs)
 
 
 def torch_save(*args, **kwargs):

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/plotting.py

@@ -610,8 +610,8 @@ def plot_labels(boxes, cls, names=(), save_dir=Path(""), on_plot=None):
     ax[3].hist2d(x["width"], x["height"], bins=50, cmap=subplot_3_4_color)
     ax[3].set_xlabel("width")
     ax[3].set_ylabel("height")
-    for a in [0, 1, 2, 3]:
-        for s in ["top", "right", "left", "bottom"]:
+    for a in {0, 1, 2, 3}:
+        for s in {"top", "right", "left", "bottom"}:
             ax[a].spines[s].set_visible(False)
 
     fname = save_dir / "labels.jpg"

{ultralytics-8.3.161 → ultralytics-8.3.163}/ultralytics/utils/torch_utils.py

@@ -30,6 +30,7 @@ from ultralytics.utils import (
     colorstr,
 )
 from ultralytics.utils.checks import check_version
+from ultralytics.utils.patches import torch_load
 
 # Version checks (all default to version>=min_version)
 TORCH_1_9 = check_version(torch.__version__, "1.9.0")
@@ -724,7 +725,7 @@ def strip_optimizer(f: Union[str, Path] = "best.pt", s: str = "", updates: Dict[
         >>>    strip_optimizer(f)
     """
     try:
-        x = torch.load(f, map_location=torch.device("cpu"))
+        x = torch_load(f, map_location=torch.device("cpu"))
         assert isinstance(x, dict), "checkpoint is not a Python dictionary"
         assert "model" in x, "'model' missing from checkpoint"
     except Exception as e: