Saltar al contenido

Referencia para ultralytics/data/augment.py

Nota

Este archivo est√° disponible en https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/data/augment .py. Si detectas alg√ļn problema, por favor, ayuda a solucionarlo contribuyendo con una Pull Request ūüõ†ÔłŹ. ¬°Gracias ūüôŹ!



ultralytics.data.augment.BaseTransform

Clase base para las transformaciones de imagen.

Se trata de una clase de transformaci√≥n gen√©rica que puede ampliarse para necesidades espec√≠ficas de procesamiento de im√°genes. La clase est√° dise√Īada para ser compatible tanto con tareas de clasificaci√≥n como de segmentaci√≥n sem√°ntica.

Métodos:

Nombre Descripción
__init__

Inicializa el objeto TransformaciónBase.

apply_image

Aplica la transformación de imagen a las etiquetas.

apply_instances

Aplica transformaciones a las instancias de objetos en etiquetas.

apply_semantic

Aplica la segmentación semántica a una imagen.

__call__

Aplica todas las transformaciones de etiquetas a una imagen, instancias y m√°scaras sem√°nticas.

Código fuente en ultralytics/data/augment.py
class BaseTransform:
    """
    Base class for image transformations.

    This is a generic transformation class that can be extended for specific image processing needs.
    The class is designed to be compatible with both classification and semantic segmentation tasks.

    Methods:
        __init__: Initializes the BaseTransform object.
        apply_image: Applies image transformation to labels.
        apply_instances: Applies transformations to object instances in labels.
        apply_semantic: Applies semantic segmentation to an image.
        __call__: Applies all label transformations to an image, instances, and semantic masks.
    """

    def __init__(self) -> None:
        """Initializes the BaseTransform object."""
        pass

    def apply_image(self, labels):
        """Applies image transformations to labels."""
        pass

    def apply_instances(self, labels):
        """Applies transformations to object instances in labels."""
        pass

    def apply_semantic(self, labels):
        """Applies semantic segmentation to an image."""
        pass

    def __call__(self, labels):
        """Applies all label transformations to an image, instances, and semantic masks."""
        self.apply_image(labels)
        self.apply_instances(labels)
        self.apply_semantic(labels)

__call__(labels)

Aplica todas las transformaciones de etiquetas a una imagen, instancias y m√°scaras sem√°nticas.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """Applies all label transformations to an image, instances, and semantic masks."""
    self.apply_image(labels)
    self.apply_instances(labels)
    self.apply_semantic(labels)

__init__()

Inicializa el objeto TransformaciónBase.

Código fuente en ultralytics/data/augment.py
def __init__(self) -> None:
    """Initializes the BaseTransform object."""
    pass

apply_image(labels)

Aplica transformaciones de imagen a las etiquetas.

Código fuente en ultralytics/data/augment.py
def apply_image(self, labels):
    """Applies image transformations to labels."""
    pass

apply_instances(labels)

Aplica transformaciones a las instancias de objetos en etiquetas.

Código fuente en ultralytics/data/augment.py
def apply_instances(self, labels):
    """Applies transformations to object instances in labels."""
    pass

apply_semantic(labels)

Aplica la segmentación semántica a una imagen.

Código fuente en ultralytics/data/augment.py
def apply_semantic(self, labels):
    """Applies semantic segmentation to an image."""
    pass



ultralytics.data.augment.Compose

Clase para componer m√ļltiples transformaciones de imagen.

Código fuente en ultralytics/data/augment.py
class Compose:
    """Class for composing multiple image transformations."""

    def __init__(self, transforms):
        """Initializes the Compose object with a list of transforms."""
        self.transforms = transforms if isinstance(transforms, list) else [transforms]

    def __call__(self, data):
        """Applies a series of transformations to input data."""
        for t in self.transforms:
            data = t(data)
        return data

    def append(self, transform):
        """Appends a new transform to the existing list of transforms."""
        self.transforms.append(transform)

    def insert(self, index, transform):
        """Inserts a new transform to the existing list of transforms."""
        self.transforms.insert(index, transform)

    def __getitem__(self, index: Union[list, int]) -> "Compose":
        """Retrieve a specific transform or a set of transforms using indexing."""
        assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
        index = [index] if isinstance(index, int) else index
        return Compose([self.transforms[i] for i in index])

    def __setitem__(self, index: Union[list, int], value: Union[list, int]) -> None:
        """Retrieve a specific transform or a set of transforms using indexing."""
        assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
        if isinstance(index, list):
            assert isinstance(
                value, list
            ), f"The indices should be the same type as values, but got {type(index)} and {type(value)}"
        if isinstance(index, int):
            index, value = [index], [value]
        for i, v in zip(index, value):
            assert i < len(self.transforms), f"list index {i} out of range {len(self.transforms)}."
            self.transforms[i] = v

    def tolist(self):
        """Converts the list of transforms to a standard Python list."""
        return self.transforms

    def __repr__(self):
        """Returns a string representation of the object."""
        return f"{self.__class__.__name__}({', '.join([f'{t}' for t in self.transforms])})"

__call__(data)

Aplica una serie de transformaciones a los datos de entrada.

Código fuente en ultralytics/data/augment.py
def __call__(self, data):
    """Applies a series of transformations to input data."""
    for t in self.transforms:
        data = t(data)
    return data

__getitem__(index)

Recupera una transformación concreta o un conjunto de transformaciones utilizando la indexación.

Código fuente en ultralytics/data/augment.py
def __getitem__(self, index: Union[list, int]) -> "Compose":
    """Retrieve a specific transform or a set of transforms using indexing."""
    assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
    index = [index] if isinstance(index, int) else index
    return Compose([self.transforms[i] for i in index])

__init__(transforms)

Inicializa el objeto Componer con una lista de transformaciones.

Código fuente en ultralytics/data/augment.py
def __init__(self, transforms):
    """Initializes the Compose object with a list of transforms."""
    self.transforms = transforms if isinstance(transforms, list) else [transforms]

__repr__()

Devuelve una representación en forma de cadena del objeto.

Código fuente en ultralytics/data/augment.py
def __repr__(self):
    """Returns a string representation of the object."""
    return f"{self.__class__.__name__}({', '.join([f'{t}' for t in self.transforms])})"

__setitem__(index, value)

Recupera una transformación concreta o un conjunto de transformaciones utilizando la indexación.

Código fuente en ultralytics/data/augment.py
def __setitem__(self, index: Union[list, int], value: Union[list, int]) -> None:
    """Retrieve a specific transform or a set of transforms using indexing."""
    assert isinstance(index, (int, list)), f"The indices should be either list or int type but got {type(index)}"
    if isinstance(index, list):
        assert isinstance(
            value, list
        ), f"The indices should be the same type as values, but got {type(index)} and {type(value)}"
    if isinstance(index, int):
        index, value = [index], [value]
    for i, v in zip(index, value):
        assert i < len(self.transforms), f"list index {i} out of range {len(self.transforms)}."
        self.transforms[i] = v

append(transform)

A√Īade una nueva transformaci√≥n a la lista de transformaciones existente.

Código fuente en ultralytics/data/augment.py
def append(self, transform):
    """Appends a new transform to the existing list of transforms."""
    self.transforms.append(transform)

insert(index, transform)

Inserta una nueva transformación en la lista de transformaciones existente.

Código fuente en ultralytics/data/augment.py
def insert(self, index, transform):
    """Inserts a new transform to the existing list of transforms."""
    self.transforms.insert(index, transform)

tolist()

Convierte la lista de transformaciones en una lista est√°ndar de Python .

Código fuente en ultralytics/data/augment.py
def tolist(self):
    """Converts the list of transforms to a standard Python list."""
    return self.transforms



ultralytics.data.augment.BaseMixTransform

Clase para transformaciones de mezcla base (MixUp/Mosaico).

Esta implementación es de mmyolo.

Código fuente en ultralytics/data/augment.py
class BaseMixTransform:
    """
    Class for base mix (MixUp/Mosaic) transformations.

    This implementation is from mmyolo.
    """

    def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
        """Initializes the BaseMixTransform object with dataset, pre_transform, and probability."""
        self.dataset = dataset
        self.pre_transform = pre_transform
        self.p = p

    def __call__(self, labels):
        """Applies pre-processing transforms and mixup/mosaic transforms to labels data."""
        if random.uniform(0, 1) > self.p:
            return labels

        # Get index of one or three other images
        indexes = self.get_indexes()
        if isinstance(indexes, int):
            indexes = [indexes]

        # Get images information will be used for Mosaic or MixUp
        mix_labels = [self.dataset.get_image_and_label(i) for i in indexes]

        if self.pre_transform is not None:
            for i, data in enumerate(mix_labels):
                mix_labels[i] = self.pre_transform(data)
        labels["mix_labels"] = mix_labels

        # Update cls and texts
        labels = self._update_label_text(labels)
        # Mosaic 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."""
        raise NotImplementedError

    def get_indexes(self):
        """Gets a list of shuffled indexes for mosaic augmentation."""
        raise NotImplementedError

    def _update_label_text(self, labels):
        """Update label text."""
        if "texts" not in labels:
            return labels

        mix_texts = sum([labels["texts"]] + [x["texts"] for x in labels["mix_labels"]], [])
        mix_texts = list({tuple(x) for x in mix_texts})
        text2id = {text: i for i, text in enumerate(mix_texts)}

        for label in [labels] + labels["mix_labels"]:
            for i, cls in enumerate(label["cls"].squeeze(-1).tolist()):
                text = label["texts"][int(cls)]
                label["cls"][i] = text2id[tuple(text)]
            label["texts"] = mix_texts
        return labels

__call__(labels)

Aplica transformaciones de preprocesamiento y transformaciones de mezcla/mosaico a los datos de las etiquetas.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """Applies pre-processing transforms and mixup/mosaic transforms to labels data."""
    if random.uniform(0, 1) > self.p:
        return labels

    # Get index of one or three other images
    indexes = self.get_indexes()
    if isinstance(indexes, int):
        indexes = [indexes]

    # Get images information will be used for Mosaic or MixUp
    mix_labels = [self.dataset.get_image_and_label(i) for i in indexes]

    if self.pre_transform is not None:
        for i, data in enumerate(mix_labels):
            mix_labels[i] = self.pre_transform(data)
    labels["mix_labels"] = mix_labels

    # Update cls and texts
    labels = self._update_label_text(labels)
    # Mosaic or MixUp
    labels = self._mix_transform(labels)
    labels.pop("mix_labels", None)
    return labels

__init__(dataset, pre_transform=None, p=0.0)

Inicializa el objeto BaseMixTransform con conjunto de datos, pre_transformación y probabilidad.

Código fuente en ultralytics/data/augment.py
def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
    """Initializes the BaseMixTransform object with dataset, pre_transform, and probability."""
    self.dataset = dataset
    self.pre_transform = pre_transform
    self.p = p

get_indexes()

Obtiene una lista de índices barajados para el aumento del mosaico.

Código fuente en ultralytics/data/augment.py
def get_indexes(self):
    """Gets a list of shuffled indexes for mosaic augmentation."""
    raise NotImplementedError



ultralytics.data.augment.Mosaic

Bases: BaseMixTransform

Aumento del mosaico.

Esta clase realiza el aumento de mosaico combinando varias (4 ó 9) imágenes en una sola imagen de mosaico. El aumento se aplica a un conjunto de datos con una probabilidad determinada.

Atributos:

Nombre Tipo Descripción
dataset

El conjunto de datos sobre el que se aplica el aumento de mosaico.

imgsz int

Tama√Īo de la imagen (alto y ancho) tras la canalizaci√≥n en mosaico de una sola imagen. Por defecto 640.

p float

Probabilidad de aplicar el aumento de mosaico. Debe estar en el intervalo 0-1. Por defecto es 1,0.

n int

El tama√Īo de la cuadr√≠cula, 4 (para 2x2) o 9 (para 3x3).

Código fuente en ultralytics/data/augment.py
class Mosaic(BaseMixTransform):
    """
    Mosaic augmentation.

    This class performs mosaic augmentation by combining multiple (4 or 9) images into a single mosaic image.
    The augmentation is applied to a dataset with a given probability.

