ultralytics 8.1.14__tar.gz → 8.1.16__tar.gz

{ultralytics-8.1.14/ultralytics.egg-info → ultralytics-8.1.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.1.14
+Version: 8.1.16
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu
@@ -19,6 +19,7 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
@@ -30,7 +31,6 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: matplotlib>=3.3.0
-Requires-Dist: numpy>=1.22.2
 Requires-Dist: opencv-python>=4.6.0
 Requires-Dist: pillow>=7.1.2
 Requires-Dist: pyyaml>=5.3.1
@@ -58,10 +58,10 @@ Requires-Dist: mkdocs-redirects; extra == "dev"
 Requires-Dist: mkdocs-ultralytics-plugin>=0.0.43; extra == "dev"
 Provides-Extra: export
 Requires-Dist: onnx>=1.12.0; extra == "export"
-Requires-Dist: coremltools>=7.0; platform_system != "Windows" and extra == "export"
-Requires-Dist: openvino-dev>=2023.0; extra == "export"
-Requires-Dist: tensorflow<=2.13.1; extra == "export"
-Requires-Dist: tensorflowjs>=3.9.0; extra == "export"
+Requires-Dist: coremltools>=7.0; (platform_system != "Windows" and python_version <= "3.11") and extra == "export"
+Requires-Dist: openvino-dev>=2023.0; python_version <= "3.11" and extra == "export"
+Requires-Dist: tensorflow<=2.13.1; python_version <= "3.11" and extra == "export"
+Requires-Dist: tensorflowjs>=3.9.0; python_version <= "3.11" and extra == "export"
 Provides-Extra: explorer
 Requires-Dist: lancedb; extra == "explorer"
 Requires-Dist: duckdb<=0.9.2; extra == "explorer"
@@ -74,7 +74,7 @@ Provides-Extra: extra
 Requires-Dist: hub-sdk>=0.0.2; extra == "extra"
 Requires-Dist: ipython; extra == "extra"
 Requires-Dist: albumentations>=1.0.3; extra == "extra"
-Requires-Dist: pycocotools>=2.0.6; extra == "extra"
+Requires-Dist: pycocotools>=2.0.7; extra == "extra"
 
 <div align="center">
   <p>

{ultralytics-8.1.14 → ultralytics-8.1.16}/pyproject.toml

@@ -52,6 +52,7 @@ classifiers = [
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
     "Topic :: Software Development",
     "Topic :: Scientific/Engineering",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
@@ -64,7 +65,6 @@ classifiers = [
 # Required dependencies ------------------------------------------------------------------------------------------------
 dependencies = [
     "matplotlib>=3.3.0",
-    "numpy>=1.22.2",
     "opencv-python>=4.6.0",
     "pillow>=7.1.2",
     "pyyaml>=5.3.1",
@@ -97,10 +97,10 @@ dev = [
 ]
 export = [
     "onnx>=1.12.0", # ONNX export
-    "coremltools>=7.0; platform_system != 'Windows'", # CoreML only supported on macOS and Linux
-    "openvino-dev>=2023.0", # OpenVINO export
-    "tensorflow<=2.13.1", # TF bug https://github.com/ultralytics/ultralytics/issues/5161
-    "tensorflowjs>=3.9.0", # TF.js export, automatically installs tensorflow
+    "coremltools>=7.0; platform_system != 'Windows' and python_version <= '3.11'", # CoreML supported on macOS and Linux
+    "openvino-dev>=2023.0; python_version <= '3.11'", # OpenVINO export
+    "tensorflow<=2.13.1; python_version <= '3.11'", # TF bug https://github.com/ultralytics/ultralytics/issues/5161
+    "tensorflowjs>=3.9.0; python_version <= '3.11'", # TF.js export, automatically installs tensorflow
 ]
 explorer = [
     "lancedb", # vector search
@@ -120,7 +120,7 @@ extra = [
     "hub-sdk>=0.0.2", # Ultralytics HUB
     "ipython", # interactive notebook
     "albumentations>=1.0.3", # training augmentations
-    "pycocotools>=2.0.6", # COCO mAP
+    "pycocotools>=2.0.7", # COCO mAP
 ]
 
 [project.urls]

{ultralytics-8.1.14 → ultralytics-8.1.16}/tests/test_cli.py

@@ -4,11 +4,10 @@ import subprocess
 
 import pytest
 
-from ultralytics.utils import ASSETS, WEIGHTS_DIR
-from ultralytics.utils.checks import cuda_device_count, cuda_is_available
+from ultralytics.utils import ASSETS, WEIGHTS_DIR, checks
 
