ultralytics 8.3.115__tar.gz → 8.3.117__tar.gz

{ultralytics-8.3.115/ultralytics.egg-info → ultralytics-8.3.117}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.115
+Version: 8.3.117
 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>
@@ -60,14 +60,13 @@ Requires-Dist: mkdocs-ultralytics-plugin>=0.1.17; extra == "dev"
 Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"
 Provides-Extra: export
 Requires-Dist: onnx>=1.12.0; extra == "export"
-Requires-Dist: coremltools>=8.0; (platform_system != "Windows" and python_version <= "3.12") and extra == "export"
+Requires-Dist: coremltools>=8.0; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.12") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"
 Requires-Dist: tensorflow>=2.0.0; extra == "export"
-Requires-Dist: tensorflowjs>=4.0.0; extra == "export"
+Requires-Dist: tensorflowjs>=2.0.0; extra == "export"
 Requires-Dist: tensorstore>=0.1.63; (platform_machine == "aarch64" and python_version >= "3.9") and extra == "export"
 Requires-Dist: keras; extra == "export"
-Requires-Dist: flatbuffers<100,>=23.5.26; platform_machine == "aarch64" and extra == "export"
 Requires-Dist: h5py!=3.11.0; platform_machine == "aarch64" and extra == "export"
 Provides-Extra: solutions
 Requires-Dist: shapely<2.1.0,>=2.0.0; extra == "solutions"

{ultralytics-8.3.115 → ultralytics-8.3.117}/pyproject.toml

@@ -94,14 +94,13 @@ dev = [
 ]
 export = [
     "onnx>=1.12.0", # ONNX export
-    "coremltools>=8.0; platform_system != 'Windows' and python_version <= '3.12'", # CoreML supported on macOS and Linux
+    "coremltools>=8.0; platform_system != 'Windows' and python_version <= '3.13'", # CoreML supported on macOS and Linux
     "scikit-learn>=1.3.2; platform_system != 'Windows' and python_version <= '3.12'", # CoreML k-means quantization
     "openvino>=2024.0.0",  # OpenVINO export
     "tensorflow>=2.0.0", # TF bug https://github.com/ultralytics/ultralytics/issues/5161
-    "tensorflowjs>=4.0.0", # TF.js export, automatically installs tensorflow
+    "tensorflowjs>=2.0.0", # TF.js export, automatically installs tensorflow
     "tensorstore>=0.1.63; platform_machine == 'aarch64' and python_version >= '3.9'", # for TF Raspberry Pi exports
     "keras", # not installed automatically by tensorflow>=2.16
-    "flatbuffers>=23.5.26,<100; platform_machine == 'aarch64'", # update old 'flatbuffers' included inside tensorflow package
     "h5py!=3.11.0; platform_machine == 'aarch64'", # fix h5py build issues due to missing aarch64 wheels in 3.11 release
 ]
 solutions = [

{ultralytics-8.3.115 → ultralytics-8.3.117}/tests/test_python.py

@@ -128,7 +128,7 @@ def test_predict_img(model_name):
         Image.open(SOURCE),  # PIL
         np.zeros((320, 640, 3), dtype=np.uint8),  # numpy
     ]
-    assert len(model(batch, imgsz=32)) == len(batch)  # multiple sources in a batch
+    assert len(model(batch, imgsz=32, classes=0)) == len(batch)  # multiple sources in a batch
 
 
 @pytest.mark.parametrize("model", MODELS)

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.115"
+__version__ = "8.3.117"
 
 import os
 

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/cfg/__init__.py

@@ -9,6 +9,7 @@ from typing import Any, Dict, List, Union
 
 import cv2
 
+from ultralytics import __version__
 from ultralytics.utils import (
     ASSETS,
     DEFAULT_CFG,
@@ -24,7 +25,6 @@ from ultralytics.utils import (
     SETTINGS_FILE,
     TESTS_RUNNING,
     IterableSimpleNamespace,
-    __version__,
     checks,
     colorstr,
     deprecation_warn,

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/augment.py

@@ -1027,10 +1027,9 @@ class RandomPerspective:
             border (Tuple[int, int]): Border dimensions for the transformed image.
 