    Attributes:
        dataset: The dataset on which the mosaic augmentation is applied.
        imgsz (int, optional): Image size (height and width) after mosaic pipeline of a single image. Default to 640.
        p (float, optional): Probability of applying the mosaic augmentation. Must be in the range 0-1. Default to 1.0.
        n (int, optional): The grid size, either 4 (for 2x2) or 9 (for 3x3).
    """

    def __init__(self, dataset, imgsz=640, p=1.0, n=4):
        """Initializes the object with a dataset, image size, probability, and border."""
        assert 0 <= p <= 1.0, f"The probability should be in range [0, 1], but got {p}."
        assert n in {4, 9}, "grid must be equal to 4 or 9."
        super().__init__(dataset=dataset, p=p)
        self.dataset = dataset
        self.imgsz = imgsz
        self.border = (-imgsz // 2, -imgsz // 2)  # width, height
        self.n = n

    def get_indexes(self, buffer=True):
        """Return a list of random indexes from the dataset."""
        if buffer:  # select images from buffer
            return random.choices(list(self.dataset.buffer), k=self.n - 1)
        else:  # select any images
            return [random.randint(0, len(self.dataset) - 1) for _ in range(self.n - 1)]

    def _mix_transform(self, labels):
        """Apply mixup transformation to the input image and labels."""
        assert labels.get("rect_shape", None) is None, "rect and mosaic are mutually exclusive."
        assert len(labels.get("mix_labels", [])), "There are no other images for mosaic augment."
        return (
            self._mosaic3(labels) if self.n == 3 else self._mosaic4(labels) if self.n == 4 else self._mosaic9(labels)
        )  # This code is modified for mosaic3 method.

    def _mosaic3(self, labels):
        """Create a 1x3 image mosaic."""
        mosaic_labels = []
        s = self.imgsz
        for i in range(3):
            labels_patch = labels if i == 0 else labels["mix_labels"][i - 1]
            # Load image
            img = labels_patch["img"]
            h, w = labels_patch.pop("resized_shape")

            # Place img in img3
            if i == 0:  # center
                img3 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 3 tiles
                h0, w0 = h, w
                c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
            elif i == 1:  # right
                c = s + w0, s, s + w0 + w, s + h
            elif i == 2:  # left
                c = s - w, s + h0 - h, s, s + h0

            padw, padh = c[:2]
            x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords

            img3[y1:y2, x1:x2] = img[y1 - padh :, x1 - padw :]  # img3[ymin:ymax, xmin:xmax]
            # hp, wp = h, w  # height, width previous for next iteration

            # Labels assuming imgsz*2 mosaic size
            labels_patch = self._update_labels(labels_patch, padw + self.border[0], padh + self.border[1])
            mosaic_labels.append(labels_patch)
        final_labels = self._cat_labels(mosaic_labels)

        final_labels["img"] = img3[-self.border[0] : self.border[0], -self.border[1] : self.border[1]]
        return final_labels

    def _mosaic4(self, labels):
        """Create a 2x2 image mosaic."""
        mosaic_labels = []
        s = self.imgsz
        yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.border)  # mosaic center x, y
        for i in range(4):
            labels_patch = labels if i == 0 else labels["mix_labels"][i - 1]
            # Load image
            img = labels_patch["img"]
            h, w = labels_patch.pop("resized_shape")

            # Place img in img4
            if i == 0:  # top left
                img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
            elif i == 1:  # top right
                x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
                x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
            elif i == 2:  # bottom left
                x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
            elif i == 3:  # bottom right
                x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

            img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
            padw = x1a - x1b
            padh = y1a - y1b

            labels_patch = self._update_labels(labels_patch, padw, padh)
            mosaic_labels.append(labels_patch)
        final_labels = self._cat_labels(mosaic_labels)
        final_labels["img"] = img4
        return final_labels

    def _mosaic9(self, labels):
        """Create a 3x3 image mosaic."""
        mosaic_labels = []
        s = self.imgsz
        hp, wp = -1, -1  # height, width previous
        for i in range(9):
            labels_patch = labels if i == 0 else labels["mix_labels"][i - 1]
            # Load image
            img = labels_patch["img"]
            h, w = labels_patch.pop("resized_shape")

            # Place img in img9
            if i == 0:  # center
                img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                h0, w0 = h, w
                c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
            elif i == 1:  # top
                c = s, s - h, s + w, s
            elif i == 2:  # top right
                c = s + wp, s - h, s + wp + w, s
            elif i == 3:  # right
                c = s + w0, s, s + w0 + w, s + h
            elif i == 4:  # bottom right
                c = s + w0, s + hp, s + w0 + w, s + hp + h
            elif i == 5:  # bottom
                c = s + w0 - w, s + h0, s + w0, s + h0 + h
            elif i == 6:  # bottom left
                c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
            elif i == 7:  # left
                c = s - w, s + h0 - h, s, s + h0
            elif i == 8:  # top left
                c = s - w, s + h0 - hp - h, s, s + h0 - hp

            padw, padh = c[:2]
            x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords

            # Image
            img9[y1:y2, x1:x2] = img[y1 - padh :, x1 - padw :]  # img9[ymin:ymax, xmin:xmax]
            hp, wp = h, w  # height, width previous for next iteration

            # Labels assuming imgsz*2 mosaic size
            labels_patch = self._update_labels(labels_patch, padw + self.border[0], padh + self.border[1])
            mosaic_labels.append(labels_patch)
        final_labels = self._cat_labels(mosaic_labels)

        final_labels["img"] = img9[-self.border[0] : self.border[0], -self.border[1] : self.border[1]]
        return final_labels

    @staticmethod
    def _update_labels(labels, padw, padh):
        """Update labels."""
        nh, nw = labels["img"].shape[:2]
        labels["instances"].convert_bbox(format="xyxy")
        labels["instances"].denormalize(nw, nh)
        labels["instances"].add_padding(padw, padh)
        return labels

    def _cat_labels(self, mosaic_labels):
        """Return labels with mosaic border instances clipped."""
        if len(mosaic_labels) == 0:
            return {}
        cls = []
        instances = []
        imgsz = self.imgsz * 2  # mosaic imgsz
        for labels in mosaic_labels:
            cls.append(labels["cls"])
            instances.append(labels["instances"])
        # Final labels
        final_labels = {
            "im_file": mosaic_labels[0]["im_file"],
            "ori_shape": mosaic_labels[0]["ori_shape"],
            "resized_shape": (imgsz, imgsz),
            "cls": np.concatenate(cls, 0),
            "instances": Instances.concatenate(instances, axis=0),
            "mosaic_border": self.border,
        }
        final_labels["instances"].clip(imgsz, imgsz)
        good = final_labels["instances"].remove_zero_area_boxes()
        final_labels["cls"] = final_labels["cls"][good]
        if "texts" in mosaic_labels[0]:
            final_labels["texts"] = mosaic_labels[0]["texts"]
        return final_labels

__init__(dataset, imgsz=640, p=1.0, n=4)

Inicializa el objeto con un conjunto de datos, tama√Īo de imagen, probabilidad y borde.

Código fuente en ultralytics/data/augment.py
def __init__(self, dataset, imgsz=640, p=1.0, n=4):
    """Initializes the object with a dataset, image size, probability, and border."""
    assert 0 <= p <= 1.0, f"The probability should be in range [0, 1], but got {p}."
    assert n in {4, 9}, "grid must be equal to 4 or 9."
    super().__init__(dataset=dataset, p=p)
    self.dataset = dataset
    self.imgsz = imgsz
    self.border = (-imgsz // 2, -imgsz // 2)  # width, height
    self.n = n

get_indexes(buffer=True)

Devuelve una lista de índices aleatorios del conjunto de datos.

Código fuente en ultralytics/data/augment.py
def get_indexes(self, buffer=True):
    """Return a list of random indexes from the dataset."""
    if buffer:  # select images from buffer
        return random.choices(list(self.dataset.buffer), k=self.n - 1)
    else:  # select any images
        return [random.randint(0, len(self.dataset) - 1) for _ in range(self.n - 1)]



ultralytics.data.augment.MixUp

Bases: BaseMixTransform

Clase para aplicar el aumento MixUp al conjunto de datos.

Código fuente en ultralytics/data/augment.py
class MixUp(BaseMixTransform):
    """Class for applying MixUp augmentation to the dataset."""

    def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
        """Initializes MixUp object with dataset, pre_transform, and probability of applying MixUp."""
        super().__init__(dataset=dataset, pre_transform=pre_transform, p=p)

    def get_indexes(self):
        """Get a random index from the dataset."""
        return random.randint(0, len(self.dataset) - 1)

    def _mix_transform(self, labels):
        """Applies MixUp augmentation as per https://arxiv.org/pdf/1710.09412.pdf."""
        r = np.random.beta(32.0, 32.0)  # mixup ratio, alpha=beta=32.0
        labels2 = labels["mix_labels"][0]
        labels["img"] = (labels["img"] * r + labels2["img"] * (1 - r)).astype(np.uint8)
        labels["instances"] = Instances.concatenate([labels["instances"], labels2["instances"]], axis=0)
        labels["cls"] = np.concatenate([labels["cls"], labels2["cls"]], 0)
        return labels

__init__(dataset, pre_transform=None, p=0.0)

Inicializa el objeto MixUp con el conjunto de datos, la pre_transformación y la probabilidad de aplicar MixUp.

Código fuente en ultralytics/data/augment.py
def __init__(self, dataset, pre_transform=None, p=0.0) -> None:
    """Initializes MixUp object with dataset, pre_transform, and probability of applying MixUp."""
    super().__init__(dataset=dataset, pre_transform=pre_transform, p=p)

get_indexes()

Obtener un índice aleatorio del conjunto de datos.

Código fuente en ultralytics/data/augment.py
def get_indexes(self):
    """Get a random index from the dataset."""
    return random.randint(0, len(self.dataset) - 1)



ultralytics.data.augment.RandomPerspective

Implementa transformaciones afines y de perspectiva aleatorias en imágenes y sus correspondientes cuadros delimitadores, segmentos y puntos clave. puntos clave. Estas transformaciones incluyen rotación, traslación, escalado y cizallamiento. La clase también ofrece la opción opción de aplicar estas transformaciones condicionalmente con una probabilidad especificada.

Atributos:

Nombre Tipo Descripción
degrees float

Rango de grados para rotaciones aleatorias.

translate float

Fracción de la anchura y altura totales para la traslación aleatoria.

scale float

Intervalo del factor de escala, por ejemplo, un factor de escala de 0,1 permite un redimensionamiento entre 90%-110%.

shear float

Intensidad de cizallamiento (√°ngulo en grados).

perspective float

Factor de distorsión de la perspectiva.

border tuple

Tupla que especifica el borde del mosaico.

pre_transform callable

Una función/transformación para aplicar a la imagen antes de iniciar la transformación aleatoria.

Métodos:

Nombre Descripción
affine_transform

Aplica una serie de transformaciones afines a la imagen.

apply_bboxes

Transforma los cuadros delimitadores utilizando la matriz afín calculada.

apply_segments

Transforma segmentos y genera nuevas cajas delimitadoras.

apply_keypoints

Transforma los puntos clave.

__call__

Método principal para aplicar transformaciones tanto a las imágenes como a sus correspondientes anotaciones.

box_candidates

Filtra los cuadros delimitadores que no cumplan determinados criterios tras la transformación.

Código fuente en ultralytics/data/augment.py
class RandomPerspective:
    """
    Implements random perspective and affine transformations on images and corresponding bounding boxes, segments, and
    keypoints. These transformations include rotation, translation, scaling, and shearing. The class also offers the
    option to apply these transformations conditionally with a specified probability.

    Attributes:
        degrees (float): Degree range for random rotations.
        translate (float): Fraction of total width and height for random translation.
        scale (float): Scaling factor interval, e.g., a scale factor of 0.1 allows a resize between 90%-110%.
        shear (float): Shear intensity (angle in degrees).
        perspective (float): Perspective distortion factor.
        border (tuple): Tuple specifying mosaic border.
        pre_transform (callable): A function/transform to apply to the image before starting the random transformation.

    Methods:
        affine_transform(img, border): Applies a series of affine transformations to the image.
        apply_bboxes(bboxes, M): Transforms bounding boxes using the calculated affine matrix.
        apply_segments(segments, M): Transforms segments and generates new bounding boxes.
        apply_keypoints(keypoints, M): Transforms keypoints.
        __call__(labels): Main method to apply transformations to both images and their corresponding annotations.
        box_candidates(box1, box2): Filters out bounding boxes that don't meet certain criteria post-transformation.
    """

    def __init__(
        self, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, border=(0, 0), pre_transform=None
    ):
        """Initializes RandomPerspective object with transformation parameters."""

        self.degrees = degrees
        self.translate = translate
        self.scale = scale
        self.shear = shear
        self.perspective = perspective
        self.border = border  # mosaic border
        self.pre_transform = pre_transform

    def affine_transform(self, img, border):
        """
        Applies a sequence of affine transformations centered around the image center.

        Args:
            img (ndarray): Input image.
            border (tuple): Border dimensions.

