ultralytics 8.3.54__tar.gz → 8.3.56__tar.gz

{ultralytics-8.3.54/ultralytics.egg-info → ultralytics-8.3.56}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.54
+Version: 8.3.56
 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>
@@ -57,7 +57,6 @@ Requires-Dist: coverage[toml]; extra == "dev"
 Requires-Dist: mkdocs>=1.6.0; extra == "dev"
 Requires-Dist: mkdocs-material>=9.5.9; extra == "dev"
 Requires-Dist: mkdocstrings[python]; extra == "dev"
-Requires-Dist: mkdocs-jupyter; extra == "dev"
 Requires-Dist: mkdocs-redirects; extra == "dev"
 Requires-Dist: mkdocs-ultralytics-plugin>=0.1.8; extra == "dev"
 Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"

{ultralytics-8.3.54 → ultralytics-8.3.56}/pyproject.toml

@@ -90,7 +90,6 @@ dev = [
     "mkdocs>=1.6.0",
     "mkdocs-material>=9.5.9",
     "mkdocstrings[python]",
-    "mkdocs-jupyter", # notebooks
     "mkdocs-redirects", # 301 redirects
     "mkdocs-ultralytics-plugin>=0.1.8", # for meta descriptions and images, dates and authors
     "mkdocs-macros-plugin>=1.0.5"  # duplicating content (i.e. export tables) in multiple places

{ultralytics-8.3.54 → ultralytics-8.3.56}/tests/__init__.py

@@ -17,7 +17,6 @@ __all__ = (
     "SOURCE",
     "SOURCES_LIST",
     "TMP",
-    "IS_TMP_WRITEABLE",
     "CUDA_IS_AVAILABLE",
     "CUDA_DEVICE_COUNT",
 )

{ultralytics-8.3.54 → ultralytics-8.3.56}/tests/conftest.py

@@ -74,10 +74,10 @@ def pytest_terminal_summary(terminalreporter, exitstatus, config):
 
     # Remove files
     models = [path for x in ["*.onnx", "*.torchscript"] for path in WEIGHTS_DIR.rglob(x)]
-    for file in ["bus.jpg", "yolo11n.onnx", "yolo11n.torchscript"] + models:
+    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)]
-    for directory in [TMP.parents[1] / ".pytest_cache", TMP] + models:
+    for directory in [WEIGHTS_DIR / "path with spaces", TMP.parents[1] / ".pytest_cache", TMP] + models:
         shutil.rmtree(directory, ignore_errors=True)

{ultralytics-8.3.54 → ultralytics-8.3.56}/tests/test_cli.py

@@ -59,7 +59,8 @@ def test_rtdetr(task="detect", model="yolov8n-rtdetr.yaml", data="coco8.yaml"):
     run(f"yolo train {task} model={model} data={data} --imgsz= 160 epochs =1, cache = disk fraction=0.25")
     run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
     if TORCH_1_9:
-        run(f"yolo predict {task} model='rtdetr-l.pt' source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
+        weights = WEIGHTS_DIR / "rtdetr-l.pt"
+        run(f"yolo predict {task} model={weights} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM with CLIP is not supported in Python 3.12")

{ultralytics-8.3.54 → ultralytics-8.3.56}/tests/test_python.py

@@ -576,11 +576,11 @@ def test_model_embeddings():
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="YOLOWorld with CLIP is not supported in Python 3.12")
 def test_yolo_world():
     """Tests YOLO world models with CLIP support, including detection and training scenarios."""
-    model = YOLO("yolov8s-world.pt")  # no YOLO11n-world model yet
+    model = YOLO(WEIGHTS_DIR / "yolov8s-world.pt")  # no YOLO11n-world model yet
     model.set_classes(["tree", "window"])
     model(SOURCE, conf=0.01)
 
-    model = YOLO("yolov8s-worldv2.pt")  # no YOLO11n-world model yet
+    model = YOLO(WEIGHTS_DIR / "yolov8s-worldv2.pt")  # no YOLO11n-world model yet
     # Training from a pretrained model. Eval is included at the final stage of training.
     # Use dota8.yaml which has fewer categories to reduce the inference time of CLIP model
     model.train(

{ultralytics-8.3.54 → ultralytics-8.3.56}/tests/test_solutions.py

@@ -3,55 +3,64 @@
 import cv2
 import pytest
 
+from tests import TMP
 from ultralytics import YOLO, solutions
+from ultralytics.utils import ASSETS_URL, WEIGHTS_DIR
 from ultralytics.utils.downloads import safe_download
 