         Returns:
-            (Tuple[np.ndarray, np.ndarray, float]): A tuple containing:
-                - np.ndarray: Transformed image.
-                - np.ndarray: 3x3 transformation matrix.
-                - float: Scale factor applied during the transformation.
+            img (np.ndarray): Transformed image.
+            M (np.ndarray): 3x3 transformation matrix.
+            s (float): Scale factor applied during the transformation.
 
         Examples:
             >>> import numpy as np
@@ -1124,9 +1123,8 @@ class RandomPerspective:
             M (np.ndarray): Affine transformation matrix with shape (3, 3).
 
         Returns:
-            (Tuple[np.ndarray, np.ndarray]): A tuple containing:
-                - New bounding boxes with shape (N, 4) in xyxy format.
-                - Transformed and clipped segments with shape (N, M, 2).
+            bboxes (np.ndarray): New bounding boxes with shape (N, 4) in xyxy format.
+            segments (np.ndarray): Transformed and clipped segments with shape (N, M, 2).
 
         Examples:
             >>> segments = np.random.rand(10, 500, 2)  # 10 segments with 500 points each

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/base.py

@@ -15,7 +15,8 @@ import psutil
 from torch.utils.data import Dataset
 
 from ultralytics.data.utils import FORMATS_HELP_MSG, HELP_URL, IMG_FORMATS, check_file_speeds
-from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM, imread
+from ultralytics.utils import DEFAULT_CFG, LOCAL_RANK, LOGGER, NUM_THREADS, TQDM
+from ultralytics.utils.patches import imread
 
 
 class BaseDataset(Dataset):
@@ -208,9 +209,9 @@ class BaseDataset(Dataset):
             rect_mode (bool, optional): Whether to use rectangular resizing.
 
         Returns:
-            (np.ndarray): Loaded image.
-            (tuple): Original image dimensions (h, w).
-            (tuple): Resized image dimensions (h, w).
+            (np.ndarray): Loaded image as a NumPy array.
+            (Tuple[int, int]): Original image dimensions in (height, width) format.
+            (Tuple[int, int]): Resized image dimensions in (height, width) format.
 
         Raises:
             FileNotFoundError: If the image file is not found.

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/build.py

@@ -187,13 +187,12 @@ def check_source(source):
         source (str | int | Path | List | Tuple | np.ndarray | PIL.Image | torch.Tensor): The input source to check.
 
     Returns:
-        (tuple): A tuple containing:
-            - source: The processed source.
-            - webcam (bool): Whether the source is a webcam.
-            - screenshot (bool): Whether the source is a screenshot.
-            - from_img (bool): Whether the source is an image or list of images.
-            - in_memory (bool): Whether the source is an in-memory object.
-            - tensor (bool): Whether the source is a torch.Tensor.
+        source (str | int | Path | List | Tuple | np.ndarray | PIL.Image | torch.Tensor): The processed source.
+        webcam (bool): Whether the source is a webcam.
+        screenshot (bool): Whether the source is a screenshot.
+        from_img (bool): Whether the source is an image or list of images.
+        in_memory (bool): Whether the source is an in-memory object.
+        tensor (bool): Whether the source is a torch.Tensor.
 
     Raises:
         TypeError: If the source type is unsupported.

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/dataset.py

@@ -12,14 +12,14 @@ import torch
 from PIL import Image
 from torch.utils.data import ConcatDataset
 
-from ultralytics.utils import LOCAL_RANK, NUM_THREADS, TQDM, colorstr
+from ultralytics.utils import LOCAL_RANK, LOGGER, NUM_THREADS, TQDM, colorstr
+from ultralytics.utils.instance import Instances
 from ultralytics.utils.ops import resample_segments, segments2boxes
 from ultralytics.utils.torch_utils import TORCHVISION_0_18
 
 from .augment import (
     Compose,
     Format,
-    Instances,
     LetterBox,
     RandomLoadText,
     classify_augmentations,
@@ -30,7 +30,6 @@ from .base import BaseDataset
 from .converter import merge_multi_segment
 from .utils import (
     HELP_URL,
-    LOGGER,
     check_file_speeds,
     get_hash,
     img2label_paths,
@@ -386,7 +385,7 @@ class YOLOMultiModalDataset(YOLODataset):
         Return category names for the dataset.
 
