dgenerate-ultralytics-headless 8.3.214__py3-none-any.whl → 8.3.248__py3-none-any.whl

ultralytics/data/dataset.py

@@ -47,8 +47,7 @@ DATASET_CACHE_VERSION = "1.0.3"
 
 
 class YOLODataset(BaseDataset):
-    """
-    Dataset class for loading object detection and/or segmentation labels in YOLO format.
+    """Dataset class for loading object detection and/or segmentation labels in YOLO format.
 
     This class supports loading data for object detection, segmentation, pose estimation, and oriented bounding box
     (OBB) tasks using the YOLO format.
@@ -73,8 +72,7 @@ class YOLODataset(BaseDataset):
     """
 
     def __init__(self, *args, data: dict | None = None, task: str = "detect", **kwargs):
-        """
-        Initialize the YOLODataset.
+        """Initialize the YOLODataset.
 
         Args:
             data (dict, optional): Dataset configuration dictionary.
@@ -90,8 +88,7 @@ class YOLODataset(BaseDataset):
         super().__init__(*args, channels=self.data.get("channels", 3), **kwargs)
 
     def cache_labels(self, path: Path = Path("./labels.cache")) -> dict:
-        """
-        Cache dataset labels, check images and read shapes.
+        """Cache dataset labels, check images and read shapes.
 
         Args:
             path (Path): Path where to save the cache file.
@@ -158,8 +155,7 @@ class YOLODataset(BaseDataset):
         return x
 
     def get_labels(self) -> list[dict]:
-        """
-        Return dictionary of labels for YOLO training.
+        """Return dictionary of labels for YOLO training.
 
         This method loads labels from disk or cache, verifies their integrity, and prepares them for training.
 
@@ -208,8 +204,7 @@ class YOLODataset(BaseDataset):
         return labels
 
     def build_transforms(self, hyp: dict | None = None) -> Compose:
-        """
-        Build and append transforms to the list.
+        """Build and append transforms to the list.
 
         Args:
             hyp (dict, optional): Hyperparameters for transforms.
@@ -240,8 +235,7 @@ class YOLODataset(BaseDataset):
         return transforms
 
     def close_mosaic(self, hyp: dict) -> None:
-        """
-        Disable mosaic, copy_paste, mixup and cutmix augmentations by setting their probabilities to 0.0.
+        """Disable mosaic, copy_paste, mixup and cutmix augmentations by setting their probabilities to 0.0.
 
         Args:
             hyp (dict): Hyperparameters for transforms.
@@ -253,8 +247,7 @@ class YOLODataset(BaseDataset):
         self.transforms = self.build_transforms(hyp)
 
     def update_labels_info(self, label: dict) -> dict:
-        """
-        Update label format for different tasks.
+        """Update label format for different tasks.
 
         Args:
             label (dict): Label dictionary containing bboxes, segments, keypoints, etc.
@@ -262,7 +255,7 @@ class YOLODataset(BaseDataset):
         Returns:
             (dict): Updated label dictionary with instances.
 
-        Note:
+        Notes:
             cls is not with bboxes now, classification and semantic segmentation need an independent cls label
             Can also support classification and semantic segmentation by adding or removing dict keys there.
         """
@@ -287,8 +280,7 @@ class YOLODataset(BaseDataset):
 
     @staticmethod
     def collate_fn(batch: list[dict]) -> dict:
-        """
-        Collate data samples into batches.
+        """Collate data samples into batches.
 
         Args:
             batch (list[dict]): List of dictionaries containing sample data.
@@ -317,11 +309,10 @@ class YOLODataset(BaseDataset):
 
 
 class YOLOMultiModalDataset(YOLODataset):
-    """
-    Dataset class for loading object detection and/or segmentation labels in YOLO format with multi-modal support.
+    """Dataset class for loading object detection and/or segmentation labels in YOLO format with multi-modal support.
 