-MAJOR_SOLUTIONS_DEMO = "https://github.com/ultralytics/assets/releases/download/v0.0.0/solutions_ci_demo.mp4"
-WORKOUTS_SOLUTION_DEMO = "https://github.com/ultralytics/assets/releases/download/v0.0.0/solution_ci_pose_demo.mp4"
+DEMO_VIDEO = "solutions_ci_demo.mp4"
+POSE_VIDEO = "solution_ci_pose_demo.mp4"
 
 
 @pytest.mark.slow
 def test_major_solutions():
-    """Test the object counting, heatmap, speed estimation and queue management solution."""
-    safe_download(url=MAJOR_SOLUTIONS_DEMO)
-    cap = cv2.VideoCapture("solutions_ci_demo.mp4")
+    """Test the object counting, heatmap, speed estimation, trackzone and queue management solution."""
+    safe_download(url=f"{ASSETS_URL}/{DEMO_VIDEO}", dir=TMP)
+    cap = cv2.VideoCapture(str(TMP / DEMO_VIDEO))
     assert cap.isOpened(), "Error reading video file"
     region_points = [(20, 400), (1080, 400), (1080, 360), (20, 360)]
     counter = solutions.ObjectCounter(region=region_points, model="yolo11n.pt", show=False)  # Test object counter
     heatmap = solutions.Heatmap(colormap=cv2.COLORMAP_PARULA, model="yolo11n.pt", show=False)  # Test heatmaps
+    heatmap_count = solutions.Heatmap(
+        colormap=cv2.COLORMAP_PARULA, model="yolo11n.pt", show=False, region=region_points
+    )  # Test heatmaps with object counting
     speed = solutions.SpeedEstimator(region=region_points, model="yolo11n.pt", show=False)  # Test queue manager
     queue = solutions.QueueManager(region=region_points, model="yolo11n.pt", show=False)  # Test speed estimation
     line_analytics = solutions.Analytics(analytics_type="line", model="yolo11n.pt", show=False)  # line analytics
     pie_analytics = solutions.Analytics(analytics_type="pie", model="yolo11n.pt", show=False)  # line analytics
     bar_analytics = solutions.Analytics(analytics_type="bar", model="yolo11n.pt", show=False)  # line analytics
     area_analytics = solutions.Analytics(analytics_type="area", model="yolo11n.pt", show=False)  # line analytics
+    trackzone = solutions.TrackZone(region=region_points, model="yolo11n.pt", show=False)  # Test trackzone
     frame_count = 0  # Required for analytics
     while cap.isOpened():
         success, im0 = cap.read()
         if not success:
             break
+        frame_count += 1
         original_im0 = im0.copy()
         _ = counter.count(original_im0.copy())
         _ = heatmap.generate_heatmap(original_im0.copy())
+        _ = heatmap_count.generate_heatmap(original_im0.copy())
         _ = speed.estimate_speed(original_im0.copy())
         _ = queue.process_queue(original_im0.copy())
         _ = line_analytics.process_data(original_im0.copy(), frame_count)
         _ = pie_analytics.process_data(original_im0.copy(), frame_count)
         _ = bar_analytics.process_data(original_im0.copy(), frame_count)
         _ = area_analytics.process_data(original_im0.copy(), frame_count)
+        _ = trackzone.trackzone(original_im0.copy())
     cap.release()
 
     # Test workouts monitoring
-    safe_download(url=WORKOUTS_SOLUTION_DEMO)
-    cap1 = cv2.VideoCapture("solution_ci_pose_demo.mp4")
-    assert cap1.isOpened(), "Error reading video file"
-    gym = solutions.AIGym(line_width=2, kpts=[5, 11, 13], show=False)
-    while cap1.isOpened():
-        success, im0 = cap1.read()
+    safe_download(url=f"{ASSETS_URL}/{POSE_VIDEO}", dir=TMP)
+    cap = cv2.VideoCapture(str(TMP / POSE_VIDEO))
+    assert cap.isOpened(), "Error reading video file"
+    gym = solutions.AIGym(kpts=[5, 11, 13], show=False)
+    while cap.isOpened():
+        success, im0 = cap.read()
         if not success:
             break
         _ = gym.monitor(im0)
-    cap1.release()
+    cap.release()
 
