ultralytics 8.3.117__tar.gz → 8.3.119__tar.gz

{ultralytics-8.3.117/ultralytics.egg-info → ultralytics-8.3.119}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.117
+Version: 8.3.119
 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>
@@ -32,7 +32,7 @@ Classifier: Operating System :: Microsoft :: Windows
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<=2.1.1,>=1.23.0
+Requires-Dist: numpy>=1.23.0
 Requires-Dist: matplotlib>=3.3.0
 Requires-Dist: opencv-python>=4.6.0
 Requires-Dist: pillow>=7.1.2
@@ -61,20 +61,19 @@ 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 <= "3.13") and extra == "export"
-Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.12") and extra == "export"
+Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"
 Requires-Dist: tensorflow>=2.0.0; 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: h5py!=3.11.0; platform_machine == "aarch64" and extra == "export"
 Provides-Extra: solutions
 Requires-Dist: shapely<2.1.0,>=2.0.0; extra == "solutions"
 Requires-Dist: streamlit<1.44.0,>=1.29.0; extra == "solutions"
 Provides-Extra: logging
-Requires-Dist: comet; extra == "logging"
-Requires-Dist: tensorboard>=2.13.0; extra == "logging"
-Requires-Dist: dvclive>=2.12.0; extra == "logging"
+Requires-Dist: wandb; extra == "logging"
+Requires-Dist: tensorboard; extra == "logging"
+Requires-Dist: mlflow; extra == "logging"
 Provides-Extra: extra
 Requires-Dist: hub-sdk>=0.0.12; extra == "extra"
 Requires-Dist: ipython; extra == "extra"

{ultralytics-8.3.117 → ultralytics-8.3.119}/pyproject.toml

@@ -61,7 +61,7 @@ classifiers = [
 
 # Required dependencies ------------------------------------------------------------------------------------------------
 dependencies = [
-    "numpy>=1.23.0,<=2.1.1", # OpenVINO and TFLite errors on '--slow' CI Tests https://github.com/ultralytics/ultralytics/pull/18943
+    "numpy>=1.23.0",
     "matplotlib>=3.3.0",
     "opencv-python>=4.6.0",
     "pillow>=7.1.2",
@@ -95,12 +95,11 @@ dev = [
 export = [
     "onnx>=1.12.0", # ONNX export
     "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
+    "scikit-learn>=1.3.2; platform_system != 'Windows' and python_version <= '3.13'", # CoreML k-means quantization
     "openvino>=2024.0.0",  # OpenVINO export
     "tensorflow>=2.0.0", # TF bug https://github.com/ultralytics/ultralytics/issues/5161
     "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
     "h5py!=3.11.0; platform_machine == 'aarch64'", # fix h5py build issues due to missing aarch64 wheels in 3.11 release
 ]
 solutions = [
@@ -108,9 +107,9 @@ solutions = [
     "streamlit>=1.29.0,<1.44.0",    # for live inference on web browser, i.e `yolo streamlit-predict`
 ]
 logging = [
-    "comet", # https://docs.ultralytics.com/integrations/comet/
-    "tensorboard>=2.13.0",
-    "dvclive>=2.12.0",
+    "wandb", # https://docs.ultralytics.com/integrations/weights-biases/
+    "tensorboard",  # https://docs.ultralytics.com/integrations/tensorboard/
+    "mlflow",  # https://docs.ultralytics.com/integrations/mlflow/
 ]
 extra = [
     "hub-sdk>=0.0.12", # Ultralytics HUB
@@ -133,7 +132,8 @@ ultralytics = "ultralytics.cfg:entrypoint"
 # Tools settings -------------------------------------------------------------------------------------------------------
 [tool.setuptools]  # configuration specific to the `setuptools` build backend.
 packages = { find = { where = ["."], include = ["ultralytics", "ultralytics.*"] } }
-package-data = { "ultralytics" = ["**/*.yaml", "**/*.sh"], "ultralytics.assets" = ["*.jpg"] }
+# Tests included below for checking Conda builds in https://github.com/conda-forge/ultralytics-feedstock
+package-data = { "ultralytics" = ["**/*.yaml", "**/*.sh", "../tests/*.py"], "ultralytics.assets" = ["*.jpg"] }
 