         Returns:
-            (Tuple[str]): List of class names.
+            (Set[str]): List of class names.
         """
         names = self.data["names"].values()
         return {n.strip() for name in names for n in name.split("/")}  # category names

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/loaders.py

@@ -16,8 +16,9 @@ import torch
 from PIL import Image
 
 from ultralytics.data.utils import FORMATS_HELP_MSG, IMG_FORMATS, VID_FORMATS
-from ultralytics.utils import IS_COLAB, IS_KAGGLE, LOGGER, imread, ops
+from ultralytics.utils import IS_COLAB, IS_KAGGLE, LOGGER, ops
 from ultralytics.utils.checks import check_requirements
+from ultralytics.utils.patches import imread
 
 
 @dataclass

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/data/utils.py

@@ -483,6 +483,7 @@ def check_cls_dataset(dataset, split=""):
 
     Returns:
         (dict): A dictionary containing the following keys:
+
             - 'train' (Path): The directory path containing the training set of the dataset.
             - 'val' (Path): The directory path containing the validation set of the dataset.
             - 'test' (Path): The directory path containing the test set of the dataset.

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/engine/exporter.py

@@ -70,6 +70,7 @@ from pathlib import Path
 import numpy as np
 import torch
 
+from ultralytics import __version__
 from ultralytics.cfg import TASK2DATA, get_cfg
 from ultralytics.data import build_dataloader
 from ultralytics.data.dataset import YOLODataset
@@ -81,7 +82,6 @@ from ultralytics.utils import (
     ARM64,
     DEFAULT_CFG,
     IS_COLAB,
-    IS_JETSON,
     LINUX,
     LOGGER,
     MACOS,
@@ -89,13 +89,13 @@ from ultralytics.utils import (
     RKNN_CHIPS,
     ROOT,
     WINDOWS,
-    __version__,
     callbacks,
     colorstr,
     get_default_args,
     yaml_save,
 )
 from ultralytics.utils.checks import (
+    IS_PYTHON_MINIMUM_3_12,
     check_imgsz,
     check_is_path_safe,
     check_requirements,
@@ -105,7 +105,7 @@ from ultralytics.utils.checks import (
 from ultralytics.utils.downloads import attempt_download_asset, get_github_assets, safe_download
 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, xywh2xyxy
+from ultralytics.utils.ops import Profile, nms_rotated
 from ultralytics.utils.torch_utils import TORCH_1_13, get_latest_opset, select_device
 
 
@@ -113,7 +113,7 @@ def export_formats():
     """Return a dictionary of Ultralytics YOLO export formats."""
     x = [
         ["PyTorch", "-", ".pt", True, True, []],
-        ["TorchScript", "torchscript", ".torchscript", True, True, ["batch", "optimize", "nms"]],
+        ["TorchScript", "torchscript", ".torchscript", True, True, ["batch", "optimize", "half", "nms"]],
         ["ONNX", "onnx", ".onnx", True, True, ["batch", "dynamic", "half", "opset", "simplify", "nms"]],
         [
             "OpenVINO",
@@ -384,6 +384,7 @@ class Exporter:
                 m.export = True
                 m.format = self.args.format
                 m.max_det = self.args.max_det
+                m.xyxy = self.args.nms and not coreml
             elif isinstance(m, C2f) and not is_tf_format:
                 # EdgeTPU does not support FlexSplitV while split provides cleaner ONNX graph
                 m.forward = m.forward_split
@@ -924,10 +925,8 @@ class Exporter:
                 "onnx>=1.12.0",
                 "onnx2tf>=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
                 "onnxruntime-gpu" if cuda else "onnxruntime",
-                "protobuf>=5",  # tflite_support pins <=4 but >=5 works
+                "protobuf>=5",
             ),
             cmds="--extra-index-url https://pypi.ngc.nvidia.com",  # onnx_graphsurgeon only on NVIDIA
         )
@@ -1278,8 +1277,20 @@ class Exporter:
 
         return f, None
 
-    def _add_tflite_metadata(self, file):
+    def _add_tflite_metadata(self, file, use_flatbuffers=False):
         """Add metadata to *.tflite models per https://ai.google.dev/edge/litert/models/metadata."""
+        if not use_flatbuffers:
+            import zipfile
+
+            with zipfile.ZipFile(file, "a", zipfile.ZIP_DEFLATED) as zf:
+                zf.writestr("metadata.json", json.dumps(self.metadata, indent=2))
+            return
+
+        if IS_PYTHON_MINIMUM_3_12:
+            LOGGER.warning(f"TFLite Support package may not be compatible with Python>=3.12 environments for {file}")
+
+        # Update old 'flatbuffers' included inside tensorflow package
+        check_requirements(("tflite_support", "flatbuffers>=23.5.26,<100; platform_machine == 'aarch64'"))
         import flatbuffers
 