        Returns:
            img (ndarray): Transformed image.
            M (ndarray): Transformation matrix.
            s (float): Scale factor.
        """

        # Center
        C = np.eye(3, dtype=np.float32)

        C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
        C[1, 2] = -img.shape[0] / 2  # y translation (pixels)

        # Perspective
        P = np.eye(3, dtype=np.float32)
        P[2, 0] = random.uniform(-self.perspective, self.perspective)  # x perspective (about y)
        P[2, 1] = random.uniform(-self.perspective, self.perspective)  # y perspective (about x)

        # Rotation and Scale
        R = np.eye(3, dtype=np.float32)
        a = random.uniform(-self.degrees, self.degrees)
        # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
        s = random.uniform(1 - self.scale, 1 + self.scale)
        # s = 2 ** random.uniform(-scale, scale)
        R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)

        # Shear
        S = np.eye(3, dtype=np.float32)
        S[0, 1] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180)  # x shear (deg)
        S[1, 0] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180)  # y shear (deg)

        # Translation
        T = np.eye(3, dtype=np.float32)
        T[0, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[0]  # x translation (pixels)
        T[1, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[1]  # y translation (pixels)

        # Combined rotation matrix
        M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
        # Affine image
        if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
            if self.perspective:
                img = cv2.warpPerspective(img, M, dsize=self.size, borderValue=(114, 114, 114))
            else:  # affine
                img = cv2.warpAffine(img, M[:2], dsize=self.size, borderValue=(114, 114, 114))
        return img, M, s

    def apply_bboxes(self, bboxes, M):
        """
        Apply affine to bboxes only.

        Args:
            bboxes (ndarray): list of bboxes, xyxy format, with shape (num_bboxes, 4).
            M (ndarray): affine matrix.

        Returns:
            new_bboxes (ndarray): bboxes after affine, [num_bboxes, 4].
        """
        n = len(bboxes)
        if n == 0:
            return bboxes

        xy = np.ones((n * 4, 3), dtype=bboxes.dtype)
        xy[:, :2] = bboxes[:, [0, 1, 2, 3, 0, 3, 2, 1]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
        xy = xy @ M.T  # transform
        xy = (xy[:, :2] / xy[:, 2:3] if self.perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine

        # Create new boxes
        x = xy[:, [0, 2, 4, 6]]
        y = xy[:, [1, 3, 5, 7]]
        return np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1)), dtype=bboxes.dtype).reshape(4, n).T

    def apply_segments(self, segments, M):
        """
        Apply affine to segments and generate new bboxes from segments.

        Args:
            segments (ndarray): list of segments, [num_samples, 500, 2].
            M (ndarray): affine matrix.

        Returns:
            new_segments (ndarray): list of segments after affine, [num_samples, 500, 2].
            new_bboxes (ndarray): bboxes after affine, [N, 4].
        """
        n, num = segments.shape[:2]
        if n == 0:
            return [], segments

        xy = np.ones((n * num, 3), dtype=segments.dtype)
        segments = segments.reshape(-1, 2)
        xy[:, :2] = segments
        xy = xy @ M.T  # transform
        xy = xy[:, :2] / xy[:, 2:3]
        segments = xy.reshape(n, -1, 2)
        bboxes = np.stack([segment2box(xy, self.size[0], self.size[1]) for xy in segments], 0)
        segments[..., 0] = segments[..., 0].clip(bboxes[:, 0:1], bboxes[:, 2:3])
        segments[..., 1] = segments[..., 1].clip(bboxes[:, 1:2], bboxes[:, 3:4])
        return bboxes, segments

    def apply_keypoints(self, keypoints, M):
        """
        Apply affine to keypoints.

        Args:
            keypoints (ndarray): keypoints, [N, 17, 3].
            M (ndarray): affine matrix.

        Returns:
            new_keypoints (ndarray): keypoints after affine, [N, 17, 3].
        """
        n, nkpt = keypoints.shape[:2]
        if n == 0:
            return keypoints
        xy = np.ones((n * nkpt, 3), dtype=keypoints.dtype)
        visible = keypoints[..., 2].reshape(n * nkpt, 1)
        xy[:, :2] = keypoints[..., :2].reshape(n * nkpt, 2)
        xy = xy @ M.T  # transform
        xy = xy[:, :2] / xy[:, 2:3]  # perspective rescale or affine
        out_mask = (xy[:, 0] < 0) | (xy[:, 1] < 0) | (xy[:, 0] > self.size[0]) | (xy[:, 1] > self.size[1])
        visible[out_mask] = 0
        return np.concatenate([xy, visible], axis=-1).reshape(n, nkpt, 3)

    def __call__(self, labels):
        """
        Affine images and targets.

        Args:
            labels (dict): a dict of `bboxes`, `segments`, `keypoints`.
        """
        if self.pre_transform and "mosaic_border" not in labels:
            labels = self.pre_transform(labels)
        labels.pop("ratio_pad", None)  # do not need ratio pad

        img = labels["img"]
        cls = labels["cls"]
        instances = labels.pop("instances")
        # Make sure the coord formats are right
        instances.convert_bbox(format="xyxy")
        instances.denormalize(*img.shape[:2][::-1])

        border = labels.pop("mosaic_border", self.border)
        self.size = img.shape[1] + border[1] * 2, img.shape[0] + border[0] * 2  # w, h
        # M is affine matrix
        # Scale for func:`box_candidates`
        img, M, scale = self.affine_transform(img, border)

        bboxes = self.apply_bboxes(instances.bboxes, M)

        segments = instances.segments
        keypoints = instances.keypoints
        # Update bboxes if there are segments.
        if len(segments):
            bboxes, segments = self.apply_segments(segments, M)

        if keypoints is not None:
            keypoints = self.apply_keypoints(keypoints, M)
        new_instances = Instances(bboxes, segments, keypoints, bbox_format="xyxy", normalized=False)
        # Clip
        new_instances.clip(*self.size)

        # Filter instances
        instances.scale(scale_w=scale, scale_h=scale, bbox_only=True)
        # Make the bboxes have the same scale with new_bboxes
        i = self.box_candidates(
            box1=instances.bboxes.T, box2=new_instances.bboxes.T, area_thr=0.01 if len(segments) else 0.10
        )
        labels["instances"] = new_instances[i]
        labels["cls"] = cls[i]
        labels["img"] = img
        labels["resized_shape"] = img.shape[:2]
        return labels

    def box_candidates(self, box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
        """
        Compute box candidates based on a set of thresholds. This method compares the characteristics of the boxes
        before and after augmentation to decide whether a box is a candidate for further processing.

        Args:
            box1 (numpy.ndarray): The 4,n bounding box before augmentation, represented as [x1, y1, x2, y2].
            box2 (numpy.ndarray): The 4,n bounding box after augmentation, represented as [x1, y1, x2, y2].
            wh_thr (float, optional): The width and height threshold in pixels. Default is 2.
            ar_thr (float, optional): The aspect ratio threshold. Default is 100.
            area_thr (float, optional): The area ratio threshold. Default is 0.1.
            eps (float, optional): A small epsilon value to prevent division by zero. Default is 1e-16.

        Returns:
            (numpy.ndarray): A boolean array indicating which boxes are candidates based on the given thresholds.
        """
        w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
        w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
        ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
        return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates

__call__(labels)

Im√°genes y objetivos afines.

Par√°metros:

Nombre Tipo Descripción Por defecto
labels dict

un dictado de bboxes, segments, keypoints.

necesario
Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """
    Affine images and targets.

    Args:
        labels (dict): a dict of `bboxes`, `segments`, `keypoints`.
    """
    if self.pre_transform and "mosaic_border" not in labels:
        labels = self.pre_transform(labels)
    labels.pop("ratio_pad", None)  # do not need ratio pad

    img = labels["img"]
    cls = labels["cls"]
    instances = labels.pop("instances")
    # Make sure the coord formats are right
    instances.convert_bbox(format="xyxy")
    instances.denormalize(*img.shape[:2][::-1])

    border = labels.pop("mosaic_border", self.border)
    self.size = img.shape[1] + border[1] * 2, img.shape[0] + border[0] * 2  # w, h
    # M is affine matrix
    # Scale for func:`box_candidates`
    img, M, scale = self.affine_transform(img, border)

    bboxes = self.apply_bboxes(instances.bboxes, M)

    segments = instances.segments
    keypoints = instances.keypoints
    # Update bboxes if there are segments.
    if len(segments):
        bboxes, segments = self.apply_segments(segments, M)

    if keypoints is not None:
        keypoints = self.apply_keypoints(keypoints, M)
    new_instances = Instances(bboxes, segments, keypoints, bbox_format="xyxy", normalized=False)
    # Clip
    new_instances.clip(*self.size)

    # Filter instances
    instances.scale(scale_w=scale, scale_h=scale, bbox_only=True)
    # Make the bboxes have the same scale with new_bboxes
    i = self.box_candidates(
        box1=instances.bboxes.T, box2=new_instances.bboxes.T, area_thr=0.01 if len(segments) else 0.10
    )
    labels["instances"] = new_instances[i]
    labels["cls"] = cls[i]
    labels["img"] = img
    labels["resized_shape"] = img.shape[:2]
    return labels

__init__(degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, border=(0, 0), pre_transform=None)

Inicializa el objeto PerspectivaAleatoria con los parámetros de transformación.

Código fuente en ultralytics/data/augment.py
def __init__(
    self, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, border=(0, 0), pre_transform=None
):
    """Initializes RandomPerspective object with transformation parameters."""

    self.degrees = degrees
    self.translate = translate
    self.scale = scale
    self.shear = shear
    self.perspective = perspective
    self.border = border  # mosaic border
    self.pre_transform = pre_transform

affine_transform(img, border)

Aplica una secuencia de transformaciones afines centradas en el centro de la imagen.

Par√°metros:

Nombre Tipo Descripción Por defecto
img ndarray

Imagen de entrada.

necesario
border tuple

Dimensiones de los bordes.

necesario

Devuelve:

Nombre Tipo Descripción
img ndarray

Imagen transformada.

M ndarray

Matriz de transformación.

s float

Factor de escala.

Código fuente en ultralytics/data/augment.py
def affine_transform(self, img, border):
    """
    Applies a sequence of affine transformations centered around the image center.

    Args:
        img (ndarray): Input image.
        border (tuple): Border dimensions.

    Returns:
        img (ndarray): Transformed image.
        M (ndarray): Transformation matrix.
        s (float): Scale factor.
    """

    # Center
    C = np.eye(3, dtype=np.float32)

    C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
    C[1, 2] = -img.shape[0] / 2  # y translation (pixels)

    # Perspective
    P = np.eye(3, dtype=np.float32)
    P[2, 0] = random.uniform(-self.perspective, self.perspective)  # x perspective (about y)
    P[2, 1] = random.uniform(-self.perspective, self.perspective)  # y perspective (about x)

    # Rotation and Scale
    R = np.eye(3, dtype=np.float32)
    a = random.uniform(-self.degrees, self.degrees)
    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
    s = random.uniform(1 - self.scale, 1 + self.scale)
    # s = 2 ** random.uniform(-scale, scale)
    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)

    # Shear
    S = np.eye(3, dtype=np.float32)
    S[0, 1] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180)  # x shear (deg)
    S[1, 0] = math.tan(random.uniform(-self.shear, self.shear) * math.pi / 180)  # y shear (deg)

    # Translation
    T = np.eye(3, dtype=np.float32)
    T[0, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[0]  # x translation (pixels)
    T[1, 2] = random.uniform(0.5 - self.translate, 0.5 + self.translate) * self.size[1]  # y translation (pixels)

    # Combined rotation matrix
    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
    # Affine image
    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
        if self.perspective:
            img = cv2.warpPerspective(img, M, dsize=self.size, borderValue=(114, 114, 114))
        else:  # affine
            img = cv2.warpAffine(img, M[:2], dsize=self.size, borderValue=(114, 114, 114))
    return img, M, s

apply_bboxes(bboxes, M)

Aplica la afinidad sólo a las cajas b.

Par√°metros:

Nombre Tipo Descripción Por defecto
bboxes ndarray

lista de bboxes, formato xyxy, con forma (num_bboxes, 4).

necesario
M ndarray

matriz afín.

necesario

Devuelve:

Nombre Tipo Descripción
new_bboxes ndarray

bboxes después de affine, [num_bboxes, 4].

Código fuente en ultralytics/data/augment.py
def apply_bboxes(self, bboxes, M):
    """
    Apply affine to bboxes only.

    Args:
        bboxes (ndarray): list of bboxes, xyxy format, with shape (num_bboxes, 4).
        M (ndarray): affine matrix.

    Returns:
        new_bboxes (ndarray): bboxes after affine, [num_bboxes, 4].
    """
    n = len(bboxes)
    if n == 0:
        return bboxes

    xy = np.ones((n * 4, 3), dtype=bboxes.dtype)
    xy[:, :2] = bboxes[:, [0, 1, 2, 3, 0, 3, 2, 1]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
    xy = xy @ M.T  # transform
    xy = (xy[:, :2] / xy[:, 2:3] if self.perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine

    # Create new boxes
    x = xy[:, [0, 2, 4, 6]]
    y = xy[:, [1, 3, 5, 7]]
    return np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1)), dtype=bboxes.dtype).reshape(4, n).T

apply_keypoints(keypoints, M)

Aplica la afinidad a los puntos clave.

Par√°metros:

Nombre Tipo Descripción Por defecto
keypoints ndarray

puntos clave, [N, 17, 3].

necesario
M ndarray

matriz afín.

necesario

Devuelve:

Nombre Tipo Descripción
new_keypoints ndarray

puntos clave después de afín, [N, 17, 3].

Código fuente en ultralytics/data/augment.py
def apply_keypoints(self, keypoints, M):
    """
    Apply affine to keypoints.