-CUDA_IS_AVAILABLE = cuda_is_available()
-CUDA_DEVICE_COUNT = cuda_device_count()
+CUDA_IS_AVAILABLE = checks.cuda_is_available()
+CUDA_DEVICE_COUNT = checks.cuda_device_count()
 TASK_ARGS = [
     ("detect", "yolov8n", "coco8.yaml"),
     ("segment", "yolov8n-seg", "coco8-seg.yaml"),
@@ -70,6 +69,7 @@ def test_rtdetr(task="detect", model="yolov8n-rtdetr.yaml", data="coco8.yaml"):
     run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=640 save save_crop save_txt")
 
 
+@pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM Clip is not supported in Python 3.12")
 def test_fastsam(task="segment", model=WEIGHTS_DIR / "FastSAM-s.pt", data="coco8-seg.yaml"):
     """Test FastSAM segmentation functionality within Ultralytics."""
     source = ASSETS / "bus.jpg"

{ultralytics-8.1.14 → ultralytics-8.1.16}/tests/test_integrations.py

@@ -41,16 +41,16 @@ def test_triton():
 
     # Create variables
     model_name = "yolo"
-    triton_repo_path = TMP / "triton_repo"
-    triton_model_path = triton_repo_path / model_name
+    triton_repo = TMP / "triton_repo"  # Triton repo path
+    triton_model = triton_repo / model_name  # Triton model path
 
     # Export model to ONNX
     f = YOLO(MODEL).export(format="onnx", dynamic=True)
 
     # Prepare Triton repo
-    (triton_model_path / "1").mkdir(parents=True, exist_ok=True)
-    Path(f).rename(triton_model_path / "1" / "model.onnx")
-    (triton_model_path / "config.pbtxt").touch()
+    (triton_model / "1").mkdir(parents=True, exist_ok=True)
+    Path(f).rename(triton_model / "1" / "model.onnx")
+    (triton_model / "config.pbtxt").touch()
 
     # Define image https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver
     tag = "nvcr.io/nvidia/tritonserver:23.09-py3"  # 6.4 GB
@@ -61,7 +61,7 @@ def test_triton():
     # Run the Triton server and capture the container ID
     container_id = (
         subprocess.check_output(
-            f"docker run -d --rm -v {triton_repo_path}:/models -p 8000:8000 {tag} tritonserver --model-repository=/models",
+            f"docker run -d --rm -v {triton_repo}:/models -p 8000:8000 {tag} tritonserver --model-repository=/models",
             shell=True,
         )
         .decode("utf-8")

{ultralytics-8.1.14 → ultralytics-8.1.16}/tests/test_python.py

@@ -218,12 +218,14 @@ def test_export_onnx():
     YOLO(f)(SOURCE)  # exported model inference
 
 
+@pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="OpenVINO not supported in Python 3.12")
 def test_export_openvino():
     """Test exporting the YOLO model to OpenVINO format."""
     f = YOLO(MODEL).export(format="openvino")
     YOLO(f)(SOURCE)  # exported model inference
 
 
+@pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="CoreML not supported in Python 3.12")
 def test_export_coreml():
     """Test exporting the YOLO model to CoreML format."""
     if not WINDOWS:  # RuntimeError: BlobWriter not loaded with coremltools 7.0 on windows

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.1.14"
+__version__ = "8.1.16"
 
 from ultralytics.data.explorer.explorer import Explorer
 from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/cfg/default.yaml

@@ -9,7 +9,7 @@ model: # (str, optional) path to model file, i.e. yolov8n.pt, yolov8n.yaml
 data: # (str, optional) path to data file, i.e. coco128.yaml
 epochs: 100 # (int) number of epochs to train for
 time: # (float, optional) number of hours to train for, overrides epochs if supplied
-patience: 50 # (int) epochs to wait for no observable improvement for early stopping of training
+patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
 batch: 16 # (int) number of images per batch (-1 for AutoBatch)
 imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
 save: True # (bool) save train checkpoints and predict results

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/data/converter.py

@@ -418,8 +418,8 @@ def min_index(arr1, arr2):
     Find a pair of indexes with the shortest distance between two arrays of 2D points.
 