         try:
@@ -1532,11 +1543,6 @@ class NMSModel(torch.nn.Module):
                 # Explicit length otherwise reshape error, hardcoded to `self.args.max_det * 5`
                 mask = score.topk(min(self.args.max_det * 5, score.shape[0])).indices
             box, score, cls, extra = box[mask], score[mask], cls[mask], extra[mask]
-            if not self.obb:
-                box = xywh2xyxy(box)
-                if self.is_tf:
-                    # TFlite bug returns less boxes
-                    box = torch.nn.functional.pad(box, (0, 0, 0, mask.shape[0] - box.shape[0]))
             nmsbox = box.clone()
             # `8` is the minimum value experimented to get correct NMS results for obb
             multiplier = 8 if self.obb else 1

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/engine/results.py

@@ -299,8 +299,8 @@ class Results(SimpleClass):
         Return the number of detections in the Results object.
 
         Returns:
-            (int): The number of detections, determined by the length of the first non-empty attribute
-                (boxes, masks, probs, keypoints, or obb).
+            (int): The number of detections, determined by the length of the first non-empty
+                attribute in (masks, probs, keypoints, or obb).
 
         Examples:
             >>> results = Results(orig_img, path, names, boxes=torch.rand(5, 4))
@@ -779,9 +779,9 @@ class Results(SimpleClass):
             decimals (int): Number of decimal places to round the output values to.
 
         Returns:
-            (List[Dict]): A list of dictionaries, each containing summarized information for a single
-                detection or classification result. The structure of each dictionary varies based on the
-                task type (classification or detection) and available information (boxes, masks, keypoints).
+            (List[Dict]): A list of dictionaries, each containing summarized information for a single detection
+                or classification result. The structure of each dictionary varies based on the task type
+                (classification or detection) and available information (boxes, masks, keypoints).
 
         Examples:
             >>> results = model("image.jpg")

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/engine/trainer.py

@@ -21,6 +21,7 @@ import torch
 from torch import distributed as dist
 from torch import nn, optim
 
+from ultralytics import __version__
 from ultralytics.cfg import get_cfg, get_save_dir
 from ultralytics.data.utils import check_cls_dataset, check_det_dataset
 from ultralytics.nn.tasks import attempt_load_one_weight, attempt_load_weights
@@ -30,7 +31,6 @@ from ultralytics.utils import (
     LOGGER,
     RANK,
     TQDM,
-    __version__,
     callbacks,
     clean_url,
     colorstr,
@@ -268,7 +268,7 @@ class BaseTrainer:
             self.amp = torch.tensor(check_amp(self.model), device=self.device)
             callbacks.default_callbacks = callbacks_backup  # restore callbacks
         if RANK > -1 and world_size > 1:  # DDP
-            dist.broadcast(self.amp, src=0)  # broadcast the tensor from rank 0 to all other ranks (returns None)
+            dist.broadcast(self.amp.int(), src=0)  # broadcast from rank 0 to all other ranks; gloo errors with boolean
         self.amp = bool(self.amp)  # as boolean
         self.scaler = (
             torch.amp.GradScaler("cuda", enabled=self.amp) if TORCH_2_4 else torch.cuda.amp.GradScaler(enabled=self.amp)

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/hub/session.py

@@ -9,8 +9,9 @@ from urllib.parse import parse_qs, urlparse
 
 import requests
 
-from ultralytics.hub.utils import HELP_MSG, HUB_WEB_ROOT, PREFIX, TQDM
-from ultralytics.utils import IS_COLAB, LOGGER, SETTINGS, __version__, checks, emojis
+from ultralytics import __version__
+from ultralytics.hub.utils import HELP_MSG, HUB_WEB_ROOT, PREFIX
+from ultralytics.utils import IS_COLAB, LOGGER, SETTINGS, TQDM, checks, emojis
 from ultralytics.utils.errors import HUBModelError
 
 AGENT_NAME = f"python-{__version__}-colab" if IS_COLAB else f"python-{__version__}-local"

