Skip to content

Référence pour ultralytics/utils/instance.py

Note

Ce fichier est disponible à l'adresse https://github.com/ultralytics/ ultralytics/blob/main/ ultralytics/utils/instance .py. Si tu repères un problème, aide à le corriger en contribuant à une Pull Request 🛠️. Merci 🙏 !



ultralytics.utils.instance.Bboxes

Une classe pour gérer les boîtes de délimitation.

La classe prend en charge différents formats de boîtes de délimitation comme 'xyxy', 'xywh' et 'ltwh'. Les données de la boîte de délimitation doivent être fournies dans des tableaux numpy.

Attributs :

Nom Type Description
bboxes ndarray

Les boîtes de délimitation sont stockées dans un tableau numpy 2D.

format str

Le format des boîtes de délimitation ('xyxy', 'xywh' ou 'ltwh').

Note

Cette classe ne gère pas la normalisation ou la dénormalisation des boîtes de délimitation.

Code source dans ultralytics/utils/instance.py
class Bboxes:
    """
    A class for handling bounding boxes.

    The class supports various bounding box formats like 'xyxy', 'xywh', and 'ltwh'.
    Bounding box data should be provided in numpy arrays.

    Attributes:
        bboxes (numpy.ndarray): The bounding boxes stored in a 2D numpy array.
        format (str): The format of the bounding boxes ('xyxy', 'xywh', or 'ltwh').

    Note:
        This class does not handle normalization or denormalization of bounding boxes.
    """

    def __init__(self, bboxes, format="xyxy") -> None:
        """Initializes the Bboxes class with bounding box data in a specified format."""
        assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}"
        bboxes = bboxes[None, :] if bboxes.ndim == 1 else bboxes
        assert bboxes.ndim == 2
        assert bboxes.shape[1] == 4
        self.bboxes = bboxes
        self.format = format
        # self.normalized = normalized

    def convert(self, format):
        """Converts bounding box format from one type to another."""
        assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}"
        if self.format == format:
            return
        elif self.format == "xyxy":
            func = xyxy2xywh if format == "xywh" else xyxy2ltwh
        elif self.format == "xywh":
            func = xywh2xyxy if format == "xyxy" else xywh2ltwh
        else:
            func = ltwh2xyxy if format == "xyxy" else ltwh2xywh
        self.bboxes = func(self.bboxes)
        self.format = format

    def areas(self):
        """Return box areas."""
        self.convert("xyxy")
        return (self.bboxes[:, 2] - self.bboxes[:, 0]) * (self.bboxes[:, 3] - self.bboxes[:, 1])

    # def denormalize(self, w, h):
    #    if not self.normalized:
    #         return
    #     assert (self.bboxes <= 1.0).all()
    #     self.bboxes[:, 0::2] *= w
    #     self.bboxes[:, 1::2] *= h
    #     self.normalized = False
    #
    # def normalize(self, w, h):
    #     if self.normalized:
    #         return
    #     assert (self.bboxes > 1.0).any()
    #     self.bboxes[:, 0::2] /= w
    #     self.bboxes[:, 1::2] /= h
    #     self.normalized = True

    def mul(self, scale):
        """
        Args:
            scale (tuple | list | int): the scale for four coords.
        """
        if isinstance(scale, Number):
            scale = to_4tuple(scale)
        assert isinstance(scale, (tuple, list))
        assert len(scale) == 4
        self.bboxes[:, 0] *= scale[0]
        self.bboxes[:, 1] *= scale[1]
        self.bboxes[:, 2] *= scale[2]
        self.bboxes[:, 3] *= scale[3]

    def add(self, offset):
        """
        Args:
            offset (tuple | list | int): the offset for four coords.
        """
        if isinstance(offset, Number):
            offset = to_4tuple(offset)
        assert isinstance(offset, (tuple, list))
        assert len(offset) == 4
        self.bboxes[:, 0] += offset[0]
        self.bboxes[:, 1] += offset[1]
        self.bboxes[:, 2] += offset[2]
        self.bboxes[:, 3] += offset[3]

    def __len__(self):
        """Return the number of boxes."""
        return len(self.bboxes)

    @classmethod
    def concatenate(cls, boxes_list: List["Bboxes"], axis=0) -> "Bboxes":
        """
        Concatenate a list of Bboxes objects into a single Bboxes object.

        Args:
            boxes_list (List[Bboxes]): A list of Bboxes objects to concatenate.
            axis (int, optional): The axis along which to concatenate the bounding boxes.
                                   Defaults to 0.