     Args:
-        arr1 (np.array): A NumPy array of shape (N, 2) representing N 2D points.
-        arr2 (np.array): A NumPy array of shape (M, 2) representing M 2D points.
+        arr1 (np.ndarray): A NumPy array of shape (N, 2) representing N 2D points.
+        arr2 (np.ndarray): A NumPy array of shape (M, 2) representing M 2D points.
 
     Returns:
         (tuple): A tuple containing the indexes of the points with the shortest distance in arr1 and arr2 respectively.

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/engine/exporter.py

@@ -81,7 +81,7 @@ from ultralytics.utils import (
     get_default_args,
     yaml_save,
 )
-from ultralytics.utils.checks import check_imgsz, check_is_path_safe, check_requirements, check_version
+from ultralytics.utils.checks import PYTHON_VERSION, check_imgsz, check_is_path_safe, check_requirements, check_version
 from ultralytics.utils.downloads import attempt_download_asset, get_github_assets
 from ultralytics.utils.files import file_size, spaces_in_path
 from ultralytics.utils.ops import Profile
@@ -455,7 +455,7 @@ class Exporter:
                 LOGGER.warning(f"{prefix} WARNING ⚠️ >300 images recommended for INT8 calibration, found {n} images.")
             quantization_dataset = nncf.Dataset(dataset, transform_fn)
             ignored_scope = None
-            if isinstance(self.model.model[-1], (Detect, RTDETRDecoder)):
+            if isinstance(self.model.model[-1], Detect):
                 # Includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
                 head_module_name = ".".join(list(self.model.named_modules())[-1][0].split(".")[:2])
 
@@ -609,10 +609,8 @@ class Exporter:
                 ct_model = cto.palettize_weights(ct_model, config=config)
         if self.args.nms and self.model.task == "detect":
             if mlmodel:
-                import platform
-
                 # coremltools<=6.2 NMS export requires Python<3.11
-                check_version(platform.python_version(), "<3.11", name="Python ", hard=True)
+                check_version(PYTHON_VERSION, "<3.11", name="Python ", hard=True)
                 weights_dir = None
             else:
                 ct_model.save(str(f))  # save otherwise weights_dir does not exist

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/engine/model.py

@@ -5,6 +5,10 @@ import sys
 from pathlib import Path
 from typing import Union
 
+import PIL
+import numpy as np
+import torch
+
 from ultralytics.cfg import TASK2DATA, get_cfg, get_save_dir
 from ultralytics.hub.utils import HUB_WEB_ROOT
 from ultralytics.nn.tasks import attempt_load_one_weight, guess_model_task, nn, yaml_model_load
@@ -78,7 +82,12 @@ class Model(nn.Module):
         NotImplementedError: If a specific model task or mode is not supported.
     """
 
-    def __init__(self, model: Union[str, Path] = "yolov8n.pt", task=None, verbose=False) -> None:
+    def __init__(
+        self,
+        model: Union[str, Path] = "yolov8n.pt",
+        task: str = None,
+        verbose: bool = False,
+    ) -> None:
         """
         Initializes a new instance of the YOLO model class.
 
@@ -135,7 +144,12 @@ class Model(nn.Module):
 
         self.model_name = model
 
-    def __call__(self, source=None, stream=False, **kwargs):
+    def __call__(
+        self,
+        source: Union[str, Path, int, list, tuple, PIL.Image.Image, np.ndarray, torch.Tensor] = None,
+        stream: bool = False,
+        **kwargs,
+    ) -> list:
         """
         An alias for the predict method, enabling the model instance to be callable.
 
@@ -143,8 +157,9 @@ class Model(nn.Module):
         with the required arguments for prediction.
 
         Args:
-            source (str | int | PIL.Image | np.ndarray, optional): The source of the image for making predictions.
-                Accepts various types, including file paths, URLs, PIL images, and numpy arrays. Defaults to None.
+            source (str | Path | int | PIL.Image | np.ndarray, optional): The source of the image for making
+                predictions. Accepts various types, including file paths, URLs, PIL images, and numpy arrays.
+                Defaults to None.
             stream (bool, optional): If True, treats the input source as a continuous stream for predictions.
                 Defaults to False.
             **kwargs (dict): Additional keyword arguments for configuring the prediction process.
@@ -163,7 +178,7 @@ class Model(nn.Module):
         return session if session.client.authenticated else None
 
     @staticmethod
-    def is_triton_model(model):
+    def is_triton_model(model: str) -> bool:
         """Is model a Triton Server URL string, i.e. <scheme>://<netloc>/<endpoint>/<task_name>"""
         from urllib.parse import urlsplit
 