 
 @pytest.mark.slow
@@ -59,9 +68,9 @@ def test_instance_segmentation():
     """Test the instance segmentation solution."""
     from ultralytics.utils.plotting import Annotator, colors
 
-    model = YOLO("yolo11n-seg.pt")
+    model = YOLO(WEIGHTS_DIR / "yolo11n-seg.pt")
     names = model.names
-    cap = cv2.VideoCapture("solutions_ci_demo.mp4")
+    cap = cv2.VideoCapture(TMP / DEMO_VIDEO)
     assert cap.isOpened(), "Error reading video file"
     while cap.isOpened():
         success, im0 = cap.read()

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.54"
+__version__ = "8.3.56"
 
 import os
 

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/cfg/__init__.py

@@ -86,7 +86,7 @@ SOLUTIONS_HELP_MSG = f"""
         yolo solutions count source="path/to/video/file.mp4" region=[(20, 400), (1080, 400), (1080, 360), (20, 360)]
 
     2. Call heatmaps solution
-        yolo solutions heatmap colormap=cv2.COLORMAP_PARAULA model=yolo11n.pt
+        yolo solutions heatmap colormap=cv2.COLORMAP_PARULA model=yolo11n.pt
 
     3. Call queue management solution
         yolo solutions queue region=[(20, 400), (1080, 400), (1080, 360), (20, 360)] model=yolo11n.pt
@@ -303,7 +303,7 @@ def get_cfg(cfg: Union[str, Path, Dict, SimpleNamespace] = DEFAULT_CFG_DICT, ove
         if k in cfg and isinstance(cfg[k], (int, float)):
             cfg[k] = str(cfg[k])
     if cfg.get("name") == "model":  # assign model to 'name' arg
-        cfg["name"] = cfg.get("model", "").split(".")[0]
+        cfg["name"] = str(cfg.get("model", "")).split(".")[0]
         LOGGER.warning(f"WARNING ⚠️ 'name=model' automatically updated to 'name={cfg['name']}'.")
 
     # Type and Value checks
@@ -694,7 +694,7 @@ def handle_yolo_solutions(args: List[str]) -> None:
                 str(ROOT / "solutions/streamlit_inference.py"),
                 "--server.headless",
                 "true",
-                overrides["model"],
+                overrides.pop("model", "yolo11n.pt"),
             ]
         )
     else:

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/cfg/datasets/coco-pose.yaml

@@ -1,5 +1,5 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
-# COCO 2017 dataset https://cocodataset.org by Microsoft
+# COCO 2017 Keypoints dataset https://cocodataset.org by Microsoft
 # Documentation: https://docs.ultralytics.com/datasets/pose/coco/
 # Example usage: yolo train data=coco-pose.yaml
 # parent
@@ -9,9 +9,9 @@
 
 # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
 path: ../datasets/coco-pose # dataset root dir
-train: train2017.txt # train images (relative to 'path') 118287 images
-val: val2017.txt # val images (relative to 'path') 5000 images
-test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+train: train2017.txt # train images (relative to 'path') 56599 images
+val: val2017.txt # val images (relative to 'path') 2346 images
+test: test-dev2017.txt # 20288 of 40670 images, submit to https://codalab.lisn.upsaclay.fr/competitions/7403
 
 # Keypoints
 kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/cfg/datasets/lvis.yaml

@@ -11,7 +11,7 @@
 path: ../datasets/lvis # dataset root dir
 train: train.txt # train images (relative to 'path') 100170 images
 val: val.txt # val images (relative to 'path') 19809 images
-minival: minival.txt # minval images (relative to 'path') 5000 images
+minival: minival.txt # minival images (relative to 'path') 5000 images
 
 names:
   0: aerosol can/spray can

ultralytics-8.3.56/ultralytics/cfg/datasets/medical-pills.yaml

@@ -0,0 +1,21 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Medical-pills dataset by Ultralytics
+# Documentation: https://docs.ultralytics.com/datasets/detect/medical-pills/
+# Example usage: yolo train data=medical-pills.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── medical-pills  ← downloads here (8.19 MB)
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/medical-pills # dataset root dir
+train: train/images # train images (relative to 'path') 92 images
+val: valid/images # val images (relative to 'path') 23 images
+test: # test images (relative to 'path')
+
+# Classes
+names:
+  0: pill
+
+# Download script/URL (optional)
+download: https://github.com/ultralytics/assets/releases/download/v0.0.0/medical-pills.zip

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/cfg/solutions/default.yaml

@@ -12,7 +12,7 @@ colormap: #  (int | str) colormap for heatmap, Only OPENCV supported colormaps c
 # 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].
+kpts: [6, 8, 10] # (list[int]) keypoints for workouts monitoring, i.e. for push-ups kpts have values of [6, 8, 10].
 