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/hub/utils.py

@@ -9,6 +9,7 @@ from pathlib import Path
 
 import requests
 
+from ultralytics import __version__
 from ultralytics.utils import (
     ARGV,
     ENVIRONMENT,
@@ -22,7 +23,6 @@ from ultralytics.utils import (
     TESTS_RUNNING,
     TQDM,
     TryExcept,
-    __version__,
     colorstr,
     get_git_origin_url,
 )

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/sam/modules/utils.py

@@ -16,9 +16,8 @@ def select_closest_cond_frames(frame_idx, cond_frame_outputs, max_cond_frame_num
         max_cond_frame_num (int): Maximum number of conditioning frames to select.
 
     Returns:
-        (Tuple[Dict[int, Any], Dict[int, Any]]): A tuple containing two dictionaries:
-            - selected_outputs: Selected items from cond_frame_outputs.
-            - unselected_outputs: Items not selected from cond_frame_outputs.
+        selected_outputs (Dict[int, Any]): Selected items from cond_frame_outputs.
+        unselected_outputs (Dict[int, Any]): Items not selected from cond_frame_outputs.
 
     Examples:
         >>> frame_idx = 5
@@ -235,9 +234,8 @@ def window_partition(x, window_size):
         window_size (int): Size of each window.
 
     Returns:
-        (Tuple[torch.Tensor, Tuple[int, int]]): A tuple containing:
-            - windows (torch.Tensor): Partitioned windows with shape (B * num_windows, window_size, window_size, C).
-            - (Hp, Wp) (Tuple[int, int]): Padded height and width before partition.
+        windows (torch.Tensor): Partitioned windows with shape (B * num_windows, window_size, window_size, C).
+        padded_h_w (Tuple[int, int]): Padded height and width before partition.
 
     Examples:
         >>> x = torch.randn(1, 16, 16, 3)

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/utils/loss.py

@@ -32,7 +32,16 @@ class DETRLoss(nn.Module):
     """
 
     def __init__(
-        self, nc=80, loss_gain=None, aux_loss=True, use_fl=True, use_vfl=False, use_uni_match=False, uni_match_ind=0
+        self,
+        nc=80,
+        loss_gain=None,
+        aux_loss=True,
+        use_fl=True,
+        use_vfl=False,
+        use_uni_match=False,
+        uni_match_ind=0,
+        gamma=1.5,
+        alpha=0.25,
     ):
         """
         Initialize DETR loss function with customizable components and gains.
@@ -48,6 +57,8 @@ class DETRLoss(nn.Module):
             use_vfl (bool): Whether to use VarifocalLoss.
             use_uni_match (bool): Whether to use fixed layer for auxiliary branch label assignment.
             uni_match_ind (int): Index of fixed layer for uni_match.
+            gamma (float): The focusing parameter that controls how much the loss focuses on hard-to-classify examples.
+            alpha (float): The balancing factor used to address class imbalance.
         """
         super().__init__()
 
@@ -57,8 +68,8 @@ class DETRLoss(nn.Module):
         self.matcher = HungarianMatcher(cost_gain={"class": 2, "bbox": 5, "giou": 2})
         self.loss_gain = loss_gain
         self.aux_loss = aux_loss
-        self.fl = FocalLoss() if use_fl else None
-        self.vfl = VarifocalLoss() if use_vfl else None
+        self.fl = FocalLoss(gamma, alpha) if use_fl else None
+        self.vfl = VarifocalLoss(gamma, alpha) if use_vfl else None
 
         self.use_uni_match = use_uni_match
         self.uni_match_ind = uni_match_ind

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/yolo/detect/predict.py

@@ -59,7 +59,7 @@ class DetectionPredictor(BasePredictor):
             self.args.classes,
             self.args.agnostic_nms,
             max_det=self.args.max_det,
-            nc=len(self.model.names),
+            nc=0 if self.args.task == "detect" else len(self.model.names),
             end2end=getattr(self.model, "end2end", False),
             rotated=self.args.task == "obb",
             return_idxs=save_feats,

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/yolo/detect/val.py

@@ -124,7 +124,7 @@ class DetectionValidator(BaseValidator):
             preds,
             self.args.conf,
             self.args.iou,
-            nc=self.nc,
+            nc=0 if self.args.task == "detect" else self.nc,
             multi_label=True,
             agnostic=self.args.single_cls or self.args.agnostic_nms,
             max_det=self.args.max_det,

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/yolo/model.py

@@ -144,7 +144,7 @@ class YOLOWorld(Model):
 class YOLOE(Model):
     """YOLOE object detection and segmentation model."""
 