-    This class extends YOLODataset to add text information for multi-modal model training, enabling models to
-    process both image and text data.
+    This class extends YOLODataset to add text information for multi-modal model training, enabling models to process
+    both image and text data.
 
     Methods:
         update_labels_info: Add text information for multi-modal model training.
@@ -334,8 +325,7 @@ class YOLOMultiModalDataset(YOLODataset):
     """
 
     def __init__(self, *args, data: dict | None = None, task: str = "detect", **kwargs):
-        """
-        Initialize a YOLOMultiModalDataset.
+        """Initialize a YOLOMultiModalDataset.
 
         Args:
             data (dict, optional): Dataset configuration dictionary.
@@ -346,8 +336,7 @@ class YOLOMultiModalDataset(YOLODataset):
         super().__init__(*args, data=data, task=task, **kwargs)
 
     def update_labels_info(self, label: dict) -> dict:
-        """
-        Add text information for multi-modal model training.
+        """Add text information for multi-modal model training.
 
         Args:
             label (dict): Label dictionary containing bboxes, segments, keypoints, etc.
@@ -363,8 +352,7 @@ class YOLOMultiModalDataset(YOLODataset):
         return labels
 
     def build_transforms(self, hyp: dict | None = None) -> Compose:
-        """
-        Enhance data transformations with optional text augmentation for multi-modal training.
+        """Enhance data transformations with optional text augmentation for multi-modal training.
 
         Args:
             hyp (dict, optional): Hyperparameters for transforms.
@@ -388,8 +376,7 @@ class YOLOMultiModalDataset(YOLODataset):
 
     @property
     def category_names(self):
-        """
-        Return category names for the dataset.
+        """Return category names for the dataset.
 
         Returns:
             (set[str]): List of class names.
@@ -418,11 +405,10 @@ class YOLOMultiModalDataset(YOLODataset):
 
 
 class GroundingDataset(YOLODataset):
-    """
-    Dataset class for object detection tasks using annotations from a JSON file in grounding format.
+    """Dataset class for object detection tasks using annotations from a JSON file in grounding format.
 
-    This dataset is designed for grounding tasks where annotations are provided in a JSON file rather than
-    the standard YOLO format text files.
+    This dataset is designed for grounding tasks where annotations are provided in a JSON file rather than the standard
+    YOLO format text files.
 
     Attributes:
         json_file (str): Path to the JSON file containing annotations.
@@ -438,8 +424,7 @@ class GroundingDataset(YOLODataset):
     """
 
     def __init__(self, *args, task: str = "detect", json_file: str = "", max_samples: int = 80, **kwargs):
-        """
-        Initialize a GroundingDataset for object detection.
+        """Initialize a GroundingDataset for object detection.
 
         Args:
             json_file (str): Path to the JSON file containing annotations.
@@ -454,8 +439,7 @@ class GroundingDataset(YOLODataset):
         super().__init__(*args, task=task, data={"channels": 3}, **kwargs)
 
     def get_img_files(self, img_path: str) -> list:
-        """
-        The image files would be read in `get_labels` function, return empty list here.
+        """The image files would be read in `get_labels` function, return empty list here.
 
         Args:
             img_path (str): Path to the directory containing images.
@@ -466,23 +450,21 @@ class GroundingDataset(YOLODataset):
         return []
 
     def verify_labels(self, labels: list[dict[str, Any]]) -> None:
-        """
-        Verify the number of instances in the dataset matches expected counts.
+        """Verify the number of instances in the dataset matches expected counts.
 
-        This method checks if the total number of bounding box instances in the provided
-        labels matches the expected count for known datasets. It performs validation
-        against a predefined set of datasets with known instance counts.
+        This method checks if the total number of bounding box instances in the provided labels matches the expected
+        count for known datasets. It performs validation against a predefined set of datasets with known instance
+        counts.
 