@@ -171,7 +186,7 @@ class Model(nn.Module):
         return url.netloc and url.path and url.scheme in {"http", "grpc"}
 
     @staticmethod
-    def is_hub_model(model):
+    def is_hub_model(model: str) -> bool:
         """Check if the provided model is a HUB model."""
         return any(
             (
@@ -181,7 +196,7 @@ class Model(nn.Module):
             )
         )
 
-    def _new(self, cfg: str, task=None, model=None, verbose=False):
+    def _new(self, cfg: str, task=None, model=None, verbose=False) -> None:
         """
         Initializes a new model and infers the task type from the model definitions.
 
@@ -202,7 +217,7 @@ class Model(nn.Module):
         self.model.args = {**DEFAULT_CFG_DICT, **self.overrides}  # combine default and model args (prefer model args)
         self.model.task = self.task
 
-    def _load(self, weights: str, task=None):
+    def _load(self, weights: str, task=None) -> None:
         """
         Initializes a new model and infers the task type from the model head.
 
@@ -224,7 +239,7 @@ class Model(nn.Module):
         self.overrides["model"] = weights
         self.overrides["task"] = self.task
 
-    def _check_is_pytorch_model(self):
+    def _check_is_pytorch_model(self) -> None:
         """Raises TypeError is model is not a PyTorch model."""
         pt_str = isinstance(self.model, (str, Path)) and Path(self.model).suffix == ".pt"
         pt_module = isinstance(self.model, nn.Module)
@@ -237,7 +252,7 @@ class Model(nn.Module):
                 f"argument directly in your inference command, i.e. 'model.predict(source=..., device=0)'"
             )
 
-    def reset_weights(self):
+    def reset_weights(self) -> "Model":
         """
         Resets the model parameters to randomly initialized values, effectively discarding all training information.
 
@@ -259,7 +274,7 @@ class Model(nn.Module):
             p.requires_grad = True
         return self
 
-    def load(self, weights="yolov8n.pt"):
+    def load(self, weights: Union[str, Path] = "yolov8n.pt") -> "Model":
         """
         Loads parameters from the specified weights file into the model.
 
@@ -281,24 +296,22 @@ class Model(nn.Module):
         self.model.load(weights)
         return self
 
-    def save(self, filename="model.pt"):
+    def save(self, filename: Union[str, Path] = "saved_model.pt") -> None:
         """
         Saves the current model state to a file.
 
         This method exports the model's checkpoint (ckpt) to the specified filename.
 
         Args:
-            filename (str): The name of the file to save the model to. Defaults to 'model.pt'.
+            filename (str | Path): The name of the file to save the model to. Defaults to 'saved_model.pt'.
 
         Raises:
             AssertionError: If the model is not a PyTorch model.
         """
         self._check_is_pytorch_model()
-        import torch
-
         torch.save(self.ckpt, filename)
 
-    def info(self, detailed=False, verbose=True):
+    def info(self, detailed: bool = False, verbose: bool = True):
         """
         Logs or returns model information.
 
@@ -330,7 +343,12 @@ class Model(nn.Module):
         self._check_is_pytorch_model()
         self.model.fuse()
 
-    def embed(self, source=None, stream=False, **kwargs):
+    def embed(
+        self,
+        source: Union[str, Path, int, list, tuple, PIL.Image.Image, np.ndarray, torch.Tensor] = None,
+        stream: bool = False,
+        **kwargs,
+    ) -> list:
         """
         Generates image embeddings based on the provided source.
 
@@ -353,7 +371,13 @@ class Model(nn.Module):
             kwargs["embed"] = [len(self.model.model) - 2]  # embed second-to-last layer if no indices passed
         return self.predict(source, stream, **kwargs)
 
-    def predict(self, source=None, stream=False, predictor=None, **kwargs):
+    def predict(
+        self,
+        source: Union[str, Path, int, list, tuple, PIL.Image.Image, np.ndarray, torch.Tensor] = None,
+        stream: bool = False,
+        predictor=None,
+        **kwargs,
+    ) -> list:
         """
         Performs predictions on the given image source using the YOLO model.
 
@@ -405,7 +429,13 @@ class Model(nn.Module):
             self.predictor.set_prompts(prompts)
         return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
 
-    def track(self, source=None, stream=False, persist=False, **kwargs):
+    def track(
+        self,
+        source: Union[str, Path, int, list, tuple, PIL.Image.Image, np.ndarray, torch.Tensor] = None,
+        stream: bool = False,
+        persist: bool = False,
+        **kwargs,
+    ) -> list:
         """
         Conducts object tracking on the specified input source using the registered trackers.
 