    Args:
        keypoints (ndarray): keypoints, [N, 17, 3].
        M (ndarray): affine matrix.

    Returns:
        new_keypoints (ndarray): keypoints after affine, [N, 17, 3].
    """
    n, nkpt = keypoints.shape[:2]
    if n == 0:
        return keypoints
    xy = np.ones((n * nkpt, 3), dtype=keypoints.dtype)
    visible = keypoints[..., 2].reshape(n * nkpt, 1)
    xy[:, :2] = keypoints[..., :2].reshape(n * nkpt, 2)
    xy = xy @ M.T  # transform
    xy = xy[:, :2] / xy[:, 2:3]  # perspective rescale or affine
    out_mask = (xy[:, 0] < 0) | (xy[:, 1] < 0) | (xy[:, 0] > self.size[0]) | (xy[:, 1] > self.size[1])
    visible[out_mask] = 0
    return np.concatenate([xy, visible], axis=-1).reshape(n, nkpt, 3)

apply_segments(segments, M)

Aplica afines a segmentos y genera nuevos bboxes a partir de segmentos.

Par√°metros:

Nombre Tipo Descripción Por defecto
segments ndarray

lista de segmentos, [num_muestras, 500, 2].

necesario
M ndarray

matriz afín.

necesario

Devuelve:

Nombre Tipo Descripción
new_segments ndarray

lista de segmentos después de afinar, [num_muestras, 500, 2].

new_bboxes ndarray

bboxes después de afín, [N, 4].

Código fuente en ultralytics/data/augment.py
def apply_segments(self, segments, M):
    """
    Apply affine to segments and generate new bboxes from segments.

    Args:
        segments (ndarray): list of segments, [num_samples, 500, 2].
        M (ndarray): affine matrix.

    Returns:
        new_segments (ndarray): list of segments after affine, [num_samples, 500, 2].
        new_bboxes (ndarray): bboxes after affine, [N, 4].
    """
    n, num = segments.shape[:2]
    if n == 0:
        return [], segments

    xy = np.ones((n * num, 3), dtype=segments.dtype)
    segments = segments.reshape(-1, 2)
    xy[:, :2] = segments
    xy = xy @ M.T  # transform
    xy = xy[:, :2] / xy[:, 2:3]
    segments = xy.reshape(n, -1, 2)
    bboxes = np.stack([segment2box(xy, self.size[0], self.size[1]) for xy in segments], 0)
    segments[..., 0] = segments[..., 0].clip(bboxes[:, 0:1], bboxes[:, 2:3])
    segments[..., 1] = segments[..., 1].clip(bboxes[:, 1:2], bboxes[:, 3:4])
    return bboxes, segments

box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16)

Calcula las cajas candidatas en función de un conjunto de umbrales. Este método compara las características de las casillas antes y después del aumento para decidir si una casilla es candidata a un tratamiento posterior.

Par√°metros:

Nombre Tipo Descripción Por defecto
box1 ndarray

El cuadro delimitador 4,n antes del aumento, representado como [x1, y1, x2, y2].

necesario
box2 ndarray

La caja delimitadora 4,n tras el aumento, representada como [x1, y1, x2, y2].

necesario
wh_thr float

El umbral de anchura y altura en píxeles. Por defecto es 2.

2
ar_thr float

El umbral de relación de aspecto. Por defecto es 100.

100
area_thr float

El umbral de la relación de áreas. Por defecto es 0,1.

0.1
eps float

Un valor √©psilon peque√Īo para evitar la divisi√≥n por cero. Por defecto es 1e-16.

1e-16

Devuelve:

Tipo Descripción
ndarray

Una matriz booleana que indica qué casillas son candidatas en función de los umbrales dados.

Código fuente en ultralytics/data/augment.py
def box_candidates(self, box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):
    """
    Compute box candidates based on a set of thresholds. This method compares the characteristics of the boxes
    before and after augmentation to decide whether a box is a candidate for further processing.

    Args:
        box1 (numpy.ndarray): The 4,n bounding box before augmentation, represented as [x1, y1, x2, y2].
        box2 (numpy.ndarray): The 4,n bounding box after augmentation, represented as [x1, y1, x2, y2].
        wh_thr (float, optional): The width and height threshold in pixels. Default is 2.
        ar_thr (float, optional): The aspect ratio threshold. Default is 100.
        area_thr (float, optional): The area ratio threshold. Default is 0.1.
        eps (float, optional): A small epsilon value to prevent division by zero. Default is 1e-16.

    Returns:
        (numpy.ndarray): A boolean array indicating which boxes are candidates based on the given thresholds.
    """
    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
    ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates



ultralytics.data.augment.RandomHSV

Esta clase se encarga de realizar ajustes aleatorios en los canales Tono, Saturación y Valor (HSV) de una imagen.

Los ajustes son aleatorios, pero dentro de los límites establecidos por hgain, sgain y vgain.

Código fuente en ultralytics/data/augment.py
class RandomHSV:
    """
    This class is responsible for performing random adjustments to the Hue, Saturation, and Value (HSV) channels of an
    image.

    The adjustments are random but within limits set by hgain, sgain, and vgain.
    """

    def __init__(self, hgain=0.5, sgain=0.5, vgain=0.5) -> None:
        """
        Initialize RandomHSV class with gains for each HSV channel.

        Args:
            hgain (float, optional): Maximum variation for hue. Default is 0.5.
            sgain (float, optional): Maximum variation for saturation. Default is 0.5.
            vgain (float, optional): Maximum variation for value. Default is 0.5.
        """
        self.hgain = hgain
        self.sgain = sgain
        self.vgain = vgain

    def __call__(self, labels):
        """
        Applies random HSV augmentation to an image within the predefined limits.

        The modified image replaces the original image in the input 'labels' dict.
        """
        img = labels["img"]
        if self.hgain or self.sgain or self.vgain:
            r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain] + 1  # random gains
            hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
            dtype = img.dtype  # uint8

            x = np.arange(0, 256, dtype=r.dtype)
            lut_hue = ((x * r[0]) % 180).astype(dtype)
            lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
            lut_val = np.clip(x * r[2], 0, 255).astype(dtype)

            im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
            cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed
        return labels

__call__(labels)

Aplica un aumento HSV aleatorio a una imagen dentro de los límites predefinidos.

La imagen modificada sustituye a la imagen original en el dictado de entrada "etiquetas".

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """
    Applies random HSV augmentation to an image within the predefined limits.

    The modified image replaces the original image in the input 'labels' dict.
    """
    img = labels["img"]
    if self.hgain or self.sgain or self.vgain:
        r = np.random.uniform(-1, 1, 3) * [self.hgain, self.sgain, self.vgain] + 1  # random gains
        hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
        dtype = img.dtype  # uint8

        x = np.arange(0, 256, dtype=r.dtype)
        lut_hue = ((x * r[0]) % 180).astype(dtype)
        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)

        im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
        cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed
    return labels

__init__(hgain=0.5, sgain=0.5, vgain=0.5)

Inicializa la clase RandomHSV con ganancias para cada canal HSV.

Par√°metros:

Nombre Tipo Descripción Por defecto
hgain float

Variación máxima del tono. Por defecto es 0,5.

0.5
sgain float

Variación máxima de la saturación. Por defecto es 0,5.

0.5
vgain float

Variación máxima del valor. Por defecto es 0,5.

0.5
Código fuente en ultralytics/data/augment.py
def __init__(self, hgain=0.5, sgain=0.5, vgain=0.5) -> None:
    """
    Initialize RandomHSV class with gains for each HSV channel.

    Args:
        hgain (float, optional): Maximum variation for hue. Default is 0.5.
        sgain (float, optional): Maximum variation for saturation. Default is 0.5.
        vgain (float, optional): Maximum variation for value. Default is 0.5.
    """
    self.hgain = hgain
    self.sgain = sgain
    self.vgain = vgain



ultralytics.data.augment.RandomFlip

Aplica un volteo horizontal o vertical aleatorio a una imagen con una probabilidad dada.

Actualiza también cualquier instancia (cuadros delimitadores, puntos clave, etc.) en consecuencia.

Código fuente en ultralytics/data/augment.py
class RandomFlip:
    """
    Applies a random horizontal or vertical flip to an image with a given probability.

    Also updates any instances (bounding boxes, keypoints, etc.) accordingly.
    """

    def __init__(self, p=0.5, direction="horizontal", flip_idx=None) -> None:
        """
        Initializes the RandomFlip class with probability and direction.

        Args:
            p (float, optional): The probability of applying the flip. Must be between 0 and 1. Default is 0.5.
            direction (str, optional): The direction to apply the flip. Must be 'horizontal' or 'vertical'.
                Default is 'horizontal'.
            flip_idx (array-like, optional): Index mapping for flipping keypoints, if any.
        """
        assert direction in {"horizontal", "vertical"}, f"Support direction `horizontal` or `vertical`, got {direction}"
        assert 0 <= p <= 1.0

        self.p = p
        self.direction = direction
        self.flip_idx = flip_idx

    def __call__(self, labels):
        """
        Applies random flip to an image and updates any instances like bounding boxes or keypoints accordingly.

        Args:
            labels (dict): A dictionary containing the keys 'img' and 'instances'. 'img' is the image to be flipped.
                           'instances' is an object containing bounding boxes and optionally keypoints.

        Returns:
            (dict): The same dict with the flipped image and updated instances under the 'img' and 'instances' keys.
        """
        img = labels["img"]
        instances = labels.pop("instances")
        instances.convert_bbox(format="xywh")
        h, w = img.shape[:2]
        h = 1 if instances.normalized else h
        w = 1 if instances.normalized else w

        # Flip up-down
        if self.direction == "vertical" and random.random() < self.p:
            img = np.flipud(img)
            instances.flipud(h)
        if self.direction == "horizontal" and random.random() < self.p:
            img = np.fliplr(img)
            instances.fliplr(w)
            # For keypoints
            if self.flip_idx is not None and instances.keypoints is not None:
                instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
        labels["img"] = np.ascontiguousarray(img)
        labels["instances"] = instances
        return labels

__call__(labels)

Aplica un volteo aleatorio a una imagen y actualiza en consecuencia cualquier instancia, como cuadros delimitadores o puntos clave.

Par√°metros:

Nombre Tipo Descripción Por defecto
labels dict

Un diccionario que contiene las claves 'img' e 'instancias'. img' es la imagen que se va a voltear. instancias' es un objeto que contiene cajas delimitadoras y, opcionalmente, puntos clave.

necesario

Devuelve:

Tipo Descripción
dict

Lo mismo dicta con la imagen volteada y las instancias actualizadas bajo las claves 'img' e 'instancias'.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """
    Applies random flip to an image and updates any instances like bounding boxes or keypoints accordingly.

    Args:
        labels (dict): A dictionary containing the keys 'img' and 'instances'. 'img' is the image to be flipped.
                       'instances' is an object containing bounding boxes and optionally keypoints.

    Returns:
        (dict): The same dict with the flipped image and updated instances under the 'img' and 'instances' keys.
    """
    img = labels["img"]
    instances = labels.pop("instances")
    instances.convert_bbox(format="xywh")
    h, w = img.shape[:2]
    h = 1 if instances.normalized else h
    w = 1 if instances.normalized else w

    # Flip up-down
    if self.direction == "vertical" and random.random() < self.p:
        img = np.flipud(img)
        instances.flipud(h)
    if self.direction == "horizontal" and random.random() < self.p:
        img = np.fliplr(img)
        instances.fliplr(w)
        # For keypoints
        if self.flip_idx is not None and instances.keypoints is not None:
            instances.keypoints = np.ascontiguousarray(instances.keypoints[:, self.flip_idx, :])
    labels["img"] = np.ascontiguousarray(img)
    labels["instances"] = instances
    return labels

__init__(p=0.5, direction='horizontal', flip_idx=None)

Inicializa la clase RandomFlip con probabilidad y dirección.

Par√°metros:

Nombre Tipo Descripción Por defecto
p float

La probabilidad de aplicar el volteo. Debe estar entre 0 y 1. Por defecto es 0,5.

0.5
direction str

La dirección para aplicar el volteo. Debe ser "horizontal" o "vertical". Por defecto es "horizontal".

'horizontal'
flip_idx array - like

Asignación de índices para voltear los puntos clave, si existe.

None
Código fuente en ultralytics/data/augment.py
def __init__(self, p=0.5, direction="horizontal", flip_idx=None) -> None:
    """
    Initializes the RandomFlip class with probability and direction.

    Args:
        p (float, optional): The probability of applying the flip. Must be between 0 and 1. Default is 0.5.
        direction (str, optional): The direction to apply the flip. Must be 'horizontal' or 'vertical'.
            Default is 'horizontal'.
        flip_idx (array-like, optional): Index mapping for flipping keypoints, if any.
    """
    assert direction in {"horizontal", "vertical"}, f"Support direction `horizontal` or `vertical`, got {direction}"
    assert 0 <= p <= 1.0

    self.p = p
    self.direction = direction
    self.flip_idx = flip_idx



ultralytics.data.augment.LetterBox

Redimensiona la imagen y el relleno para la detección, la segmentación de instancias y la pose.