         Args:
-            labels (list[dict[str, Any]]): List of label dictionaries, where each dictionary
-                contains dataset annotations. Each label dict must have a 'bboxes' key with
-                a numpy array or tensor containing bounding box coordinates.
+            labels (list[dict[str, Any]]): List of label dictionaries, where each dictionary contains dataset
+                annotations. Each label dict must have a 'bboxes' key with a numpy array or tensor containing bounding
+                box coordinates.
 
         Raises:
-            AssertionError: If the actual instance count doesn't match the expected count
-                for a recognized dataset.
+            AssertionError: If the actual instance count doesn't match the expected count for a recognized dataset.
 
-        Note:
+        Notes:
             For unrecognized datasets (those not in the predefined expected_counts),
             a warning is logged and verification is skipped.
         """
@@ -501,8 +483,7 @@ class GroundingDataset(YOLODataset):
         LOGGER.warning(f"Skipping instance count verification for unrecognized dataset '{self.json_file}'")
 
     def cache_labels(self, path: Path = Path("./labels.cache")) -> dict[str, Any]:
-        """
-        Load annotations from a JSON file, filter, and normalize bounding boxes for each image.
+        """Load annotations from a JSON file, filter, and normalize bounding boxes for each image.
 
         Args:
             path (Path): Path where to save the cache file.
@@ -548,7 +529,7 @@ class GroundingDataset(YOLODataset):
                     cat2id[cat_name] = len(cat2id)
                     texts.append([cat_name])
                 cls = cat2id[cat_name]  # class
-                box = [cls] + box.tolist()
+                box = [cls, *box.tolist()]
                 if box not in bboxes:
                     bboxes.append(box)
                     if ann.get("segmentation") is not None:
@@ -565,7 +546,7 @@ class GroundingDataset(YOLODataset):
                                 .reshape(-1)
                                 .tolist()
                             )
-                        s = [cls] + s
+                        s = [cls, *s]
                         segments.append(s)
             lb = np.array(bboxes, dtype=np.float32) if len(bboxes) else np.zeros((0, 5), dtype=np.float32)
 
@@ -592,8 +573,7 @@ class GroundingDataset(YOLODataset):
         return x
 
     def get_labels(self) -> list[dict]:
-        """
-        Load labels from cache or generate them from JSON file.
+        """Load labels from cache or generate them from JSON file.
 
         Returns:
             (list[dict]): List of label dictionaries, each containing information about an image and its annotations.
@@ -614,8 +594,7 @@ class GroundingDataset(YOLODataset):
         return labels
 
     def build_transforms(self, hyp: dict | None = None) -> Compose:
-        """
-        Configure augmentations for training with optional text loading.
+        """Configure augmentations for training with optional text loading.
 
         Args:
             hyp (dict, optional): Hyperparameters for transforms.
@@ -661,11 +640,10 @@ class GroundingDataset(YOLODataset):
 
 
 class YOLOConcatDataset(ConcatDataset):
-    """
-    Dataset as a concatenation of multiple datasets.
+    """Dataset as a concatenation of multiple datasets.
 
-    This class is useful to assemble different existing datasets for YOLO training, ensuring they use the same
-    collation function.
+    This class is useful to assemble different existing datasets for YOLO training, ensuring they use the same collation
+    function.
 
     Methods:
         collate_fn: Static method that collates data samples into batches using YOLODataset's collation function.
@@ -678,8 +656,7 @@ class YOLOConcatDataset(ConcatDataset):
 
     @staticmethod
     def collate_fn(batch: list[dict]) -> dict:
-        """
-        Collate data samples into batches.
+        """Collate data samples into batches.
 
         Args:
             batch (list[dict]): List of dictionaries containing sample data.
@@ -690,8 +667,7 @@ class YOLOConcatDataset(ConcatDataset):
         return YOLODataset.collate_fn(batch)
 
     def close_mosaic(self, hyp: dict) -> None:
-        """
-        Set mosaic, copy_paste and mixup options to 0.0 and build transformations.
+        """Set mosaic, copy_paste and mixup options to 0.0 and build transformations.
 