 [tool.setuptools.dynamic]
 version = { attr = "ultralytics.__version__" }

ultralytics-8.3.119/tests/__init__.py

@@ -0,0 +1,22 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from ultralytics.utils import ASSETS, ROOT, WEIGHTS_DIR, checks
+
+# Constants used in tests
+MODEL = WEIGHTS_DIR / "path with spaces" / "yolo11n.pt"  # test spaces in path
+CFG = "yolo11n.yaml"
+SOURCE = ASSETS / "bus.jpg"
+SOURCES_LIST = [ASSETS / "bus.jpg", ASSETS, ASSETS / "*", ASSETS / "**/*.jpg"]
+TMP = (ROOT / "../tests/tmp").resolve()  # temp directory for test files
+CUDA_IS_AVAILABLE = checks.cuda_is_available()
+CUDA_DEVICE_COUNT = checks.cuda_device_count()
+
+__all__ = (
+    "MODEL",
+    "CFG",
+    "SOURCE",
+    "SOURCES_LIST",
+    "TMP",
+    "CUDA_IS_AVAILABLE",
+    "CUDA_DEVICE_COUNT",
+)

ultralytics-8.3.119/tests/conftest.py

@@ -0,0 +1,83 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import shutil
+from pathlib import Path
+
+from tests import TMP
+
+
+def pytest_addoption(parser):
+    """
+    Add custom command-line options to pytest.
+
+    Args:
+        parser (pytest.config.Parser): The pytest parser object for adding custom command-line options.
+
+    Returns:
+        (None)
+    """
+    parser.addoption("--slow", action="store_true", default=False, help="Run slow tests")
+
+
+def pytest_collection_modifyitems(config, items):
+    """
+    Modify the list of test items to exclude tests marked as slow if the --slow option is not specified.
+
+    Args:
+        config (pytest.config.Config): The pytest configuration object that provides access to command-line options.
+        items (list): The list of collected pytest item objects to be modified based on the presence of --slow option.
+
+    Returns:
+        (None): The function modifies the 'items' list in place.
+    """
+    if not config.getoption("--slow"):
+        # Remove the item entirely from the list of test items if it's marked as 'slow'
+        items[:] = [item for item in items if "slow" not in item.keywords]
+
+
+def pytest_sessionstart(session):
+    """
+    Initialize session configurations for pytest.
+
+    This function is automatically called by pytest after the 'Session' object has been created but before performing
+    test collection. It sets the initial seeds and prepares the temporary directory for the test session.
+
+    Args:
+        session (pytest.Session): The pytest session object.
+
+    Returns:
+        (None)
+    """
+    from ultralytics.utils.torch_utils import init_seeds
+
+    init_seeds()
+    shutil.rmtree(TMP, ignore_errors=True)  # delete any existing tests/tmp directory
+    TMP.mkdir(parents=True, exist_ok=True)  # create a new empty directory
+
+
+def pytest_terminal_summary(terminalreporter, exitstatus, config):
+    """
+    Cleanup operations after pytest session.
+
+    This function is automatically called by pytest at the end of the entire test session. It removes certain files
+    and directories used during testing.
+
+    Args:
+        terminalreporter (pytest.terminal.TerminalReporter): The terminal reporter object used for terminal output.
+        exitstatus (int): The exit status of the test run.
+        config (pytest.config.Config): The pytest config object.
+
+    Returns:
+        (None)
+    """
+    from ultralytics.utils import WEIGHTS_DIR
+
+    # Remove files
+    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)]
+    for directory in [WEIGHTS_DIR / "path with spaces", TMP.parents[1] / ".pytest_cache", TMP] + models:
+        shutil.rmtree(directory, ignore_errors=True)

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.117"
+__version__ = "8.3.119"
 
 import os
 

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/cfg/__init__.py

@@ -181,6 +181,7 @@ CFG_FRACTION_KEYS = frozenset(
         "bgr",
         "mosaic",
         "mixup",
+        "cutmix",
         "copy_paste",
         "conf",
         "iou",