-    def __init__(self, model="yoloe-v8s-seg.pt", task=None, verbose=False) -> None:
+    def __init__(self, model="yoloe-11s-seg.pt", task=None, verbose=False) -> None:
         """
         Initialize YOLOE model with a pre-trained model file.
 
@@ -197,7 +197,7 @@ class YOLOE(Model):
             (torch.Tensor): Visual positional embeddings.
 
         Examples:
-            >>> model = YOLOE("yoloe-v8s.pt")
+            >>> model = YOLOE("yoloe-11s-seg.pt")
             >>> img = torch.rand(1, 3, 640, 640)
             >>> visual_features = model.model.backbone(img)
             >>> pe = model.get_visual_pe(img, visual_features)
@@ -220,7 +220,7 @@ class YOLOE(Model):
             AssertionError: If the model is not an instance of YOLOEModel.
 
         Examples:
-            >>> model = YOLOE("yoloe-v8s.pt")
+            >>> model = YOLOE("yoloe-11s-seg.pt")
             >>> model.set_vocab(["person", "car", "dog"], ["person", "car", "dog"])
         """
         assert isinstance(self.model, YOLOEModel)
@@ -304,7 +304,7 @@ class YOLOE(Model):
             (List | generator): List of Results objects or generator of Results objects if stream=True.
 
         Examples:
-            >>> model = YOLOE("yoloe-v8s-seg.pt")
+            >>> model = YOLOE("yoloe-11s-seg.pt")
             >>> results = model.predict("path/to/image.jpg")
             >>> # With visual prompts
             >>> prompts = {"bboxes": [[10, 20, 100, 200]], "cls": ["person"]}

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/yolo/segment/predict.py

@@ -59,7 +59,7 @@ class SegmentationPredictor(DetectionPredictor):
                    Each Results object includes both bounding boxes and segmentation masks.
 
         Examples:
-            >>> predictor = SegmentationPredictor(overrides=dict(model="yolov8n-seg.pt"))
+            >>> predictor = SegmentationPredictor(overrides=dict(model="yolo11n-seg.pt"))
             >>> results = predictor.postprocess(preds, img, orig_img)
         """
         # Extract protos - tuple if PyTorch model or array if exported

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/models/yolo/yoloe/val.py

@@ -9,9 +9,9 @@ from ultralytics.data import YOLOConcatDataset, build_dataloader, build_yolo_dat
 from ultralytics.data.augment import LoadVisualPrompt
 from ultralytics.data.utils import check_det_dataset
 from ultralytics.models.yolo.detect import DetectionValidator
-from ultralytics.models.yolo.model import YOLOEModel
 from ultralytics.models.yolo.segment import SegmentationValidator
 from ultralytics.nn.modules.head import YOLOEDetect
+from ultralytics.nn.tasks import YOLOEModel
 from ultralytics.utils import LOGGER, TQDM
 from ultralytics.utils.torch_utils import select_device, smart_inference_mode
 

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/nn/autobackend.py

@@ -432,10 +432,14 @@ class AutoBackend(nn.Module):
             output_details = interpreter.get_output_details()  # outputs
             # Load metadata
             try:
-                with zipfile.ZipFile(w, "r") as model:
-                    meta_file = model.namelist()[0]
-                    metadata = ast.literal_eval(model.read(meta_file).decode("utf-8"))
-            except zipfile.BadZipFile:
+                with zipfile.ZipFile(w, "r") as zf:
+                    name = zf.namelist()[0]
+                    contents = zf.read(name).decode("utf-8")
+                    if name == "metadata.json":  # Custom Ultralytics metadata dict for Python>=3.12
+                        metadata = json.loads(contents)
+                    else:
+                        metadata = ast.literal_eval(contents)  # Default tflite-support metadata for Python<=3.11
+            except (zipfile.BadZipFile, SyntaxError, ValueError, json.JSONDecodeError):
                 pass
 
         # TF.js

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/nn/modules/conv.py

@@ -447,9 +447,8 @@ class RepConv(nn.Module):
         Calculate equivalent kernel and bias by fusing convolutions.
 