@@ -438,7 +468,11 @@ class Model(nn.Module):
         kwargs["mode"] = "track"
         return self.predict(source=source, stream=stream, **kwargs)
 
-    def val(self, validator=None, **kwargs):
+    def val(
+        self,
+        validator=None,
+        **kwargs,
+    ):
         """
         Validates the model using a specified dataset and validation configuration.
 
@@ -471,7 +505,10 @@ class Model(nn.Module):
         self.metrics = validator.metrics
         return validator.metrics
 
-    def benchmark(self, **kwargs):
+    def benchmark(
+        self,
+        **kwargs,
+    ):
         """
         Benchmarks the model across various export formats to evaluate performance.
 
@@ -509,7 +546,10 @@ class Model(nn.Module):
             verbose=kwargs.get("verbose"),
         )
 
-    def export(self, **kwargs):
+    def export(
+        self,
+        **kwargs,
+    ):
         """
         Exports the model to a different format suitable for deployment.
 
@@ -537,7 +577,11 @@ class Model(nn.Module):
         args = {**self.overrides, **custom, **kwargs, "mode": "export"}  # highest priority args on the right
         return Exporter(overrides=args, _callbacks=self.callbacks)(model=self.model)
 
-    def train(self, trainer=None, **kwargs):
+    def train(
+        self,
+        trainer=None,
+        **kwargs,
+    ):
         """
         Trains the model using the specified dataset and training configuration.
 
@@ -607,7 +651,13 @@ class Model(nn.Module):
             self.metrics = getattr(self.trainer.validator, "metrics", None)  # TODO: no metrics returned by DDP
         return self.metrics
 
-    def tune(self, use_ray=False, iterations=10, *args, **kwargs):
+    def tune(
+        self,
+        use_ray=False,
+        iterations=10,
+        *args,
+        **kwargs,
+    ):
         """
         Conducts hyperparameter tuning for the model, with an option to use Ray Tune.
 
@@ -640,7 +690,7 @@ class Model(nn.Module):
             args = {**self.overrides, **custom, **kwargs, "mode": "train"}  # highest priority args on the right
             return Tuner(args=args, _callbacks=self.callbacks)(model=self, iterations=iterations)
 
-    def _apply(self, fn):
+    def _apply(self, fn) -> "Model":
         """Apply to(), cpu(), cuda(), half(), float() to model tensors that are not parameters or registered buffers."""
         self._check_is_pytorch_model()
         self = super()._apply(fn)  # noqa
@@ -649,7 +699,7 @@ class Model(nn.Module):
         return self
 
     @property
-    def names(self):
+    def names(self) -> list:
         """
         Retrieves the class names associated with the loaded model.
 
@@ -664,7 +714,7 @@ class Model(nn.Module):
         return check_class_names(self.model.names) if hasattr(self.model, "names") else None
 
     @property
-    def device(self):
+    def device(self) -> torch.device:
         """
         Retrieves the device on which the model's parameters are allocated.
 
@@ -688,7 +738,7 @@ class Model(nn.Module):
         """
         return self.model.transforms if hasattr(self.model, "transforms") else None
 
-    def add_callback(self, event: str, func):
+    def add_callback(self, event: str, func) -> None:
         """
         Adds a callback function for a specified event.
 
@@ -704,7 +754,7 @@ class Model(nn.Module):
         """
         self.callbacks[event].append(func)
 
-    def clear_callback(self, event: str):
+    def clear_callback(self, event: str) -> None:
         """
         Clears all callback functions registered for a specified event.
 
@@ -718,7 +768,7 @@ class Model(nn.Module):
         """
         self.callbacks[event] = []
 
-    def reset_callbacks(self):
+    def reset_callbacks(self) -> None:
         """
         Resets all callbacks to their default functions.
 