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/cfg/default.yaml

@@ -114,6 +114,7 @@ fliplr: 0.5 # (float) image flip left-right (probability)
 bgr: 0.0 # (float) image channel BGR (probability)
 mosaic: 1.0 # (float) image mosaic (probability)
 mixup: 0.0 # (float) image mixup (probability)
+cutmix: 0.0 # (float) image cutmix (probability)
 copy_paste: 0.0 # (float) segment copy-paste (probability)
 copy_paste_mode: "flip" # (str) the method to do copy_paste augmentation (flip, mixup)
 auto_augment: randaugment # (str) auto augmentation policy for classification (randaugment, autoaugment, augmix)

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/data/augment.py

@@ -317,7 +317,7 @@ class Compose:
 
 class BaseMixTransform:
     """
-    Base class for mix transformations like MixUp and Mosaic.
+    Base class for mix transformations like Cutmix, MixUp and Mosaic.
 
     This class provides a foundation for implementing mix transformations on datasets. It handles the
     probability-based application of transforms and manages the mixing of multiple images and labels.
@@ -348,7 +348,7 @@ class BaseMixTransform:
 
     def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
         """
-        Initializes the BaseMixTransform object for mix transformations like MixUp and Mosaic.
+        Initializes the BaseMixTransform object for mix transformations like CutMix, MixUp and Mosaic.
 
         This class serves as a base for implementing mix transformations in image processing pipelines.
 
@@ -368,7 +368,7 @@ class BaseMixTransform:
 
     def __call__(self, labels):
         """
-        Applies pre-processing transforms and mixup/mosaic transforms to labels data.
+        Applies pre-processing transforms and cutmix/mixup/mosaic transforms to labels data.
 
         This method determines whether to apply the mix transform based on a probability factor. If applied, it
         selects additional images, applies pre-transforms if specified, and then performs the mix transform.
@@ -391,7 +391,7 @@ class BaseMixTransform:
         if isinstance(indexes, int):
             indexes = [indexes]
 
-        # Get images information will be used for Mosaic or MixUp
+        # Get images information will be used for Mosaic, CutMix or MixUp
         mix_labels = [self.dataset.get_image_and_label(i) for i in indexes]
 
         if self.pre_transform is not None:
@@ -401,16 +401,16 @@ class BaseMixTransform:
 
         # Update cls and texts
         labels = self._update_label_text(labels)
-        # Mosaic or MixUp
+        # Mosaic, CutMix or MixUp
         labels = self._mix_transform(labels)
         labels.pop("mix_labels", None)
         return labels
 
     def _mix_transform(self, labels):
         """
-        Applies MixUp or Mosaic augmentation to the label dictionary.
+        Applies CutMix, MixUp or Mosaic augmentation to the label dictionary.
 
-        This method should be implemented by subclasses to perform specific mix transformations like MixUp or
+        This method should be implemented by subclasses to perform specific mix transformations like CutMix, MixUp or
         Mosaic. It modifies the input label dictionary in-place with the augmented data.
 
         Args:
@@ -949,6 +949,117 @@ class MixUp(BaseMixTransform):
         return labels
 