 # Analytics settings ---------------------------------------------------------------------------------------------------
 analytics_type: "line" # (str) analytics type i.e "line", "pie", "bar" or "area" charts.

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/data/augment.py

@@ -441,7 +441,8 @@ class BaseMixTransform:
         """
         raise NotImplementedError
 
-    def _update_label_text(self, labels):
+    @staticmethod
+    def _update_label_text(labels):
         """
         Updates label text and class IDs for mixed labels in image augmentation.
 
@@ -1259,7 +1260,8 @@ class RandomPerspective:
         labels["resized_shape"] = img.shape[:2]
         return labels
 
-    def box_candidates(self, box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
+    @staticmethod
+    def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
         """
         Compute candidate boxes for further processing based on size and aspect ratio criteria.
 
@@ -1598,7 +1600,8 @@ class LetterBox:
         else:
             return img
 
-    def _update_labels(self, labels, ratio, padw, padh):
+    @staticmethod
+    def _update_labels(labels, ratio, padw, padh):
         """
         Updates labels after applying letterboxing to an image.
 

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/data/converter.py

@@ -266,7 +266,7 @@ def convert_coco(
             # since LVIS val set contains images from COCO 2017 train in addition to the COCO 2017 val split.
             (fn / "train2017").mkdir(parents=True, exist_ok=True)
             (fn / "val2017").mkdir(parents=True, exist_ok=True)
-        with open(json_file) as f:
+        with open(json_file, encoding="utf-8") as f:
             data = json.load(f)
 
         # Create image dict

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/data/dataset.py

@@ -68,7 +68,7 @@ class YOLODataset(BaseDataset):
         Cache dataset labels, check images and read shapes.
 
         Args:
-            path (Path): Path where to save the cache file. Default is Path('./labels.cache').
+            path (Path): Path where to save the cache file. Default is Path("./labels.cache").
 
         Returns:
             (dict): labels.
@@ -219,7 +219,7 @@ class YOLODataset(BaseDataset):
         segment_resamples = 100 if self.use_obb else 1000
         if len(segments) > 0:
             # make sure segments interpolate correctly if original length is greater than segment_resamples
-            max_len = max([len(s) for s in segments])
+            max_len = max(len(s) for s in segments)
             segment_resamples = (max_len + 1) if segment_resamples < max_len else segment_resamples
             # list[np.array(segment_resamples, 2)] * num_samples
             segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0)
@@ -323,7 +323,8 @@ class GroundingDataset(YOLODataset):
                 if box[2] <= 0 or box[3] <= 0:
                     continue
 
-                cat_name = " ".join([img["caption"][t[0] : t[1]] for t in ann["tokens_positive"]])
+                caption = img["caption"]
+                cat_name = " ".join([caption[t[0] : t[1]] for t in ann["tokens_positive"]])
                 if cat_name not in cat2id:
                     cat2id[cat_name] = len(cat2id)
                     texts.append([cat_name])

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/engine/exporter.py

@@ -285,6 +285,7 @@ class Exporter:
                 "(torchscript, onnx, openvino, engine, coreml) formats. "
                 "See https://docs.ultralytics.com/models/yolo-world for details."
             )
+            model.clip_model = None  # openvino int8 export error: https://github.com/ultralytics/ultralytics/pull/18445
         if self.args.int8 and not self.args.data:
             self.args.data = DEFAULT_CFG.data or TASK2DATA[getattr(model, "task", "detect")]  # assign default data
             LOGGER.warning(
@@ -602,7 +603,7 @@ class Exporter:
     @try_export
     def export_paddle(self, prefix=colorstr("PaddlePaddle:")):
         """YOLO Paddle export."""
-        check_requirements(("paddlepaddle", "x2paddle"))
+        check_requirements(("paddlepaddle-gpu" if torch.cuda.is_available() else "paddlepaddle", "x2paddle"))
         import x2paddle  # noqa
         from x2paddle.convert import pytorch2paddle  # noqa
 