Código fuente en ultralytics/data/augment.py
class LetterBox:
    """Resize image and padding for detection, instance segmentation, pose."""

    def __init__(self, new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, center=True, stride=32):
        """Initialize LetterBox object with specific parameters."""
        self.new_shape = new_shape
        self.auto = auto
        self.scaleFill = scaleFill
        self.scaleup = scaleup
        self.stride = stride
        self.center = center  # Put the image in the middle or top-left

    def __call__(self, labels=None, image=None):
        """Return updated labels and image with added border."""
        if labels is None:
            labels = {}
        img = labels.get("img") if image is None else image
        shape = img.shape[:2]  # current shape [height, width]
        new_shape = labels.pop("rect_shape", self.new_shape)
        if isinstance(new_shape, int):
            new_shape = (new_shape, new_shape)

        # Scale ratio (new / old)
        r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
        if not self.scaleup:  # only scale down, do not scale up (for better val mAP)
            r = min(r, 1.0)

        # Compute padding
        ratio = r, r  # width, height ratios
        new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
        dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
        if self.auto:  # minimum rectangle
            dw, dh = np.mod(dw, self.stride), np.mod(dh, self.stride)  # wh padding
        elif self.scaleFill:  # stretch
            dw, dh = 0.0, 0.0
            new_unpad = (new_shape[1], new_shape[0])
            ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

        if self.center:
            dw /= 2  # divide padding into 2 sides
            dh /= 2

        if shape[::-1] != new_unpad:  # resize
            img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
        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))
        img = cv2.copyMakeBorder(
            img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)
        )  # add border
        if labels.get("ratio_pad"):
            labels["ratio_pad"] = (labels["ratio_pad"], (left, top))  # for evaluation

        if len(labels):
            labels = self._update_labels(labels, ratio, dw, dh)
            labels["img"] = img
            labels["resized_shape"] = new_shape
            return labels
        else:
            return img

    def _update_labels(self, labels, ratio, padw, padh):
        """Update labels."""
        labels["instances"].convert_bbox(format="xyxy")
        labels["instances"].denormalize(*labels["img"].shape[:2][::-1])
        labels["instances"].scale(*ratio)
        labels["instances"].add_padding(padw, padh)
        return labels

__call__(labels=None, image=None)

Devuelve las etiquetas actualizadas y la imagen con el borde a√Īadido.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels=None, image=None):
    """Return updated labels and image with added border."""
    if labels is None:
        labels = {}
    img = labels.get("img") if image is None else image
    shape = img.shape[:2]  # current shape [height, width]
    new_shape = labels.pop("rect_shape", self.new_shape)
    if isinstance(new_shape, int):
        new_shape = (new_shape, new_shape)

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    if not self.scaleup:  # only scale down, do not scale up (for better val mAP)
        r = min(r, 1.0)

    # Compute padding
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
    if self.auto:  # minimum rectangle
        dw, dh = np.mod(dw, self.stride), np.mod(dh, self.stride)  # wh padding
    elif self.scaleFill:  # stretch
        dw, dh = 0.0, 0.0
        new_unpad = (new_shape[1], new_shape[0])
        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

    if self.center:
        dw /= 2  # divide padding into 2 sides
        dh /= 2

    if shape[::-1] != new_unpad:  # resize
        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
    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))
    img = cv2.copyMakeBorder(
        img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)
    )  # add border
    if labels.get("ratio_pad"):
        labels["ratio_pad"] = (labels["ratio_pad"], (left, top))  # for evaluation

    if len(labels):
        labels = self._update_labels(labels, ratio, dw, dh)
        labels["img"] = img
        labels["resized_shape"] = new_shape
        return labels
    else:
        return img

__init__(new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, center=True, stride=32)

Inicializa el objeto Buzón con parámetros específicos.

Código fuente en ultralytics/data/augment.py
def __init__(self, new_shape=(640, 640), auto=False, scaleFill=False, scaleup=True, center=True, stride=32):
    """Initialize LetterBox object with specific parameters."""
    self.new_shape = new_shape
    self.auto = auto
    self.scaleFill = scaleFill
    self.scaleup = scaleup
    self.stride = stride
    self.center = center  # Put the image in the middle or top-left



ultralytics.data.augment.CopyPaste

Implementa el aumento Copiar-Pegar descrito en el documento https://arxiv.org/abs/2012.07177. Esta clase es responsable de aplicar el aumento Copy-Paste a las im√°genes y a sus instancias correspondientes.

Código fuente en ultralytics/data/augment.py
class CopyPaste:
    """
    Implements the Copy-Paste augmentation as described in the paper https://arxiv.org/abs/2012.07177. This class is
    responsible for applying the Copy-Paste augmentation on images and their corresponding instances.
    """

    def __init__(self, p=0.5) -> None:
        """
        Initializes the CopyPaste class with a given probability.

        Args:
            p (float, optional): The probability of applying the Copy-Paste augmentation. Must be between 0 and 1.
                                 Default is 0.5.
        """
        self.p = p

    def __call__(self, labels):
        """
        Applies the Copy-Paste augmentation to the given image and instances.

        Args:
            labels (dict): A dictionary containing:
                           - 'img': The image to augment.
                           - 'cls': Class labels associated with the instances.
                           - 'instances': Object containing bounding boxes, and optionally, keypoints and segments.

        Returns:
            (dict): Dict with augmented image and updated instances under the 'img', 'cls', and 'instances' keys.

        Notes:
            1. Instances are expected to have 'segments' as one of their attributes for this augmentation to work.
            2. This method modifies the input dictionary 'labels' in place.
        """
        im = labels["img"]
        cls = labels["cls"]
        h, w = im.shape[:2]
        instances = labels.pop("instances")
        instances.convert_bbox(format="xyxy")
        instances.denormalize(w, h)
        if self.p and len(instances.segments):
            n = len(instances)
            _, w, _ = im.shape  # height, width, channels
            im_new = np.zeros(im.shape, np.uint8)

            # Calculate ioa first then select indexes randomly
            ins_flip = deepcopy(instances)
            ins_flip.fliplr(w)

            ioa = bbox_ioa(ins_flip.bboxes, instances.bboxes)  # intersection over area, (N, M)
            indexes = np.nonzero((ioa < 0.30).all(1))[0]  # (N, )
            n = len(indexes)
            for j in random.sample(list(indexes), k=round(self.p * n)):
                cls = np.concatenate((cls, cls[[j]]), axis=0)
                instances = Instances.concatenate((instances, ins_flip[[j]]), axis=0)
                cv2.drawContours(im_new, instances.segments[[j]].astype(np.int32), -1, (1, 1, 1), cv2.FILLED)

            result = cv2.flip(im, 1)  # augment segments (flip left-right)
            i = cv2.flip(im_new, 1).astype(bool)
            im[i] = result[i]

        labels["img"] = im
        labels["cls"] = cls
        labels["instances"] = instances
        return labels

__call__(labels)

Aplica el aumento Copiar-Pegar a la imagen y a las instancias dadas.

Par√°metros:

Nombre Tipo Descripción Por defecto
labels dict

Un diccionario que contiene: - 'img': La imagen a aumentar. - 'cls': Las etiquetas de clase asociadas a las instancias. - 'instancias': Objeto que contiene cajas delimitadoras y, opcionalmente, puntos clave y segmentos.

necesario

Devuelve:

Tipo Descripción
dict

Dict con imagen aumentada e instancias actualizadas bajo las claves 'img', 'cls' e 'instancias'.

Notas
  1. Se espera que las instancias tengan "segmentos" como uno de sus atributos para que funcione este aumento.
  2. Este método modifica el diccionario de entrada "etiquetas" en su lugar.
Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """
    Applies the Copy-Paste augmentation to the given image and instances.

    Args:
        labels (dict): A dictionary containing:
                       - 'img': The image to augment.
                       - 'cls': Class labels associated with the instances.
                       - 'instances': Object containing bounding boxes, and optionally, keypoints and segments.

    Returns:
        (dict): Dict with augmented image and updated instances under the 'img', 'cls', and 'instances' keys.

    Notes:
        1. Instances are expected to have 'segments' as one of their attributes for this augmentation to work.
        2. This method modifies the input dictionary 'labels' in place.
    """
    im = labels["img"]
    cls = labels["cls"]
    h, w = im.shape[:2]
    instances = labels.pop("instances")
    instances.convert_bbox(format="xyxy")
    instances.denormalize(w, h)
    if self.p and len(instances.segments):
        n = len(instances)
        _, w, _ = im.shape  # height, width, channels
        im_new = np.zeros(im.shape, np.uint8)

        # Calculate ioa first then select indexes randomly
        ins_flip = deepcopy(instances)
        ins_flip.fliplr(w)

        ioa = bbox_ioa(ins_flip.bboxes, instances.bboxes)  # intersection over area, (N, M)
        indexes = np.nonzero((ioa < 0.30).all(1))[0]  # (N, )
        n = len(indexes)
        for j in random.sample(list(indexes), k=round(self.p * n)):
            cls = np.concatenate((cls, cls[[j]]), axis=0)
            instances = Instances.concatenate((instances, ins_flip[[j]]), axis=0)
            cv2.drawContours(im_new, instances.segments[[j]].astype(np.int32), -1, (1, 1, 1), cv2.FILLED)

        result = cv2.flip(im, 1)  # augment segments (flip left-right)
        i = cv2.flip(im_new, 1).astype(bool)
        im[i] = result[i]

    labels["img"] = im
    labels["cls"] = cls
    labels["instances"] = instances
    return labels

__init__(p=0.5)

Inicializa la clase CopyPaste con una probabilidad dada.

Par√°metros:

Nombre Tipo Descripción Por defecto
p float

La probabilidad de aplicar el aumento Copiar-Pegar. Debe estar entre 0 y 1. Por defecto es 0,5.

0.5
Código fuente en ultralytics/data/augment.py
def __init__(self, p=0.5) -> None:
    """
    Initializes the CopyPaste class with a given probability.

    Args:
        p (float, optional): The probability of applying the Copy-Paste augmentation. Must be between 0 and 1.
                             Default is 0.5.
    """
    self.p = p



ultralytics.data.augment.Albumentations

Transformaciones de las albumentaciones.

Opcional, desinstala el paquete para desactivarlo. Aplica Desenfoque, Desenfoque medio, convertir a escala de grises, Contraste limitado adaptativo ecualización de histograma, cambio aleatorio de brillo y contraste, RandomGamma y reducción de la calidad de imagen por compresión.

Código fuente en ultralytics/data/augment.py
class Albumentations:
    """
    Albumentations transformations.

    Optional, uninstall package to disable. Applies Blur, Median Blur, convert to grayscale, Contrast Limited Adaptive
    Histogram Equalization, random change of brightness and contrast, RandomGamma and lowering of image quality by
    compression.
    """

    def __init__(self, p=1.0):
        """Initialize the transform object for YOLO bbox formatted params."""
        self.p = p
        self.transform = None
        prefix = colorstr("albumentations: ")

        try:
            import albumentations as A

            check_version(A.__version__, "1.0.3", hard=True)  # version requirement

            # List of possible spatial transforms
            spatial_transforms = {
                "Affine",
                "BBoxSafeRandomCrop",
                "CenterCrop",
                "CoarseDropout",
                "Crop",
                "CropAndPad",
                "CropNonEmptyMaskIfExists",
                "D4",
                "ElasticTransform",
                "Flip",
                "GridDistortion",
                "GridDropout",
                "HorizontalFlip",
                "Lambda",
                "LongestMaxSize",
                "MaskDropout",
                "MixUp",
                "Morphological",
                "NoOp",
                "OpticalDistortion",
                "PadIfNeeded",
                "Perspective",
                "PiecewiseAffine",
                "PixelDropout",
                "RandomCrop",
                "RandomCropFromBorders",
                "RandomGridShuffle",
                "RandomResizedCrop",
                "RandomRotate90",
                "RandomScale",
                "RandomSizedBBoxSafeCrop",
                "RandomSizedCrop",
                "Resize",
                "Rotate",
                "SafeRotate",
                "ShiftScaleRotate",
                "SmallestMaxSize",
                "Transpose",
                "VerticalFlip",
                "XYMasking",
            }  # from https://albumentations.ai/docs/getting_started/transforms_and_targets/#spatial-level-transforms

            # Transforms
            T = [
                A.Blur(p=0.01),
                A.MedianBlur(p=0.01),
                A.ToGray(p=0.01),
                A.CLAHE(p=0.01),
                A.RandomBrightnessContrast(p=0.0),
                A.RandomGamma(p=0.0),
                A.ImageCompression(quality_lower=75, p=0.0),
            ]