 
+class CutMix(BaseMixTransform):
+    """
+    Applies CutMix augmentation to image datasets as described in the paper https://arxiv.org/abs/1905.04899.
+
+    CutMix combines two images by replacing a random rectangular region of one image with the corresponding region from another image,
+    and adjusts the labels proportionally to the area of the mixed region.
+
+    Attributes:
+        dataset (Any): The dataset to which CutMix augmentation will be applied.
+        pre_transform (Callable | None): Optional transform to apply before CutMix.
+        p (float): Probability of applying CutMix augmentation.
+        beta (float): Beta distribution parameter for sampling the mixing ratio (default=1.0).
+
+    Methods:
+        get_indexes: Returns a random index from the dataset.
+        _mix_transform: Applies CutMix augmentation to the input labels.
+        _rand_bbox: Generates random bounding box coordinates for the cut region.
+
+    Examples:
+        >>> from ultralytics.data.augment import CutMix
+        >>> dataset = YourDataset(...)  # Your image dataset
+        >>> cutmix = CutMix(dataset, p=0.5)
+        >>> augmented_labels = cutmix(original_labels)
+    """
+
+    def __init__(self, dataset, pre_transform=None, p=0.0, beta=1.0) -> None:
+        """
+        Initializes the CutMix augmentation object.
+
+        Args:
+            dataset (Any): The dataset to which CutMix augmentation will be applied.
+            pre_transform (Callable | None): Optional transform to apply before CutMix.
+            p (float): Probability of applying CutMix augmentation.
+            beta (float): Beta distribution parameter for sampling the mixing ratio (default=1.0).
+        """
+        super().__init__(dataset=dataset, pre_transform=pre_transform, p=p)
+        self.beta = beta
+
+    def get_indexes(self):
+        """
+        Get a random index from the dataset.
+
+        Returns:
+            (int): A random integer index within the range of the dataset length.
+        """
+        return random.randint(0, len(self.dataset) - 1)
+
+    def _rand_bbox(self, width, height, lam):
+        """
+        Generates random bounding box coordinates for the cut region.
+
+        Args:
+            width (int): Width of the image.
+            height (int): Height of the image.
+            lam (float): Mixing ratio from the Beta distribution.
+
+        Returns:
+            (tuple): (x1, y1, x2, y2) coordinates of the bounding box.
+        """
+        cut_ratio = np.sqrt(1.0 - lam)
+        cut_w = int(width * cut_ratio)
+        cut_h = int(height * cut_ratio)
+
+        # Random center
+        cx = np.random.randint(width)
+        cy = np.random.randint(height)
+
+        # Bounding box coordinates
+        x1 = np.clip(cx - cut_w // 2, 0, width)
+        y1 = np.clip(cy - cut_h // 2, 0, height)
+        x2 = np.clip(cx + cut_w // 2, 0, width)
+        y2 = np.clip(cy + cut_h // 2, 0, height)
+
+        return x1, y1, x2, y2
+
+    def _mix_transform(self, labels):
+        """
+        Applies CutMix augmentation to the input labels.
+
+        Args:
+            labels (dict): A dictionary containing the original image and label information.
+
+        Returns:
+            (dict): A dictionary containing the mixed image and adjusted labels.
+
+        Examples:
+            >>> cutter = CutMix(dataset)
+            >>> mixed_labels = cutter._mix_transform(labels)
+        """
+        # Sample mixing ratio from Beta distribution
+        lam = np.random.beta(self.beta, self.beta)
+
+        # Get a random second image
+        labels2 = labels["mix_labels"][0]
+        img2 = labels2["img"]
+        h, w = labels["img"].shape[:2]
+
+        # Generate random bounding box
+        x1, y1, x2, y2 = self._rand_bbox(w, h, lam)
+
+        # Apply CutMix
+        labels["img"][y1:y2, x1:x2] = img2[y1:y2, x1:x2]
+
+        # Adjust lambda to match the actual area ratio
+        lam = 1 - ((x2 - x1) * (y2 - y1) / (w * h))
+
+        labels["cls"] = np.concatenate([labels["cls"], labels2["cls"]], axis=0)
+        labels["instances"] = Instances.concatenate([labels["instances"], labels2["instances"]], axis=0)
+        return labels
+
+
 class RandomPerspective:
     """
     Implements random perspective and affine transformations on images and corresponding annotations.
@@ -1586,6 +1697,9 @@ class LetterBox:
 
         if shape[::-1] != new_unpad:  # resize
             img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
+            if img.ndim == 2:
+                img = img[..., None]
+
         top, bottom = int(round(dh - 0.1)) if self.center else 0, int(round(dh + 0.1))
         left, right = int(round(dw - 0.1)) if self.center else 0, int(round(dw + 0.1))
         h, w, c = img.shape
@@ -2442,6 +2556,7 @@ def v8_transforms(dataset, imgsz, hyp, stretch=False):
         [
             pre_transform,
             MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup),
+            CutMix(dataset, pre_transform=pre_transform, p=hyp.cutmix),
             Albumentations(p=1.0),
             RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
             RandomFlip(direction="vertical", p=hyp.flipud),