         Args:
             hyp (dict): Hyperparameters for transforms.
@@ -712,8 +688,7 @@ class SemanticDataset(BaseDataset):
 
 
 class ClassificationDataset:
-    """
-    Dataset class for image classification tasks extending torchvision ImageFolder functionality.
+    """Dataset class for image classification tasks extending torchvision ImageFolder functionality.
 
     This class offers functionalities like image augmentation, caching, and verification. It's designed to efficiently
     handle large datasets for training deep learning models, with optional image transformations and caching mechanisms
@@ -723,7 +698,7 @@ class ClassificationDataset:
         cache_ram (bool): Indicates if caching in RAM is enabled.
         cache_disk (bool): Indicates if caching on disk is enabled.
         samples (list): A list of tuples, each containing the path to an image, its class index, path to its .npy cache
-                        file (if caching on disk), and optionally the loaded image array (if caching in RAM).
+            file (if caching on disk), and optionally the loaded image array (if caching in RAM).
         torch_transforms (callable): PyTorch transforms to be applied to the images.
         root (str): Root directory of the dataset.
         prefix (str): Prefix for logging and cache filenames.
@@ -735,8 +710,7 @@ class ClassificationDataset:
     """
 
     def __init__(self, root: str, args, augment: bool = False, prefix: str = ""):
-        """
-        Initialize YOLO classification dataset with root directory, arguments, augmentations, and cache settings.
+        """Initialize YOLO classification dataset with root directory, arguments, augmentations, and cache settings.
 
         Args:
             root (str): Path to the dataset directory where images are stored in a class-specific folder structure.
@@ -768,7 +742,7 @@ class ClassificationDataset:
             self.cache_ram = False
         self.cache_disk = str(args.cache).lower() == "disk"  # cache images on hard drive as uncompressed *.npy files
         self.samples = self.verify_images()  # filter out bad images
-        self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples]  # file, index, npy, im
+        self.samples = [[*list(x), Path(x[0]).with_suffix(".npy"), None] for x in self.samples]  # file, index, npy, im
         scale = (1.0 - args.scale, 1.0)  # (0.08, 1.0)
         self.torch_transforms = (
             classify_augmentations(
@@ -787,8 +761,7 @@ class ClassificationDataset:
         )
 
     def __getitem__(self, i: int) -> dict:
-        """
-        Return subset of data and targets corresponding to given indices.
+        """Return subset of data and targets corresponding to given indices.
 
         Args:
             i (int): Index of the sample to retrieve.
@@ -816,8 +789,7 @@ class ClassificationDataset:
         return len(self.samples)
 
     def verify_images(self) -> list[tuple]:
-        """
-        Verify all images in dataset.
+        """Verify all images in dataset.
 
         Returns:
             (list): List of valid samples after verification.

ultralytics/data/loaders.py

@@ -25,11 +25,10 @@ from ultralytics.utils.patches import imread
 
 @dataclass
 class SourceTypes:
-    """
-    Class to represent various types of input sources for predictions.
+    """Class to represent various types of input sources for predictions.
 
-    This class uses dataclass to define boolean flags for different types of input sources that can be used for
-    making predictions with YOLO models.
+    This class uses dataclass to define boolean flags for different types of input sources that can be used for making
+    predictions with YOLO models.
 
     Attributes:
         stream (bool): Flag indicating if the input source is a video stream.
@@ -52,11 +51,10 @@ class SourceTypes:
 
 
 class LoadStreams:
-    """
-    Stream Loader for various types of video streams.
+    """Stream Loader for various types of video streams.
 
-    Supports RTSP, RTMP, HTTP, and TCP streams. This class handles the loading and processing of multiple video
-    streams simultaneously, making it suitable for real-time video analysis tasks.
+    Supports RTSP, RTMP, HTTP, and TCP streams. This class handles the loading and processing of multiple video streams
+    simultaneously, making it suitable for real-time video analysis tasks.
 