@@ -813,7 +814,7 @@ class Exporter:
         workspace = int(self.args.workspace * (1 << 30)) if self.args.workspace is not None else 0
         if is_trt10 and workspace > 0:
             config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace)
-        elif workspace > 0 and not is_trt10:  # TensorRT versions 7, 8
+        elif workspace > 0:  # TensorRT versions 7, 8
             config.max_workspace_size = workspace
         flag = 1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)
         network = builder.create_network(flag)
@@ -949,7 +950,7 @@ class Exporter:
                 "sng4onnx>=1.0.1",  # required by 'onnx2tf' package
                 "onnx_graphsurgeon>=0.3.26",  # required by 'onnx2tf' package
                 "onnx>=1.12.0",
-                "onnx2tf>1.17.5,<=1.22.3",
+                "onnx2tf>1.17.5,<=1.26.3",
                 "onnxslim>=0.1.31",
                 "tflite_support<=0.4.3" if IS_JETSON else "tflite_support",  # fix ImportError 'GLIBCXX_3.4.29'
                 "flatbuffers>=23.5.26,<100",  # update old 'flatbuffers' included inside tensorflow package
@@ -1136,7 +1137,7 @@ class Exporter:
         if getattr(self.model, "end2end", False):
             raise ValueError("IMX export is not supported for end2end models.")
         if "C2f" not in self.model.__str__():
-            raise ValueError("IMX export is only supported for YOLOv8 detection models")
+            raise ValueError("IMX export is only supported for YOLOv8n detection models")
         check_requirements(("model-compression-toolkit==2.1.1", "sony-custom-layers==0.2.0", "tensorflow==2.12.0"))
         check_requirements("imx500-converter[pt]==3.14.3")  # Separate requirements for imx500-converter
 

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/engine/model.py

@@ -2,7 +2,7 @@
 
 import inspect
 from pathlib import Path
-from typing import Dict, List, Union
+from typing import Any, Dict, List, Union
 
 import numpy as np
 import torch
@@ -152,7 +152,7 @@ class Model(nn.Module):
         self,
         source: Union[str, Path, int, Image.Image, list, tuple, np.ndarray, torch.Tensor] = None,
         stream: bool = False,
-        **kwargs,
+        **kwargs: Any,
     ) -> list:
         """
         Alias for the predict method, enabling the model instance to be callable for predictions.
@@ -165,7 +165,7 @@ class Model(nn.Module):
                 the image(s) to make predictions on. Can be a file path, URL, PIL image, numpy array, PyTorch
                 tensor, or a list/tuple of these.
             stream (bool): If True, treat the input source as a continuous stream for predictions.
-            **kwargs (Any): Additional keyword arguments to configure the prediction process.
+            **kwargs: Additional keyword arguments to configure the prediction process.
 
         Returns:
             (List[ultralytics.engine.results.Results]): A list of prediction results, each encapsulated in a
@@ -466,7 +466,7 @@ class Model(nn.Module):
         self,
         source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None,
         stream: bool = False,
-        **kwargs,
+        **kwargs: Any,
     ) -> list:
         """
         Generates image embeddings based on the provided source.
@@ -478,7 +478,7 @@ class Model(nn.Module):
             source (str | Path | int | List | Tuple | np.ndarray | torch.Tensor): The source of the image for
                 generating embeddings. Can be a file path, URL, PIL image, numpy array, etc.
             stream (bool): If True, predictions are streamed.
-            **kwargs (Any): Additional keyword arguments for configuring the embedding process.
+            **kwargs: Additional keyword arguments for configuring the embedding process.
 
         Returns:
             (List[torch.Tensor]): A list containing the image embeddings.
@@ -501,7 +501,7 @@ class Model(nn.Module):
         source: Union[str, Path, int, Image.Image, list, tuple, np.ndarray, torch.Tensor] = None,
         stream: bool = False,
         predictor=None,
-        **kwargs,
+        **kwargs: Any,
     ) -> List[Results]:
         """
         Performs predictions on the given image source using the YOLO model.
@@ -517,7 +517,7 @@ class Model(nn.Module):
             stream (bool): If True, treats the input source as a continuous stream for predictions.
             predictor (BasePredictor | None): An instance of a custom predictor class for making predictions.
                 If None, the method uses a default predictor.
-            **kwargs (Any): Additional keyword arguments for configuring the prediction process.
+            **kwargs: Additional keyword arguments for configuring the prediction process.
 