            # Compose transforms
            self.contains_spatial = any(transform.__class__.__name__ in spatial_transforms for transform in T)
            self.transform = (
                A.Compose(T, bbox_params=A.BboxParams(format="yolo", label_fields=["class_labels"]))
                if self.contains_spatial
                else A.Compose(T)
            )
            LOGGER.info(prefix + ", ".join(f"{x}".replace("always_apply=False, ", "") for x in T if x.p))
        except ImportError:  # package not installed, skip
            pass
        except Exception as e:
            LOGGER.info(f"{prefix}{e}")

    def __call__(self, labels):
        """Generates object detections and returns a dictionary with detection results."""
        if self.transform is None or random.random() > self.p:
            return labels

        if self.contains_spatial:
            cls = labels["cls"]
            if len(cls):
                im = labels["img"]
                labels["instances"].convert_bbox("xywh")
                labels["instances"].normalize(*im.shape[:2][::-1])
                bboxes = labels["instances"].bboxes
                # TODO: add supports of segments and keypoints
                new = self.transform(image=im, bboxes=bboxes, class_labels=cls)  # transformed
                if len(new["class_labels"]) > 0:  # skip update if no bbox in new im
                    labels["img"] = new["image"]
                    labels["cls"] = np.array(new["class_labels"])
                    bboxes = np.array(new["bboxes"], dtype=np.float32)
                labels["instances"].update(bboxes=bboxes)
        else:
            labels["img"] = self.transform(image=labels["img"])["image"]  # transformed

        return labels

__call__(labels)

Genera detecciones de objetos y devuelve un diccionario con los resultados de la detección.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """Generates object detections and returns a dictionary with detection results."""
    if self.transform is None or random.random() > self.p:
        return labels

    if self.contains_spatial:
        cls = labels["cls"]
        if len(cls):
            im = labels["img"]
            labels["instances"].convert_bbox("xywh")
            labels["instances"].normalize(*im.shape[:2][::-1])
            bboxes = labels["instances"].bboxes
            # TODO: add supports of segments and keypoints
            new = self.transform(image=im, bboxes=bboxes, class_labels=cls)  # transformed
            if len(new["class_labels"]) > 0:  # skip update if no bbox in new im
                labels["img"] = new["image"]
                labels["cls"] = np.array(new["class_labels"])
                bboxes = np.array(new["bboxes"], dtype=np.float32)
            labels["instances"].update(bboxes=bboxes)
    else:
        labels["img"] = self.transform(image=labels["img"])["image"]  # transformed

    return labels

__init__(p=1.0)

Inicializa el objeto de transformación para los parámetros con formato YOLO bbox.

Código fuente en ultralytics/data/augment.py
def __init__(self, p=1.0):
    """Initialize the transform object for YOLO bbox formatted params."""
    self.p = p
    self.transform = None
    prefix = colorstr("albumentations: ")

    try:
        import albumentations as A

        check_version(A.__version__, "1.0.3", hard=True)  # version requirement

        # List of possible spatial transforms
        spatial_transforms = {
            "Affine",
            "BBoxSafeRandomCrop",
            "CenterCrop",
            "CoarseDropout",
            "Crop",
            "CropAndPad",
            "CropNonEmptyMaskIfExists",
            "D4",
            "ElasticTransform",
            "Flip",
            "GridDistortion",
            "GridDropout",
            "HorizontalFlip",
            "Lambda",
            "LongestMaxSize",
            "MaskDropout",
            "MixUp",
            "Morphological",
            "NoOp",
            "OpticalDistortion",
            "PadIfNeeded",
            "Perspective",
            "PiecewiseAffine",
            "PixelDropout",
            "RandomCrop",
            "RandomCropFromBorders",
            "RandomGridShuffle",
            "RandomResizedCrop",
            "RandomRotate90",
            "RandomScale",
            "RandomSizedBBoxSafeCrop",
            "RandomSizedCrop",
            "Resize",
            "Rotate",
            "SafeRotate",
            "ShiftScaleRotate",
            "SmallestMaxSize",
            "Transpose",
            "VerticalFlip",
            "XYMasking",
        }  # from https://albumentations.ai/docs/getting_started/transforms_and_targets/#spatial-level-transforms

        # Transforms
        T = [
            A.Blur(p=0.01),
            A.MedianBlur(p=0.01),
            A.ToGray(p=0.01),
            A.CLAHE(p=0.01),
            A.RandomBrightnessContrast(p=0.0),
            A.RandomGamma(p=0.0),
            A.ImageCompression(quality_lower=75, p=0.0),
        ]

        # Compose transforms
        self.contains_spatial = any(transform.__class__.__name__ in spatial_transforms for transform in T)
        self.transform = (
            A.Compose(T, bbox_params=A.BboxParams(format="yolo", label_fields=["class_labels"]))
            if self.contains_spatial
            else A.Compose(T)
        )
        LOGGER.info(prefix + ", ".join(f"{x}".replace("always_apply=False, ", "") for x in T if x.p))
    except ImportError:  # package not installed, skip
        pass
    except Exception as e:
        LOGGER.info(f"{prefix}{e}")



ultralytics.data.augment.Format

Formatea anotaciones de imágenes para tareas de detección de objetos, segmentación de instancias y estimación de poses. La clase estandariza las anotaciones de imágenes e instancias que utilizará la clase collate_fn en PyTorch DataLoader.

Atributos:

Nombre Tipo Descripción
bbox_format str

Formato de las cajas delimitadoras. Por defecto es 'xywh'.

normalize bool

Si se normalizan los cuadros delimitadores. Por defecto es Verdadero.

return_mask bool

Devuelve máscaras de instancia para la segmentación. Por defecto es Falso.

return_keypoint bool

Devuelve los puntos clave para la estimación de la pose. Por defecto es Falso.

mask_ratio int

Relación de reducción de la muestra de las máscaras. Por defecto es 4.

mask_overlap bool

Si se solapan las m√°scaras. Por defecto es Verdadero.

batch_idx bool

Mantener índices por lotes. Por defecto es Verdadero.

bgr float

La probabilidad de devolver im√°genes BGR. Por defecto es 0,0.

Código fuente en ultralytics/data/augment.py
class Format:
    """
    Formats image annotations for object detection, instance segmentation, and pose estimation tasks. The class
    standardizes the image and instance annotations to be used by the `collate_fn` in PyTorch DataLoader.

    Attributes:
        bbox_format (str): Format for bounding boxes. Default is 'xywh'.
        normalize (bool): Whether to normalize bounding boxes. Default is True.
        return_mask (bool): Return instance masks for segmentation. Default is False.
        return_keypoint (bool): Return keypoints for pose estimation. Default is False.
        mask_ratio (int): Downsample ratio for masks. Default is 4.
        mask_overlap (bool): Whether to overlap masks. Default is True.
        batch_idx (bool): Keep batch indexes. Default is True.
        bgr (float): The probability to return BGR images. Default is 0.0.
    """

    def __init__(
        self,
        bbox_format="xywh",
        normalize=True,
        return_mask=False,
        return_keypoint=False,
        return_obb=False,
        mask_ratio=4,
        mask_overlap=True,
        batch_idx=True,
        bgr=0.0,
    ):
        """Initializes the Format class with given parameters."""
        self.bbox_format = bbox_format
        self.normalize = normalize
        self.return_mask = return_mask  # set False when training detection only
        self.return_keypoint = return_keypoint
        self.return_obb = return_obb
        self.mask_ratio = mask_ratio
        self.mask_overlap = mask_overlap
        self.batch_idx = batch_idx  # keep the batch indexes
        self.bgr = bgr

    def __call__(self, labels):
        """Return formatted image, classes, bounding boxes & keypoints to be used by 'collate_fn'."""
        img = labels.pop("img")
        h, w = img.shape[:2]
        cls = labels.pop("cls")
        instances = labels.pop("instances")
        instances.convert_bbox(format=self.bbox_format)
        instances.denormalize(w, h)
        nl = len(instances)

        if self.return_mask:
            if nl:
                masks, instances, cls = self._format_segments(instances, cls, w, h)
                masks = torch.from_numpy(masks)
            else:
                masks = torch.zeros(
                    1 if self.mask_overlap else nl, img.shape[0] // self.mask_ratio, img.shape[1] // self.mask_ratio
                )
            labels["masks"] = masks
        labels["img"] = self._format_img(img)
        labels["cls"] = torch.from_numpy(cls) if nl else torch.zeros(nl)
        labels["bboxes"] = torch.from_numpy(instances.bboxes) if nl else torch.zeros((nl, 4))
        if self.return_keypoint:
            labels["keypoints"] = torch.from_numpy(instances.keypoints)
            if self.normalize:
                labels["keypoints"][..., 0] /= w
                labels["keypoints"][..., 1] /= h
        if self.return_obb:
            labels["bboxes"] = (
                xyxyxyxy2xywhr(torch.from_numpy(instances.segments)) if len(instances.segments) else torch.zeros((0, 5))
            )
        # NOTE: need to normalize obb in xywhr format for width-height consistency
        if self.normalize:
            labels["bboxes"][:, [0, 2]] /= w
            labels["bboxes"][:, [1, 3]] /= h
        # Then we can use collate_fn
        if self.batch_idx:
            labels["batch_idx"] = torch.zeros(nl)
        return labels

    def _format_img(self, img):
        """Format the image for YOLO from Numpy array to PyTorch tensor."""
        if len(img.shape) < 3:
            img = np.expand_dims(img, -1)
        img = img.transpose(2, 0, 1)
        img = np.ascontiguousarray(img[::-1] if random.uniform(0, 1) > self.bgr else img)
        img = torch.from_numpy(img)
        return img

    def _format_segments(self, instances, cls, w, h):
        """Convert polygon points to bitmap."""
        segments = instances.segments
        if self.mask_overlap:
            masks, sorted_idx = polygons2masks_overlap((h, w), segments, downsample_ratio=self.mask_ratio)
            masks = masks[None]  # (640, 640) -> (1, 640, 640)
            instances = instances[sorted_idx]
            cls = cls[sorted_idx]
        else:
            masks = polygons2masks((h, w), segments, color=1, downsample_ratio=self.mask_ratio)

        return masks, instances, cls

__call__(labels)

Devuelve la imagen formateada, las clases, las cajas delimitadoras y los puntos clave que utilizar√° 'collate_fn'.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels):
    """Return formatted image, classes, bounding boxes & keypoints to be used by 'collate_fn'."""
    img = labels.pop("img")
    h, w = img.shape[:2]
    cls = labels.pop("cls")
    instances = labels.pop("instances")
    instances.convert_bbox(format=self.bbox_format)
    instances.denormalize(w, h)
    nl = len(instances)

    if self.return_mask:
        if nl:
            masks, instances, cls = self._format_segments(instances, cls, w, h)
            masks = torch.from_numpy(masks)
        else:
            masks = torch.zeros(
                1 if self.mask_overlap else nl, img.shape[0] // self.mask_ratio, img.shape[1] // self.mask_ratio
            )
        labels["masks"] = masks
    labels["img"] = self._format_img(img)
    labels["cls"] = torch.from_numpy(cls) if nl else torch.zeros(nl)
    labels["bboxes"] = torch.from_numpy(instances.bboxes) if nl else torch.zeros((nl, 4))
    if self.return_keypoint:
        labels["keypoints"] = torch.from_numpy(instances.keypoints)
        if self.normalize:
            labels["keypoints"][..., 0] /= w
            labels["keypoints"][..., 1] /= h
    if self.return_obb:
        labels["bboxes"] = (
            xyxyxyxy2xywhr(torch.from_numpy(instances.segments)) if len(instances.segments) else torch.zeros((0, 5))
        )
    # NOTE: need to normalize obb in xywhr format for width-height consistency
    if self.normalize:
        labels["bboxes"][:, [0, 2]] /= w
        labels["bboxes"][:, [1, 3]] /= h
    # Then we can use collate_fn
    if self.batch_idx:
        labels["batch_idx"] = torch.zeros(nl)
    return labels

__init__(bbox_format='xywh', normalize=True, return_mask=False, return_keypoint=False, return_obb=False, mask_ratio=4, mask_overlap=True, batch_idx=True, bgr=0.0)

Inicializa la clase Formato con los par√°metros dados.

Código fuente en ultralytics/data/augment.py
def __init__(
    self,
    bbox_format="xywh",
    normalize=True,
    return_mask=False,
    return_keypoint=False,
    return_obb=False,
    mask_ratio=4,
    mask_overlap=True,
    batch_idx=True,
    bgr=0.0,
):
    """Initializes the Format class with given parameters."""
    self.bbox_format = bbox_format
    self.normalize = normalize
    self.return_mask = return_mask  # set False when training detection only
    self.return_keypoint = return_keypoint
    self.return_obb = return_obb
    self.mask_ratio = mask_ratio
    self.mask_overlap = mask_overlap
    self.batch_idx = batch_idx  # keep the batch indexes
    self.bgr = bgr



ultralytics.data.augment.RandomLoadText

Toma muestras aleatorias de textos positivos y negativos y actualiza los √≠ndices de clase en funci√≥n del n√ļmero de muestras.