     Attributes:
         sources (list[str]): The source input paths or URLs for the video streams.
@@ -71,7 +69,7 @@ class LoadStreams:
         shape (list[tuple[int, int, int]]): List of shapes for each stream.
         caps (list[cv2.VideoCapture]): List of cv2.VideoCapture objects for each stream.
         bs (int): Batch size for processing.
-        cv2_flag (int): OpenCV flag for image reading (grayscale or RGB).
+        cv2_flag (int): OpenCV flag for image reading (grayscale or color/BGR).
 
     Methods:
         update: Read stream frames in daemon thread.
@@ -94,21 +92,20 @@ class LoadStreams:
     """
 
     def __init__(self, sources: str = "file.streams", vid_stride: int = 1, buffer: bool = False, channels: int = 3):
-        """
-        Initialize stream loader for multiple video sources, supporting various stream types.
+        """Initialize stream loader for multiple video sources, supporting various stream types.
 
         Args:
             sources (str): Path to streams file or single stream URL.
             vid_stride (int): Video frame-rate stride.
             buffer (bool): Whether to buffer input streams.
-            channels (int): Number of image channels (1 for grayscale, 3 for RGB).
+            channels (int): Number of image channels (1 for grayscale, 3 for color).
         """
         torch.backends.cudnn.benchmark = True  # faster for fixed-size inference
         self.buffer = buffer  # buffer input streams
         self.running = True  # running flag for Thread
         self.mode = "stream"
         self.vid_stride = vid_stride  # video frame-rate stride
-        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or RGB
+        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or color (BGR)
 
         sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources]
         n = len(sources)
@@ -126,7 +123,7 @@ class LoadStreams:
             if urllib.parse.urlparse(s).hostname in {"www.youtube.com", "youtube.com", "youtu.be"}:  # YouTube video
                 # YouTube format i.e. 'https://www.youtube.com/watch?v=Jsn8D3aC840' or 'https://youtu.be/Jsn8D3aC840'
                 s = get_best_youtube_url(s)
-            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
+            s = int(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
             if s == 0 and (IS_COLAB or IS_KAGGLE):
                 raise NotImplementedError(
                     "'source=0' webcam not supported in Colab and Kaggle notebooks. "
@@ -227,11 +224,10 @@ class LoadStreams:
 
 
 class LoadScreenshots:
-    """
-    Ultralytics screenshot dataloader for capturing and processing screen images.
+    """Ultralytics screenshot dataloader for capturing and processing screen images.
 
-    This class manages the loading of screenshot images for processing with YOLO. It is suitable for use with
-    `yolo predict source=screen`.
+    This class manages the loading of screenshot images for processing with YOLO. It is suitable for use with `yolo
+    predict source=screen`.
 
     Attributes:
         source (str): The source input indicating which screen to capture.
@@ -246,7 +242,7 @@ class LoadScreenshots:
         bs (int): Batch size, set to 1.
         fps (int): Frames per second, set to 30.
         monitor (dict[str, int]): Monitor configuration details.
-        cv2_flag (int): OpenCV flag for image reading (grayscale or RGB).
+        cv2_flag (int): OpenCV flag for image reading (grayscale or color/BGR).
 
     Methods:
         __iter__: Returns an iterator object.
@@ -259,15 +255,14 @@ class LoadScreenshots:
     """
 
     def __init__(self, source: str, channels: int = 3):
-        """
-        Initialize screenshot capture with specified screen and region parameters.
+        """Initialize screenshot capture with specified screen and region parameters.
 