         Returns:
             (List[ultralytics.engine.results.Results]): A list of prediction results, each encapsulated in a
@@ -562,7 +562,7 @@ class Model(nn.Module):
         source: Union[str, Path, int, list, tuple, np.ndarray, torch.Tensor] = None,
         stream: bool = False,
         persist: bool = False,
-        **kwargs,
+        **kwargs: Any,
     ) -> List[Results]:
         """
         Conducts object tracking on the specified input source using the registered trackers.
@@ -576,7 +576,7 @@ class Model(nn.Module):
                 tracking. Can be a file path, URL, or video stream.
             stream (bool): If True, treats the input source as a continuous video stream. Defaults to False.
             persist (bool): If True, persists trackers between different calls to this method. Defaults to False.
-            **kwargs (Any): Additional keyword arguments for configuring the tracking process.
+            **kwargs: Additional keyword arguments for configuring the tracking process.
 
         Returns:
             (List[ultralytics.engine.results.Results]): A list of tracking results, each a Results object.
@@ -607,7 +607,7 @@ class Model(nn.Module):
     def val(
         self,
         validator=None,
-        **kwargs,
+        **kwargs: Any,
     ):
         """
         Validates the model using a specified dataset and validation configuration.
@@ -619,7 +619,7 @@ class Model(nn.Module):
         Args:
             validator (ultralytics.engine.validator.BaseValidator | None): An instance of a custom validator class for
                 validating the model.
-            **kwargs (Any): Arbitrary keyword arguments for customizing the validation process.
+            **kwargs: Arbitrary keyword arguments for customizing the validation process.
 
         Returns:
             (ultralytics.utils.metrics.DetMetrics): Validation metrics obtained from the validation process.
@@ -642,7 +642,7 @@ class Model(nn.Module):
 
     def benchmark(
         self,
-        **kwargs,
+        **kwargs: Any,
     ):
         """
         Benchmarks the model across various export formats to evaluate performance.
@@ -653,7 +653,7 @@ class Model(nn.Module):
         defaults, and any additional user-provided keyword arguments.
 
         Args:
-            **kwargs (Any): Arbitrary keyword arguments to customize the benchmarking process. These are combined with
+            **kwargs: Arbitrary keyword arguments to customize the benchmarking process. These are combined with
                 default configurations, model-specific arguments, and method defaults. Common options include:
                 - data (str): Path to the dataset for benchmarking.
                 - imgsz (int | List[int]): Image size for benchmarking.
@@ -691,7 +691,7 @@ class Model(nn.Module):
 
     def export(
         self,
-        **kwargs,
+        **kwargs: Any,
     ) -> str:
         """
         Exports the model to a different format suitable for deployment.
@@ -701,7 +701,7 @@ class Model(nn.Module):
         defaults, and any additional arguments provided.
 
         Args:
-            **kwargs (Dict): Arbitrary keyword arguments to customize the export process. These are combined with
+            **kwargs: Arbitrary keyword arguments to customize the export process. These are combined with
                 the model's overrides and method defaults. Common arguments include:
                 format (str): Export format (e.g., 'onnx', 'engine', 'coreml').
                 half (bool): Export model in half-precision.
@@ -740,7 +740,7 @@ class Model(nn.Module):
     def train(
         self,
         trainer=None,
-        **kwargs,
+        **kwargs: Any,
     ):
         """
         Trains the model using the specified dataset and training configuration.
@@ -755,7 +755,7 @@ class Model(nn.Module):
 
         Args:
             trainer (BaseTrainer | None): Custom trainer instance for model training. If None, uses default.
-            **kwargs (Any): Arbitrary keyword arguments for training configuration. Common options include:
+            **kwargs: Arbitrary keyword arguments for training configuration. Common options include:
                 data (str): Path to dataset configuration file.
                 epochs (int): Number of training epochs.
                 batch_size (int): Batch size for training.
@@ -816,8 +816,8 @@ class Model(nn.Module):
         self,
         use_ray=False,
         iterations=10,
-        *args,
-        **kwargs,
+        *args: Any,
+        **kwargs: Any,
     ):
         """
         Conducts hyperparameter tuning for the model, with an option to use Ray Tune.
@@ -830,8 +830,8 @@ class Model(nn.Module):
         Args:
             use_ray (bool): If True, uses Ray Tune for hyperparameter tuning. Defaults to False.
             iterations (int): The number of tuning iterations to perform. Defaults to 10.
-            *args (List): Variable length argument list for additional arguments.
-            **kwargs (Dict): Arbitrary keyword arguments. These are combined with the model's overrides and defaults.
+            *args: Variable length argument list for additional arguments.
+            **kwargs: Arbitrary keyword arguments. These are combined with the model's overrides and defaults.
 
