Reference for ultralytics/data/build.py

def seed_worker(worker_id: int):  # noqa
    """Set dataloader worker seed for reproducibility across worker processes."""
    worker_seed = torch.initial_seed() % 2**32
    np.random.seed(worker_seed)
    random.seed(worker_seed)

def build_yolo_dataset(cfg, img_path, batch, data, mode="train", rect=False, stride=32, multi_modal=False):
    """Build and return a YOLO dataset based on configuration parameters."""
    dataset = YOLOMultiModalDataset if multi_modal else YOLODataset
    return dataset(
        img_path=img_path,
        imgsz=cfg.imgsz,
        batch_size=batch,
        augment=mode == "train",  # augmentation
        hyp=cfg,  # TODO: probably add a get_hyps_from_cfg function
        rect=cfg.rect or rect,  # rectangular batches
        cache=cfg.cache or None,
        single_cls=cfg.single_cls or False,
        stride=int(stride),
        pad=0.0 if mode == "train" else 0.5,
        prefix=colorstr(f"{mode}: "),
        task=cfg.task,
        classes=cfg.classes,
        data=data,
        fraction=cfg.fraction if mode == "train" else 1.0,
    )

def build_grounding(cfg, img_path, json_file, batch, mode="train", rect=False, stride=32):
    """Build and return a GroundingDataset based on configuration parameters."""
    return GroundingDataset(
        img_path=img_path,
        json_file=json_file,
        imgsz=cfg.imgsz,
        batch_size=batch,
        augment=mode == "train",  # augmentation
        hyp=cfg,  # TODO: probably add a get_hyps_from_cfg function
        rect=cfg.rect or rect,  # rectangular batches
        cache=cfg.cache or None,
        single_cls=cfg.single_cls or False,
        stride=int(stride),
        pad=0.0 if mode == "train" else 0.5,
        prefix=colorstr(f"{mode}: "),
        task=cfg.task,
        classes=cfg.classes,
        fraction=cfg.fraction if mode == "train" else 1.0,
    )

def build_dataloader(dataset, batch: int, workers: int, shuffle: bool = True, rank: int = -1):
    """
    Create and return an InfiniteDataLoader or DataLoader for training or validation.

    Args:
        dataset (Dataset): Dataset to load data from.
        batch (int): Batch size for the dataloader.
        workers (int): Number of worker threads for loading data.
        shuffle (bool, optional): Whether to shuffle the dataset.
        rank (int, optional): Process rank in distributed training. -1 for single-GPU training.

    Returns:
        (InfiniteDataLoader): A dataloader that can be used for training or validation.

    Examples:
        Create a dataloader for training
        >>> dataset = YOLODataset(...)
        >>> dataloader = build_dataloader(dataset, batch=16, workers=4, shuffle=True)
    """
    batch = min(batch, len(dataset))
    nd = torch.cuda.device_count()  # number of CUDA devices
    nw = min(os.cpu_count() // max(nd, 1), workers)  # number of workers
    sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
    generator = torch.Generator()
    generator.manual_seed(6148914691236517205 + RANK)
    return InfiniteDataLoader(
        dataset=dataset,
        batch_size=batch,
        shuffle=shuffle and sampler is None,
        num_workers=nw,
        sampler=sampler,
        pin_memory=PIN_MEMORY,
        collate_fn=getattr(dataset, "collate_fn", None),
        worker_init_fn=seed_worker,
        generator=generator,
    )

def check_source(source):
    """
    Check the type of input source and return corresponding flag values.

    Args:
        source (str | int | Path | list | tuple | np.ndarray | PIL.Image | torch.Tensor): The input source to check.

    Returns:
        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.

    Examples:
        Check a file path source
        >>> source, webcam, screenshot, from_img, in_memory, tensor = check_source("image.jpg")

        Check a webcam source
        >>> source, webcam, screenshot, from_img, in_memory, tensor = check_source(0)
    """
    webcam, screenshot, from_img, in_memory, tensor = False, False, False, False, False
    if isinstance(source, (str, int, Path)):  # int for local usb camera
        source = str(source)
        source_lower = source.lower()
        is_file = source_lower.rpartition(".")[-1] in (IMG_FORMATS | VID_FORMATS)
        is_url = source_lower.startswith(("https://", "http://", "rtsp://", "rtmp://", "tcp://"))
        webcam = source.isnumeric() or source.endswith(".streams") or (is_url and not is_file)
        screenshot = source_lower == "screen"
        if is_url and is_file:
            source = check_file(source)  # download
    elif isinstance(source, LOADERS):
        in_memory = True
    elif isinstance(source, (list, tuple)):
        source = autocast_list(source)  # convert all list elements to PIL or np arrays
        from_img = True
    elif isinstance(source, (Image.Image, np.ndarray)):
        from_img = True
    elif isinstance(source, torch.Tensor):
        tensor = True
    else:
        raise TypeError("Unsupported image type. For supported types see https://docs.ultralytics.com/modes/predict")

    return source, webcam, screenshot, from_img, in_memory, tensor

def load_inference_source(source=None, batch: int = 1, vid_stride: int = 1, buffer: bool = False, channels: int = 3):
    """
    Load an inference source for object detection and apply necessary transformations.

    Args:
        source (str | Path | torch.Tensor | PIL.Image | np.ndarray, optional): The input source for inference.
        batch (int, optional): Batch size for dataloaders.
        vid_stride (int, optional): The frame interval for video sources.
        buffer (bool, optional): Whether stream frames will be buffered.
        channels (int, optional): The number of input channels for the model.

    Returns:
        (Dataset): A dataset object for the specified input source with attached source_type attribute.

    Examples:
        Load an image source for inference
        >>> dataset = load_inference_source("image.jpg", batch=1)

        Load a video stream source
        >>> dataset = load_inference_source("rtsp://example.com/stream", vid_stride=2)
    """
    source, stream, screenshot, from_img, in_memory, tensor = check_source(source)
    source_type = source.source_type if in_memory else SourceTypes(stream, screenshot, from_img, tensor)

    # Dataloader
    if tensor:
        dataset = LoadTensor(source)
    elif in_memory:
        dataset = source
    elif stream:
        dataset = LoadStreams(source, vid_stride=vid_stride, buffer=buffer, channels=channels)
    elif screenshot:
        dataset = LoadScreenshots(source, channels=channels)
    elif from_img:
        dataset = LoadPilAndNumpy(source, channels=channels)
    else:
        dataset = LoadImagesAndVideos(source, batch=batch, vid_stride=vid_stride, channels=channels)

    # Attach source types to the dataset
    setattr(dataset, "source_type", source_type)

    return dataset