@@ -729,7 +779,7 @@ class Model(nn.Module):
             self.callbacks[event] = [callbacks.default_callbacks[event][0]]
 
     @staticmethod
-    def _reset_ckpt_args(args):
+    def _reset_ckpt_args(args: dict) -> dict:
         """Reset arguments when loading a PyTorch model."""
         include = {"imgsz", "data", "task", "single_cls"}  # only remember these arguments when loading a PyTorch model
         return {k: v for k, v in args.items() if k in include}
@@ -739,7 +789,7 @@ class Model(nn.Module):
     #    name = self.__class__.__name__
     #    raise AttributeError(f"'{name}' object has no attribute '{attr}'. See valid attributes below.\n{self.__doc__}")
 
-    def _smart_load(self, key):
+    def _smart_load(self, key: str):
         """Load model/trainer/validator/predictor."""
         try:
             return self.task_map[self.task][key]
@@ -751,7 +801,7 @@ class Model(nn.Module):
             ) from e
 
     @property
-    def task_map(self):
+    def task_map(self) -> dict:
         """
         Map head to model, trainer, validator, and predictor classes.
 

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/engine/results.py

@@ -710,8 +710,8 @@ class OBB(BaseTensor):
     def xyxyxyxyn(self):
         """Return the boxes in xyxyxyxy format, (N, 4, 2)."""
         xyxyxyxyn = self.xyxyxyxy.clone() if isinstance(self.xyxyxyxy, torch.Tensor) else np.copy(self.xyxyxyxy)
-        xyxyxyxyn[..., 0] /= self.orig_shape[0]
-        xyxyxyxyn[..., 1] /= self.orig_shape[1]
+        xyxyxyxyn[..., 0] /= self.orig_shape[1]
+        xyxyxyxyn[..., 1] /= self.orig_shape[0]
         return xyxyxyxyn
 
     @property

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/engine/trainer.py

@@ -285,7 +285,7 @@ class BaseTrainer:
         batch_size = self.batch_size // max(world_size, 1)
         self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode="train")
         if RANK in (-1, 0):
-            # NOTE: When training DOTA dataset, double batch size could get OOM cause some images got more than 2000 objects.
+            # Note: When training DOTA dataset, double batch size could get OOM on images with >2000 objects.
             self.test_loader = self.get_dataloader(
                 self.testset, batch_size=batch_size if self.args.task == "obb" else batch_size * 2, rank=-1, mode="val"
             )

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/models/yolo/detect/val.py

@@ -132,8 +132,7 @@ class DetectionValidator(BaseValidator):
                 if nl:
                     for k in self.stats.keys():
                         self.stats[k].append(stat[k])
-                    # TODO: obb has not supported confusion_matrix yet.
-                    if self.args.plots and self.args.task != "obb":
+                    if self.args.plots:
                         self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
                 continue
 
@@ -147,8 +146,7 @@ class DetectionValidator(BaseValidator):
             # Evaluate
             if nl:
                 stat["tp"] = self._process_batch(predn, bbox, cls)
-                # TODO: obb has not supported confusion_matrix yet.
-                if self.args.plots and self.args.task != "obb":
+                if self.args.plots:
                     self.confusion_matrix.process_batch(predn, bbox, cls)
             for k in self.stats.keys():
                 self.stats[k].append(stat[k])

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/models/yolo/obb/val.py

@@ -55,10 +55,11 @@ class OBBValidator(DetectionValidator):
         Return correct prediction matrix.
 
         Args:
-            detections (torch.Tensor): Tensor of shape [N, 6] representing detections.
-                Each detection is of the format: x1, y1, x2, y2, conf, class.
-            labels (torch.Tensor): Tensor of shape [M, 5] representing labels.
-                Each label is of the format: class, x1, y1, x2, y2.
+            detections (torch.Tensor): Tensor of shape [N, 7] representing detections.
+                Each detection is of the format: x1, y1, x2, y2, conf, class, angle.
+            gt_bboxes (torch.Tensor): Tensor of shape [M, 5] representing rotated boxes.
+                Each box is of the format: x1, y1, x2, y2, angle.
+            labels (torch.Tensor): Tensor of shape [M] representing labels.
 
         Returns:
             (torch.Tensor): Correct prediction matrix of shape [N, 10] for 10 IoU levels.

{ultralytics-8.1.14 → ultralytics-8.1.16}/ultralytics/nn/tasks.py

@@ -761,6 +761,8 @@ def attempt_load_weights(weights, device=None, inplace=True, fuse=False):
     for m in ensemble.modules():
         if hasattr(m, "inplace"):
             m.inplace = inplace
+        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
 
     # Return model
     if len(ensemble) == 1:
@@ -794,6 +796,8 @@ def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False):
     for m in model.modules():
         if hasattr(m, "inplace"):
             m.inplace = inplace
+        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
 
     # Return model and ckpt
     return model, ckpt