         Returns:
             (Dict): A dictionary containing the results of the hyperparameter search.
@@ -1170,6 +1170,4 @@ class Model(nn.Module):
             >>> print(model.stride)
             >>> print(model.task)
         """
-        if name == "model":
-            return self._modules["model"]
-        return getattr(self.model, name)
+        return self._modules["model"] if name == "model" else getattr(self.model, name)

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/engine/validator.py

@@ -245,7 +245,7 @@ class BaseValidator:
 
                 cost_matrix = iou * (iou >= threshold)
                 if cost_matrix.any():
-                    labels_idx, detections_idx = scipy.optimize.linear_sum_assignment(cost_matrix, maximize=True)
+                    labels_idx, detections_idx = scipy.optimize.linear_sum_assignment(cost_matrix)
                     valid = cost_matrix[labels_idx, detections_idx] > 0
                     if valid.any():
                         correct[detections_idx[valid], i] = True

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/models/sam/modules/tiny_encoder.py

@@ -955,7 +955,8 @@ class TinyViT(nn.Module):
 
         self.apply(_check_lr_scale)
 
-    def _init_weights(self, m):
+    @staticmethod
+    def _init_weights(m):
         """Initializes weights for linear and normalization layers in the TinyViT model."""
         if isinstance(m, nn.Linear):
             # NOTE: This initialization is needed only for training.

{ultralytics-8.3.54 → ultralytics-8.3.56}/ultralytics/models/sam/predict.py

@@ -91,9 +91,9 @@ class Predictor(BasePredictor):
             _callbacks (Dict | None): Dictionary of callback functions to customize behavior.
 
         Examples:
-            >>> predictor = Predictor(cfg=DEFAULT_CFG)
-            >>> predictor = Predictor(overrides={"imgsz": 640})
-            >>> predictor = Predictor(_callbacks={"on_predict_start": custom_callback})
+            >>> predictor_example = Predictor(cfg=DEFAULT_CFG)
+            >>> predictor_example_with_imgsz = Predictor(overrides={"imgsz": 640})
+            >>> predictor_example_with_callback = Predictor(_callbacks={"on_predict_start": custom_callback})
         """
         if overrides is None:
             overrides = {}
@@ -215,7 +215,7 @@ class Predictor(BasePredictor):
             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) 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.
+            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.
 
@@ -260,7 +260,7 @@ class Predictor(BasePredictor):
             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.
+            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:
@@ -853,8 +853,8 @@ class SAM2VideoPredictor(SAM2Predictor):
 
         Examples:
             >>> predictor = SAM2VideoPredictor(cfg=DEFAULT_CFG)
-            >>> predictor = SAM2VideoPredictor(overrides={"imgsz": 640})
-            >>> predictor = SAM2VideoPredictor(_callbacks={"on_predict_start": custom_callback})
+            >>> predictor_example_with_imgsz = SAM2VideoPredictor(overrides={"imgsz": 640})
+            >>> predictor_example_with_callback = SAM2VideoPredictor(_callbacks={"on_predict_start": custom_callback})
         """
         super().__init__(cfg, overrides, _callbacks)
         self.inference_state = {}
@@ -1377,7 +1377,7 @@ class SAM2VideoPredictor(SAM2Predictor):
             if "maskmem_pos_enc" not in model_constants:
                 assert isinstance(out_maskmem_pos_enc, list)
                 # only take the slice for one object, since it's same across objects
-                maskmem_pos_enc = [x[0:1].clone() for x in out_maskmem_pos_enc]
+                maskmem_pos_enc = [x[:1].clone() for x in out_maskmem_pos_enc]
                 model_constants["maskmem_pos_enc"] = maskmem_pos_enc
             else:
                 maskmem_pos_enc = model_constants["maskmem_pos_enc"]