         Args:
             source (str): Screen capture source string in format "screen_num left top width height".
-            channels (int): Number of image channels (1 for grayscale, 3 for RGB).
+            channels (int): Number of image channels (1 for grayscale, 3 for color).
         """
         check_requirements("mss")
-        import mss  # noqa
+        import mss
 
         source, *params = source.split()
         self.screen, left, top, width, height = 0, None, None, None, None  # default to full screen 0
@@ -282,7 +277,7 @@ class LoadScreenshots:
         self.sct = mss.mss()
         self.bs = 1
         self.fps = 30
-        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or RGB
+        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or color (BGR)
 
         # Parse monitor shape
         monitor = self.sct.monitors[self.screen]
@@ -307,11 +302,10 @@ class LoadScreenshots:
 
 
 class LoadImagesAndVideos:
-    """
-    A class for loading and processing images and videos for YOLO object detection.
+    """A class for loading and processing images and videos for YOLO object detection.
 
-    This class manages the loading and pre-processing of image and video data from various sources, including
-    single image files, video files, and lists of image and video paths.
+    This class manages the loading and pre-processing of image and video data from various sources, including single
+    image files, video files, and lists of image and video paths.
 
     Attributes:
         files (list[str]): List of image and video file paths.
@@ -325,7 +319,7 @@ class LoadImagesAndVideos:
         frames (int): Total number of frames in the video.
         count (int): Counter for iteration, initialized at 0 during __iter__().
         ni (int): Number of images.
-        cv2_flag (int): OpenCV flag for image reading (grayscale or RGB).
+        cv2_flag (int): OpenCV flag for image reading (grayscale or color/BGR).
 
     Methods:
         __init__: Initialize the LoadImagesAndVideos object.
@@ -347,14 +341,13 @@ class LoadImagesAndVideos:
     """
 
     def __init__(self, path: str | Path | list, batch: int = 1, vid_stride: int = 1, channels: int = 3):
-        """
-        Initialize dataloader for images and videos, supporting various input formats.
+        """Initialize dataloader for images and videos, supporting various input formats.
 
         Args:
             path (str | Path | list): Path to images/videos, directory, or list of paths.
             batch (int): Batch size for processing.
             vid_stride (int): Video frame-rate stride.
-            channels (int): Number of image channels (1 for grayscale, 3 for RGB).
+            channels (int): Number of image channels (1 for grayscale, 3 for color).
         """
         parent = None
         if isinstance(path, str) and Path(path).suffix in {".txt", ".csv"}:  # txt/csv file with source paths
@@ -392,7 +385,7 @@ class LoadImagesAndVideos:
         self.mode = "video" if ni == 0 else "image"  # default to video if no images
         self.vid_stride = vid_stride  # video frame-rate stride
         self.bs = batch
-        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or RGB
+        self.cv2_flag = cv2.IMREAD_GRAYSCALE if channels == 1 else cv2.IMREAD_COLOR  # grayscale or color (BGR)
         if any(videos):
             self._new_video(videos[0])  # new video
         else:
@@ -490,8 +483,7 @@ class LoadImagesAndVideos:
 
 
 class LoadPilAndNumpy:
-    """
-    Load images from PIL and Numpy arrays for batch processing.
+    """Load images from PIL and Numpy arrays for batch processing.
 
     This class manages loading and pre-processing of image data from both PIL and Numpy formats. It performs basic
     validation and format conversion to ensure that the images are in the required format for downstream processing.
@@ -517,12 +509,11 @@ class LoadPilAndNumpy:
     """
 
     def __init__(self, im0: Image.Image | np.ndarray | list, channels: int = 3):
-        """
-        Initialize a loader for PIL and Numpy images, converting inputs to a standardized format.
+        """Initialize a loader for PIL and Numpy images, converting inputs to a standardized format.
 