         Returns:
-            (tuple): Tuple containing:
-                - Equivalent kernel (torch.Tensor)
-                - Equivalent bias (torch.Tensor)
+            (torch.Tensor): Equivalent kernel
+            (torch.Tensor): Equivalent bias
         """
         kernel3x3, bias3x3 = self._fuse_bn_tensor(self.conv1)
         kernel1x1, bias1x1 = self._fuse_bn_tensor(self.conv2)
@@ -480,9 +479,8 @@ class RepConv(nn.Module):
             branch (Conv | nn.BatchNorm2d | None): Branch to fuse.
 
         Returns:
-            (tuple): Tuple containing:
-                - Fused kernel (torch.Tensor)
-                - Fused bias (torch.Tensor)
+            (torch.Tensor): Fused kernel
+            (torch.Tensor): Fused bias
         """
         if branch is None:
             return 0, 0

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/nn/modules/head.py

@@ -32,6 +32,7 @@ class Detect(nn.Module):
     anchors = torch.empty(0)  # init
     strides = torch.empty(0)  # init
     legacy = False  # backward compatibility for v3/v5/v8/v9 models
+    xyxy = False  # xyxy or xywh output
 
     def __init__(self, nc=80, ch=()):
         """Initialize the YOLO detection layer with specified number of classes and channels."""
@@ -83,9 +84,10 @@ class Detect(nn.Module):
             x (List[torch.Tensor]): Input feature maps from different levels.
 
         Returns:
-            (dict | tuple): If in training mode, returns a dictionary containing the outputs of both one2many and
-                one2one detections. If not in training mode, returns processed detections or a tuple with
-                processed detections and raw outputs.
+            (dict | tuple):
+
+                - If in training mode, returns a dictionary containing outputs of both one2many and one2one detections.
+                - If not in training mode, returns processed detections or a tuple with processed detections and raw outputs.
         """
         x_detach = [xi.detach() for xi in x]
         one2one = [
@@ -156,7 +158,7 @@ class Detect(nn.Module):
 
     def decode_bboxes(self, bboxes, anchors, xywh=True):
         """Decode bounding boxes."""
-        return dist2bbox(bboxes, anchors, xywh=xywh and (not self.end2end), dim=1)
+        return dist2bbox(bboxes, anchors, xywh=xywh and not (self.end2end or self.xyxy), dim=1)
 
     @staticmethod
     def postprocess(preds: torch.Tensor, max_det: int, nc: int = 80):

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/nn/text_model.py

@@ -23,10 +23,8 @@ try:
         warnings.filterwarnings("ignore", category=FutureWarning)
         import mobileclip
 except ImportError:
-    # MobileCLIP repo has an incorrect version of torchvision as dependency
-    # Manually install other dependencies first and install mobileclip with "--no-deps" flag
-    checks.check_requirements(["open-clip-torch>=2.20.0", "timm>=0.9.5"])
-    checks.check_requirements("git+https://github.com/apple/ml-mobileclip.git", cmds="--no-deps")
+    # Ultralytics fork preferred since Apple MobileCLIP repo has incorrect version of torchvision
+    checks.check_requirements("git+https://github.com/ultralytics/mobileclip.git")
     import mobileclip
 
 

{ultralytics-8.3.115 → ultralytics-8.3.117}/ultralytics/solutions/ai_gym.py

@@ -103,12 +103,13 @@ class AIGym(BaseSolution):
                     self.stage[ind] = "up"
 
                 # Display angle, count, and stage text
-                annotator.plot_angle_and_count_and_stage(
-                    angle_text=self.angle[ind],  # angle text for display
-                    count_text=self.count[ind],  # count text for workouts
-                    stage_text=self.stage[ind],  # stage position text
-                    center_kpt=k[int(self.kpts[1])],  # center keypoint for display
-                )
+                if self.show_labels:
+                    annotator.plot_angle_and_count_and_stage(
+                        angle_text=self.angle[ind],  # angle text for display
+                        count_text=self.count[ind],  # count text for workouts
+                        stage_text=self.stage[ind],  # stage position text
+                        center_kpt=k[int(self.kpts[1])],  # center keypoint for display
+                    )
         plot_im = annotator.result()
         self.display_output(plot_im)  # Display output image, if environment support display