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/data/base.py

@@ -33,6 +33,7 @@ class BaseDataset(Dataset):
         single_cls (bool): Whether to treat all objects as a single class.
         prefix (str): Prefix to print in log messages.
         fraction (float): Fraction of dataset to utilize.
+        cv2_flag (int): OpenCV flag for reading images.
         im_files (List[str]): List of image file paths.
         labels (List[Dict]): List of label data dictionaries.
         ni (int): Number of images in the dataset.
@@ -79,6 +80,7 @@ class BaseDataset(Dataset):
         single_cls=False,
         classes=None,
         fraction=1.0,
+        channels=3,
     ):
         """
         Initialize BaseDataset with given configuration and options.
@@ -97,6 +99,7 @@ class BaseDataset(Dataset):
             single_cls (bool, optional): If True, single class training is used.
             classes (list, optional): List of included classes.
             fraction (float, optional): Fraction of dataset to utilize.
+            channels (int, optional): Number of channels in the images (1 for grayscale, 3 for RGB).
         """
         super().__init__()
         self.img_path = img_path
@@ -105,6 +108,8 @@ class BaseDataset(Dataset):
         self.single_cls = single_cls
         self.prefix = prefix
         self.fraction = fraction
+        self.channels = channels
+        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR
         self.im_files = self.get_img_files(self.img_path)
         self.labels = self.get_labels()
         self.update_labels(include_class=classes)  # single_cls and include_class
@@ -224,9 +229,9 @@ class BaseDataset(Dataset):
                 except Exception as e:
                     LOGGER.warning(f"{self.prefix}Removing corrupt *.npy image file {fn} due to: {e}")
                     Path(fn).unlink(missing_ok=True)
-                    im = imread(f)  # BGR
+                    im = imread(f, flags=self.cv2_flag)  # BGR
             else:  # read image
-                im = imread(f)  # BGR
+                im = imread(f, flags=self.cv2_flag)  # BGR
             if im is None:
                 raise FileNotFoundError(f"Image Not Found {f}")
 
@@ -238,6 +243,8 @@ class BaseDataset(Dataset):
                     im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
             elif not (h0 == w0 == self.imgsz):  # resize by stretching image to square imgsz
                 im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR)
+            if im.ndim == 2:
+                im = im[..., None]
 
             # Add to buffer if training with augmentations
             if self.augment:

{ultralytics-8.3.117 → ultralytics-8.3.119}/ultralytics/data/dataset.py

@@ -84,7 +84,7 @@ class YOLODataset(BaseDataset):
         self.use_obb = task == "obb"
         self.data = data
         assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints."
-        super().__init__(*args, **kwargs)
+        super().__init__(*args, channels=self.data["channels"], **kwargs)
 
     def cache_labels(self, path=Path("./labels.cache")):
         """
@@ -215,6 +215,7 @@ class YOLODataset(BaseDataset):
         if self.augment:
             hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
             hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
+            hyp.cutmix = hyp.cutmix if self.augment and not self.rect else 0.0
             transforms = v8_transforms(self, self.imgsz, hyp)
         else:
             transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
@@ -235,14 +236,15 @@ class YOLODataset(BaseDataset):
 
     def close_mosaic(self, hyp):
         """
-        Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations.
+        Disable mosaic, copy_paste, mixup and cutmix augmentations by setting their probabilities to 0.0.
 
         Args:
             hyp (dict): Hyperparameters for transforms.
         """
-        hyp.mosaic = 0.0  # set mosaic ratio=0.0
-        hyp.copy_paste = 0.0  # keep the same behavior as previous v8 close-mosaic
-        hyp.mixup = 0.0  # keep the same behavior as previous v8 close-mosaic
+        hyp.mosaic = 0.0
+        hyp.copy_paste = 0.0
+        hyp.mixup = 0.0
+        hyp.cutmix = 0.0
         self.transforms = self.build_transforms(hyp)
 
     def update_labels_info(self, label):