Atributos:

Nombre Tipo Descripción
prompt_format str

Formato del mensaje. Por defecto es '{}'.

neg_samples tuple[int]

Un guardabosques para muestrear aleatoriamente textos negativos, Por defecto es (80, 80).

max_samples int

El n√ļmero m√°ximo de muestras de texto diferentes en una imagen, Por defecto es 80.

padding bool

Si se rellenan los textos con un m√°ximo de muestras. Por defecto es Falso.

padding_value str

El texto de relleno. Por defecto es "".

Código fuente en ultralytics/data/augment.py
class RandomLoadText:
    """
    Randomly sample positive texts and negative texts and update the class indices accordingly to the number of samples.

    Attributes:
        prompt_format (str): Format for prompt. Default is '{}'.
        neg_samples (tuple[int]): A ranger to randomly sample negative texts, Default is (80, 80).
        max_samples (int): The max number of different text samples in one image, Default is 80.
        padding (bool): Whether to pad texts to max_samples. Default is False.
        padding_value (str): The padding text. Default is "".
    """

    def __init__(
        self,
        prompt_format: str = "{}",
        neg_samples: Tuple[int, int] = (80, 80),
        max_samples: int = 80,
        padding: bool = False,
        padding_value: str = "",
    ) -> None:
        """Initializes the RandomLoadText class with given parameters."""
        self.prompt_format = prompt_format
        self.neg_samples = neg_samples
        self.max_samples = max_samples
        self.padding = padding
        self.padding_value = padding_value

    def __call__(self, labels: dict) -> dict:
        """Return updated classes and texts."""
        assert "texts" in labels, "No texts found in labels."
        class_texts = labels["texts"]
        num_classes = len(class_texts)
        cls = np.asarray(labels.pop("cls"), dtype=int)
        pos_labels = np.unique(cls).tolist()

        if len(pos_labels) > self.max_samples:
            pos_labels = set(random.sample(pos_labels, k=self.max_samples))

        neg_samples = min(min(num_classes, self.max_samples) - len(pos_labels), random.randint(*self.neg_samples))
        neg_labels = []
        for i in range(num_classes):
            if i not in pos_labels:
                neg_labels.append(i)
        neg_labels = random.sample(neg_labels, k=neg_samples)

        sampled_labels = pos_labels + neg_labels
        random.shuffle(sampled_labels)

        label2ids = {label: i for i, label in enumerate(sampled_labels)}
        valid_idx = np.zeros(len(labels["instances"]), dtype=bool)
        new_cls = []
        for i, label in enumerate(cls.squeeze(-1).tolist()):
            if label not in label2ids:
                continue
            valid_idx[i] = True
            new_cls.append([label2ids[label]])
        labels["instances"] = labels["instances"][valid_idx]
        labels["cls"] = np.array(new_cls)

        # Randomly select one prompt when there's more than one prompts
        texts = []
        for label in sampled_labels:
            prompts = class_texts[label]
            assert len(prompts) > 0
            prompt = self.prompt_format.format(prompts[random.randrange(len(prompts))])
            texts.append(prompt)

        if self.padding:
            valid_labels = len(pos_labels) + len(neg_labels)
            num_padding = self.max_samples - valid_labels
            if num_padding > 0:
                texts += [self.padding_value] * num_padding

        labels["texts"] = texts
        return labels

__call__(labels)

Devuelve las clases y textos actualizados.

Código fuente en ultralytics/data/augment.py
def __call__(self, labels: dict) -> dict:
    """Return updated classes and texts."""
    assert "texts" in labels, "No texts found in labels."
    class_texts = labels["texts"]
    num_classes = len(class_texts)
    cls = np.asarray(labels.pop("cls"), dtype=int)
    pos_labels = np.unique(cls).tolist()

    if len(pos_labels) > self.max_samples:
        pos_labels = set(random.sample(pos_labels, k=self.max_samples))

    neg_samples = min(min(num_classes, self.max_samples) - len(pos_labels), random.randint(*self.neg_samples))
    neg_labels = []
    for i in range(num_classes):
        if i not in pos_labels:
            neg_labels.append(i)
    neg_labels = random.sample(neg_labels, k=neg_samples)

    sampled_labels = pos_labels + neg_labels
    random.shuffle(sampled_labels)

    label2ids = {label: i for i, label in enumerate(sampled_labels)}
    valid_idx = np.zeros(len(labels["instances"]), dtype=bool)
    new_cls = []
    for i, label in enumerate(cls.squeeze(-1).tolist()):
        if label not in label2ids:
            continue
        valid_idx[i] = True
        new_cls.append([label2ids[label]])
    labels["instances"] = labels["instances"][valid_idx]
    labels["cls"] = np.array(new_cls)

    # Randomly select one prompt when there's more than one prompts
    texts = []
    for label in sampled_labels:
        prompts = class_texts[label]
        assert len(prompts) > 0
        prompt = self.prompt_format.format(prompts[random.randrange(len(prompts))])
        texts.append(prompt)

    if self.padding:
        valid_labels = len(pos_labels) + len(neg_labels)
        num_padding = self.max_samples - valid_labels
        if num_padding > 0:
            texts += [self.padding_value] * num_padding

    labels["texts"] = texts
    return labels

__init__(prompt_format='{}', neg_samples=(80, 80), max_samples=80, padding=False, padding_value='')

Inicializa la clase RandomLoadText con los par√°metros dados.

Código fuente en ultralytics/data/augment.py
def __init__(
    self,
    prompt_format: str = "{}",
    neg_samples: Tuple[int, int] = (80, 80),
    max_samples: int = 80,
    padding: bool = False,
    padding_value: str = "",
) -> None:
    """Initializes the RandomLoadText class with given parameters."""
    self.prompt_format = prompt_format
    self.neg_samples = neg_samples
    self.max_samples = max_samples
    self.padding = padding
    self.padding_value = padding_value



ultralytics.data.augment.ClassifyLetterBox

YOLOv8 Clase LetterBox para el preprocesamiento de im√°genes, dise√Īada para formar parte de una cadena de transformaci√≥n, p. ej, T.Componer([LetterBox(tama√Īo), ToTensor()]).

Atributos:

Nombre Tipo Descripción
h int

Altura objetivo de la imagen.

w int

Anchura objetivo de la imagen.

auto bool

Si es Verdadero, resuelve autom√°ticamente el lado corto utilizando la zancada.

stride int

El valor de la zancada, utilizado cuando "auto" es Verdadero.

Código fuente en ultralytics/data/augment.py
class ClassifyLetterBox:
    """
    YOLOv8 LetterBox class for image preprocessing, designed to be part of a transformation pipeline, e.g.,
    T.Compose([LetterBox(size), ToTensor()]).

    Attributes:
        h (int): Target height of the image.
        w (int): Target width of the image.
        auto (bool): If True, automatically solves for short side using stride.
        stride (int): The stride value, used when 'auto' is True.
    """

    def __init__(self, size=(640, 640), auto=False, stride=32):
        """
        Initializes the ClassifyLetterBox class with a target size, auto-flag, and stride.

        Args:
            size (Union[int, Tuple[int, int]]): The target dimensions (height, width) for the letterbox.
            auto (bool): If True, automatically calculates the short side based on stride.
            stride (int): The stride value, used when 'auto' is True.
        """
        super().__init__()
        self.h, self.w = (size, size) if isinstance(size, int) else size
        self.auto = auto  # pass max size integer, automatically solve for short side using stride
        self.stride = stride  # used with auto

    def __call__(self, im):
        """
        Resizes the image and pads it with a letterbox method.

        Args:
            im (numpy.ndarray): The input image as a numpy array of shape HWC.

        Returns:
            (numpy.ndarray): The letterboxed and resized image as a numpy array.
        """
        imh, imw = im.shape[:2]
        r = min(self.h / imh, self.w / imw)  # ratio of new/old dimensions
        h, w = round(imh * r), round(imw * r)  # resized image dimensions

        # Calculate padding dimensions
        hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else (self.h, self.w)
        top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)

        # Create padded image
        im_out = np.full((hs, ws, 3), 114, dtype=im.dtype)
        im_out[top : top + h, left : left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
        return im_out

__call__(im)

Cambia el tama√Īo de la imagen y la rellena con un m√©todo letterbox.

Par√°metros:

Nombre Tipo Descripción Por defecto
im ndarray

La imagen de entrada como una matriz numpy de forma HWC.

necesario

Devuelve:

Tipo Descripción
ndarray

La imagen recuadrada y redimensionada como una matriz numpy.

Código fuente en ultralytics/data/augment.py
def __call__(self, im):
    """
    Resizes the image and pads it with a letterbox method.

    Args:
        im (numpy.ndarray): The input image as a numpy array of shape HWC.

    Returns:
        (numpy.ndarray): The letterboxed and resized image as a numpy array.
    """
    imh, imw = im.shape[:2]
    r = min(self.h / imh, self.w / imw)  # ratio of new/old dimensions
    h, w = round(imh * r), round(imw * r)  # resized image dimensions

    # Calculate padding dimensions
    hs, ws = (math.ceil(x / self.stride) * self.stride for x in (h, w)) if self.auto else (self.h, self.w)
    top, left = round((hs - h) / 2 - 0.1), round((ws - w) / 2 - 0.1)

    # Create padded image
    im_out = np.full((hs, ws, 3), 114, dtype=im.dtype)
    im_out[top : top + h, left : left + w] = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
    return im_out

__init__(size=(640, 640), auto=False, stride=32)

Inicializa la clase ClassifyLetterBox con un tama√Īo objetivo, un auto-flag y un stride.

Par√°metros:

Nombre Tipo Descripción Por defecto
size Union[int, Tuple[int, int]]

Las dimensiones objetivo (alto, ancho) para el buzón.

(640, 640)
auto bool

Si es Verdadero, calcula autom√°ticamente el lado corto bas√°ndose en la zancada.

False
stride int

El valor de la zancada, utilizado cuando "auto" es Verdadero.

32
Código fuente en ultralytics/data/augment.py
def __init__(self, size=(640, 640), auto=False, stride=32):
    """
    Initializes the ClassifyLetterBox class with a target size, auto-flag, and stride.

    Args:
        size (Union[int, Tuple[int, int]]): The target dimensions (height, width) for the letterbox.
        auto (bool): If True, automatically calculates the short side based on stride.
        stride (int): The stride value, used when 'auto' is True.
    """
    super().__init__()
    self.h, self.w = (size, size) if isinstance(size, int) else size
    self.auto = auto  # pass max size integer, automatically solve for short side using stride
    self.stride = stride  # used with auto



ultralytics.data.augment.CenterCrop

YOLOv8 Clase CenterCrop para el preprocesamiento de im√°genes, dise√Īada para formar parte de una cadena de transformaci√≥n, p. ej, T.Componer([RecorteCentral(tama√Īo), ToTensor()]).

Código fuente en ultralytics/data/augment.py
class CenterCrop:
    """YOLOv8 CenterCrop class for image preprocessing, designed to be part of a transformation pipeline, e.g.,
    T.Compose([CenterCrop(size), ToTensor()]).
    """

    def __init__(self, size=640):
        """Converts an image from numpy array to PyTorch tensor."""
        super().__init__()
        self.h, self.w = (size, size) if isinstance(size, int) else size

    def __call__(self, im):
        """
        Resizes and crops the center of the image using a letterbox method.

        Args:
            im (numpy.ndarray): The input image as a numpy array of shape HWC.

        Returns:
            (numpy.ndarray): The center-cropped and resized image as a numpy array.
        """
        imh, imw = im.shape[:2]
        m = min(imh, imw)  # min dimension
        top, left = (imh - m) // 2, (imw - m) // 2
        return cv2.resize(im[top : top + m, left : left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR)

__call__(im)

Redimensiona y recorta el centro de la imagen utilizando un método letterbox.

Par√°metros:

Nombre Tipo Descripción Por defecto
im ndarray

La imagen de entrada como una matriz numpy de forma HWC.

necesario

Devuelve:

Tipo Descripción
ndarray

La imagen recortada por el centro y redimensionada como una matriz numpy.

Código fuente en ultralytics/data/augment.py
def __call__(self, im):
    """
    Resizes and crops the center of the image using a letterbox method.

    Args:
        im (numpy.ndarray): The input image as a numpy array of shape HWC.

    Returns:
        (numpy.ndarray): The center-cropped and resized image as a numpy array.
    """
    imh, imw = im.shape[:2]
    m = min(imh, imw)  # min dimension
    top, left = (imh - m) // 2, (imw - m) // 2
    return cv2.resize(im[top : top + m, left : left + m], (self.w, self.h), interpolation=cv2.INTER_LINEAR)

__init__(size=640)

Convierte una imagen de una matriz numpy a PyTorch tensor .

Código fuente en ultralytics/data/augment.py
def __init__(self, size=640):
    """Converts an image from numpy array to PyTorch tensor."""
    super().__init__()
    self.h, self.w = (size, size) if isinstance(size, int) else size



ultralytics.data.augment.ToTensor

YOLOv8 Clase ToTensor para el preprocesamiento de im√°genes, es decir, T.Compose([LetterBox(tama√Īo), ToTensor()]).