         Args:
             im0 (PIL.Image.Image | np.ndarray | list): Single image or list of images in PIL or numpy format.
-            channels (int): Number of image channels (1 for grayscale, 3 for RGB).
+            channels (int): Number of image channels (1 for grayscale, 3 for color).
         """
         if not isinstance(im0, list):
             im0 = [im0]
@@ -535,11 +526,16 @@ class LoadPilAndNumpy:
 
     @staticmethod
     def _single_check(im: Image.Image | np.ndarray, flag: str = "RGB") -> np.ndarray:
-        """Validate and format an image to numpy array, ensuring RGB order and contiguous memory."""
+        """Validate and format an image to a NumPy array.
+
+        Notes:
+            - PIL inputs are converted to NumPy and returned in OpenCV-compatible BGR order for color images.
+            - NumPy inputs are returned as-is (no channel-order conversion is applied).
+        """
         assert isinstance(im, (Image.Image, np.ndarray)), f"Expected PIL/np.ndarray image type, but got {type(im)}"
         if isinstance(im, Image.Image):
             im = np.asarray(im.convert(flag))
-            # adding new axis if it's grayscale, and converting to BGR if it's RGB
+            # Add a new axis if grayscale; convert RGB -> BGR for OpenCV compatibility.
             im = im[..., None] if flag == "L" else im[..., ::-1]
             im = np.ascontiguousarray(im)  # contiguous
         elif im.ndim == 2:  # grayscale in numpy form
@@ -564,11 +560,10 @@ class LoadPilAndNumpy:
 
 
 class LoadTensor:
-    """
-    A class for loading and processing tensor data for object detection tasks.
+    """A class for loading and processing tensor data for object detection tasks.
 
-    This class handles the loading and pre-processing of image data from PyTorch tensors, preparing them for
-    further processing in object detection pipelines.
+    This class handles the loading and pre-processing of image data from PyTorch tensors, preparing them for further
+    processing in object detection pipelines.
 
     Attributes:
         im0 (torch.Tensor): The input tensor containing the image(s) with shape (B, C, H, W).
@@ -588,8 +583,7 @@ class LoadTensor:
     """
 
     def __init__(self, im0: torch.Tensor) -> None:
-        """
-        Initialize LoadTensor object for processing torch.Tensor image data.
+        """Initialize LoadTensor object for processing torch.Tensor image data.
 
         Args:
             im0 (torch.Tensor): Input tensor with shape (B, C, H, W).
@@ -656,8 +650,7 @@ def autocast_list(source: list[Any]) -> list[Image.Image | np.ndarray]:
 
 
 def get_best_youtube_url(url: str, method: str = "pytube") -> str | None:
-    """
-    Retrieve the URL of the best quality MP4 video stream from a given YouTube video.
+    """Retrieve the URL of the best quality MP4 video stream from a given YouTube video.
 
     Args:
         url (str): The URL of the YouTube video.
@@ -690,7 +683,7 @@ def get_best_youtube_url(url: str, method: str = "pytube") -> str | None:
 
     elif method == "pafy":
         check_requirements(("pafy", "youtube_dl==2020.12.2"))
-        import pafy  # noqa
+        import pafy
 
         return pafy.new(url).getbestvideo(preftype="mp4").url
 

ultralytics/data/split.py

@@ -11,11 +11,10 @@ from ultralytics.utils import DATASETS_DIR, LOGGER, TQDM
 
 
 def split_classify_dataset(source_dir: str | Path, train_ratio: float = 0.8) -> Path:
-    """
-    Split classification dataset into train and val directories in a new directory.
+    """Split classification dataset into train and val directories in a new directory.
 
-    Creates a new directory '{source_dir}_split' with train/val subdirectories, preserving the original class
-    structure with an 80/20 split by default.
+    Creates a new directory '{source_dir}_split' with train/val subdirectories, preserving the original class structure
+    with an 80/20 split by default.
 
     Directory structure:
         Before:
@@ -101,8 +100,8 @@ def autosplit(
     weights: tuple[float, float, float] = (0.9, 0.1, 0.0),
     annotated_only: bool = False,
 ) -> None:
-    """
-    Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
+    """Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt
+    files.
 
     Args:
         path (Path): Path to images directory.