Código fuente en ultralytics/data/augment.py
class ToTensor:
    """YOLOv8 ToTensor class for image preprocessing, i.e., T.Compose([LetterBox(size), ToTensor()])."""

    def __init__(self, half=False):
        """Initialize YOLOv8 ToTensor object with optional half-precision support."""
        super().__init__()
        self.half = half

    def __call__(self, im):
        """
        Transforms an image from a numpy array to a PyTorch tensor, applying optional half-precision and normalization.

        Args:
            im (numpy.ndarray): Input image as a numpy array with shape (H, W, C) in BGR order.

        Returns:
            (torch.Tensor): The transformed image as a PyTorch tensor in float32 or float16, normalized to [0, 1].
        """
        im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1])  # HWC to CHW -> BGR to RGB -> contiguous
        im = torch.from_numpy(im)  # to torch
        im = im.half() if self.half else im.float()  # uint8 to fp16/32
        im /= 255.0  # 0-255 to 0.0-1.0
        return im

__call__(im)

Transforma una imagen de una matriz numpy a PyTorch tensor , aplicando media precisión y normalización opcionales.

Par√°metros:

Nombre Tipo Descripción Por defecto
im ndarray

Imagen de entrada como matriz numpy con forma (H, W, C) en orden BGR.

necesario

Devuelve:

Tipo Descripción
Tensor

La imagen transformada como PyTorch tensor en float32 o float16, normalizada a [0, 1].

Código fuente en ultralytics/data/augment.py
def __call__(self, im):
    """
    Transforms an image from a numpy array to a PyTorch tensor, applying optional half-precision and normalization.

    Args:
        im (numpy.ndarray): Input image as a numpy array with shape (H, W, C) in BGR order.

    Returns:
        (torch.Tensor): The transformed image as a PyTorch tensor in float32 or float16, normalized to [0, 1].
    """
    im = np.ascontiguousarray(im.transpose((2, 0, 1))[::-1])  # HWC to CHW -> BGR to RGB -> contiguous
    im = torch.from_numpy(im)  # to torch
    im = im.half() if self.half else im.float()  # uint8 to fp16/32
    im /= 255.0  # 0-255 to 0.0-1.0
    return im

__init__(half=False)

Inicializa el objeto YOLOv8 ToTensor con soporte opcional de media precisión.

Código fuente en ultralytics/data/augment.py
def __init__(self, half=False):
    """Initialize YOLOv8 ToTensor object with optional half-precision support."""
    super().__init__()
    self.half = half



ultralytics.data.augment.v8_transforms(dataset, imgsz, hyp, stretch=False)

Convierte las im√°genes a un tama√Īo adecuado para el entrenamiento YOLOv8 .

Código fuente en ultralytics/data/augment.py
def v8_transforms(dataset, imgsz, hyp, stretch=False):
    """Convert images to a size suitable for YOLOv8 training."""
    pre_transform = Compose(
        [
            Mosaic(dataset, imgsz=imgsz, p=hyp.mosaic),
            CopyPaste(p=hyp.copy_paste),
            RandomPerspective(
                degrees=hyp.degrees,
                translate=hyp.translate,
                scale=hyp.scale,
                shear=hyp.shear,
                perspective=hyp.perspective,
                pre_transform=None if stretch else LetterBox(new_shape=(imgsz, imgsz)),
            ),
        ]
    )
    flip_idx = dataset.data.get("flip_idx", [])  # for keypoints augmentation
    if dataset.use_keypoints:
        kpt_shape = dataset.data.get("kpt_shape", None)
        if len(flip_idx) == 0 and hyp.fliplr > 0.0:
            hyp.fliplr = 0.0
            LOGGER.warning("WARNING ‚ö†ÔłŹ No 'flip_idx' array defined in data.yaml, setting augmentation 'fliplr=0.0'")
        elif flip_idx and (len(flip_idx) != kpt_shape[0]):
            raise ValueError(f"data.yaml flip_idx={flip_idx} length must be equal to kpt_shape[0]={kpt_shape[0]}")

    return Compose(
        [
            pre_transform,
            MixUp(dataset, pre_transform=pre_transform, p=hyp.mixup),
            Albumentations(p=1.0),
            RandomHSV(hgain=hyp.hsv_h, sgain=hyp.hsv_s, vgain=hyp.hsv_v),
            RandomFlip(direction="vertical", p=hyp.flipud),
            RandomFlip(direction="horizontal", p=hyp.fliplr, flip_idx=flip_idx),
        ]
    )  # transforms



ultralytics.data.augment.classify_transforms(size=224, mean=DEFAULT_MEAN, std=DEFAULT_STD, interpolation=Image.BILINEAR, crop_fraction=DEFAULT_CROP_FRACTION)

Transformaciones de clasificación para evaluación/inferencia. Inspirado en timm/data/transforms_factory.py.

Par√°metros:

Nombre Tipo Descripción Por defecto
size int

Tama√Īo de la imagen

224
mean tuple

valores medios de los canales RGB

DEFAULT_MEAN
std tuple

valores est√°ndar de los canales RGB

DEFAULT_STD
interpolation InterpolationMode

Modo de interpolación. Por defecto es T.InterpolationMode.BILINEAR.

BILINEAR
crop_fraction float

fracción de imagen a recortar. por defecto es 1.0.

DEFAULT_CROP_FRACTION

Devuelve:

Tipo Descripción
Compose

torchvision transforma

Código fuente en ultralytics/data/augment.py
def classify_transforms(
    size=224,
    mean=DEFAULT_MEAN,
    std=DEFAULT_STD,
    interpolation=Image.BILINEAR,
    crop_fraction: float = DEFAULT_CROP_FRACTION,
):
    """
    Classification transforms for evaluation/inference. Inspired by timm/data/transforms_factory.py.

    Args:
        size (int): image size
        mean (tuple): mean values of RGB channels
        std (tuple): std values of RGB channels
        interpolation (T.InterpolationMode): interpolation mode. default is T.InterpolationMode.BILINEAR.
        crop_fraction (float): fraction of image to crop. default is 1.0.

    Returns:
        (T.Compose): torchvision transforms
    """
    import torchvision.transforms as T  # scope for faster 'import ultralytics'

    if isinstance(size, (tuple, list)):
        assert len(size) == 2
        scale_size = tuple(math.floor(x / crop_fraction) for x in size)
    else:
        scale_size = math.floor(size / crop_fraction)
        scale_size = (scale_size, scale_size)

    # Aspect ratio is preserved, crops center within image, no borders are added, image is lost
    if scale_size[0] == scale_size[1]:
        # Simple case, use torchvision built-in Resize with the shortest edge mode (scalar size arg)
        tfl = [T.Resize(scale_size[0], interpolation=interpolation)]
    else:
        # Resize the shortest edge to matching target dim for non-square target
        tfl = [T.Resize(scale_size)]
    tfl += [T.CenterCrop(size)]

    tfl += [
        T.ToTensor(),
        T.Normalize(
            mean=torch.tensor(mean),
            std=torch.tensor(std),
        ),
    ]

    return T.Compose(tfl)



ultralytics.data.augment.classify_augmentations(size=224, mean=DEFAULT_MEAN, std=DEFAULT_STD, scale=None, ratio=None, hflip=0.5, vflip=0.0, auto_augment=None, hsv_h=0.015, hsv_s=0.4, hsv_v=0.4, force_color_jitter=False, erasing=0.0, interpolation=Image.BILINEAR)

Transformaciones de clasificación con aumento para el entrenamiento. Inspirado en timm/data/transforms_factory.py.

Par√°metros:

Nombre Tipo Descripción Por defecto
size int

Tama√Īo de la imagen

224
scale tuple

rango de escala de la imagen. por defecto es (0.08, 1.0)

None
ratio tuple

rango de relación de aspecto de la imagen. por defecto es (3./4., 4./3.)

None
mean tuple

valores medios de los canales RGB

DEFAULT_MEAN
std tuple

valores est√°ndar de los canales RGB

DEFAULT_STD
hflip float

probabilidad de volteo horizontal

0.5
vflip float

probabilidad de volteo vertical

0.0
auto_augment str

Política de autoaumento. Puede ser "randaugment", "augmix", "autoaugment" o Ninguna.

None
hsv_h float

imagen Aumento HSV-Hue (fracción)

0.015
hsv_s float

imagen Aumento de la saturación HSV (fracción)

0.4
hsv_v float

imagen Aumento del valor HSV (fracción)

0.4
force_color_jitter bool

obligar a aplicar la fluctuación de color aunque esté activado el aumento automático

False
erasing float

probabilidad de borrado aleatorio

0.0
interpolation InterpolationMode

Modo de interpolación. Por defecto es T.InterpolationMode.BILINEAR.

BILINEAR

Devuelve:

Tipo Descripción
Compose

torchvision transforma

Código fuente en ultralytics/data/augment.py
def classify_augmentations(
    size=224,
    mean=DEFAULT_MEAN,
    std=DEFAULT_STD,
    scale=None,
    ratio=None,
    hflip=0.5,
    vflip=0.0,
    auto_augment=None,
    hsv_h=0.015,  # image HSV-Hue augmentation (fraction)
    hsv_s=0.4,  # image HSV-Saturation augmentation (fraction)
    hsv_v=0.4,  # image HSV-Value augmentation (fraction)
    force_color_jitter=False,
    erasing=0.0,
    interpolation=Image.BILINEAR,
):
    """
    Classification transforms with augmentation for training. Inspired by timm/data/transforms_factory.py.

    Args:
        size (int): image size
        scale (tuple): scale range of the image. default is (0.08, 1.0)
        ratio (tuple): aspect ratio range of the image. default is (3./4., 4./3.)
        mean (tuple): mean values of RGB channels
        std (tuple): std values of RGB channels
        hflip (float): probability of horizontal flip
        vflip (float): probability of vertical flip
        auto_augment (str): auto augmentation policy. can be 'randaugment', 'augmix', 'autoaugment' or None.
        hsv_h (float): image HSV-Hue augmentation (fraction)
        hsv_s (float): image HSV-Saturation augmentation (fraction)
        hsv_v (float): image HSV-Value augmentation (fraction)
        force_color_jitter (bool): force to apply color jitter even if auto augment is enabled
        erasing (float): probability of random erasing
        interpolation (T.InterpolationMode): interpolation mode. default is T.InterpolationMode.BILINEAR.

    Returns:
        (T.Compose): torchvision transforms
    """
    # Transforms to apply if Albumentations not installed
    import torchvision.transforms as T  # scope for faster 'import ultralytics'

    if not isinstance(size, int):
        raise TypeError(f"classify_transforms() size {size} must be integer, not (list, tuple)")
    scale = tuple(scale or (0.08, 1.0))  # default imagenet scale range
    ratio = tuple(ratio or (3.0 / 4.0, 4.0 / 3.0))  # default imagenet ratio range
    primary_tfl = [T.RandomResizedCrop(size, scale=scale, ratio=ratio, interpolation=interpolation)]
    if hflip > 0.0:
        primary_tfl += [T.RandomHorizontalFlip(p=hflip)]
    if vflip > 0.0:
        primary_tfl += [T.RandomVerticalFlip(p=vflip)]

    secondary_tfl = []
    disable_color_jitter = False
    if auto_augment:
        assert isinstance(auto_augment, str)
        # color jitter is typically disabled if AA/RA on,
        # this allows override without breaking old hparm cfgs
        disable_color_jitter = not force_color_jitter

        if auto_augment == "randaugment":
            if TORCHVISION_0_11:
                secondary_tfl += [T.RandAugment(interpolation=interpolation)]
            else:
                LOGGER.warning('"auto_augment=randaugment" requires torchvision >= 0.11.0. Disabling it.')

        elif auto_augment == "augmix":
            if TORCHVISION_0_13:
                secondary_tfl += [T.AugMix(interpolation=interpolation)]
            else:
                LOGGER.warning('"auto_augment=augmix" requires torchvision >= 0.13.0. Disabling it.')

        elif auto_augment == "autoaugment":
            if TORCHVISION_0_10:
                secondary_tfl += [T.AutoAugment(interpolation=interpolation)]
            else:
                LOGGER.warning('"auto_augment=autoaugment" requires torchvision >= 0.10.0. Disabling it.')

        else:
            raise ValueError(
                f'Invalid auto_augment policy: {auto_augment}. Should be one of "randaugment", '
                f'"augmix", "autoaugment" or None'
            )

    if not disable_color_jitter:
        secondary_tfl += [T.ColorJitter(brightness=hsv_v, contrast=hsv_v, saturation=hsv_s, hue=hsv_h)]

    final_tfl = [
        T.ToTensor(),
        T.Normalize(mean=torch.tensor(mean), std=torch.tensor(std)),
        T.RandomErasing(p=erasing, inplace=True),
    ]

    return T.Compose(primary_tfl + secondary_tfl + final_tfl)





Creado 2023-11-12, Actualizado 2024-05-18
Autores: glenn-jocher (5), Burhan-Q (1), Laughing-q (1)