        Returns:
            Bboxes: A new Bboxes object containing the concatenated bounding boxes.

        Note:
            The input should be a list or tuple of Bboxes objects.
        """
        assert isinstance(boxes_list, (list, tuple))
        if not boxes_list:
            return cls(np.empty(0))
        assert all(isinstance(box, Bboxes) for box in boxes_list)

        if len(boxes_list) == 1:
            return boxes_list[0]
        return cls(np.concatenate([b.bboxes for b in boxes_list], axis=axis))

    def __getitem__(self, index) -> "Bboxes":
        """
        Retrieve a specific bounding box or a set of bounding boxes using indexing.

        Args:
            index (int, slice, or np.ndarray): The index, slice, or boolean array to select
                                               the desired bounding boxes.

        Returns:
            Bboxes: A new Bboxes object containing the selected bounding boxes.

        Raises:
            AssertionError: If the indexed bounding boxes do not form a 2-dimensional matrix.

        Note:
            When using boolean indexing, make sure to provide a boolean array with the same
            length as the number of bounding boxes.
        """
        if isinstance(index, int):
            return Bboxes(self.bboxes[index].view(1, -1))
        b = self.bboxes[index]
        assert b.ndim == 2, f"Indexing on Bboxes with {index} failed to return a matrix!"
        return Bboxes(b)

__getitem__(index)

Récupère une boîte de délimitation spécifique ou un ensemble de boîtes de délimitation à l'aide de l'indexation.

Paramètres :

Nom Type Description DĂ©faut
index int, slice, or np.ndarray

L'index, la tranche ou le tableau booléen permettant de sélectionner les boîtes de délimitation souhaitées.

requis

Retourne :

Nom Type Description
Bboxes Bboxes

Un nouvel objet Bboxes contenant les boîtes de délimitation sélectionnées.

Augmente :

Type Description
AssertionError

Si les boîtes de délimitation indexées ne forment pas une matrice à 2 dimensions.

Note

Lorsque tu utilises l'indexation booléenne, assure-toi de fournir un tableau booléen ayant la même longueur que le nombre de boîtes de délimitation. que le nombre de boîtes de délimitation.

Code source dans ultralytics/utils/instance.py
def __getitem__(self, index) -> "Bboxes":
    """
    Retrieve a specific bounding box or a set of bounding boxes using indexing.

    Args:
        index (int, slice, or np.ndarray): The index, slice, or boolean array to select
                                           the desired bounding boxes.

    Returns:
        Bboxes: A new Bboxes object containing the selected bounding boxes.

    Raises:
        AssertionError: If the indexed bounding boxes do not form a 2-dimensional matrix.

    Note:
        When using boolean indexing, make sure to provide a boolean array with the same
        length as the number of bounding boxes.
    """
    if isinstance(index, int):
        return Bboxes(self.bboxes[index].view(1, -1))
    b = self.bboxes[index]
    assert b.ndim == 2, f"Indexing on Bboxes with {index} failed to return a matrix!"
    return Bboxes(b)

__init__(bboxes, format='xyxy')

Initialise la classe Bboxes avec les données de la boîte de délimitation dans un format spécifié.

Code source dans ultralytics/utils/instance.py
def __init__(self, bboxes, format="xyxy") -> None:
    """Initializes the Bboxes class with bounding box data in a specified format."""
    assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}"
    bboxes = bboxes[None, :] if bboxes.ndim == 1 else bboxes
    assert bboxes.ndim == 2
    assert bboxes.shape[1] == 4
    self.bboxes = bboxes
    self.format = format

__len__()

Renvoie le nombre de boîtes.

Code source dans ultralytics/utils/instance.py
def __len__(self):
    """Return the number of boxes."""
    return len(self.bboxes)

add(offset)

Paramètres :

Nom Type Description DĂ©faut
offset tuple | list | int

le décalage pour quatre coordonnées.

requis
Code source dans ultralytics/utils/instance.py
def add(self, offset):
    """
    Args:
        offset (tuple | list | int): the offset for four coords.
    """
    if isinstance(offset, Number):
        offset = to_4tuple(offset)
    assert isinstance(offset, (tuple, list))
    assert len(offset) == 4
    self.bboxes[:, 0] += offset[0]
    self.bboxes[:, 1] += offset[1]
    self.bboxes[:, 2] += offset[2]
    self.bboxes[:, 3] += offset[3]

areas()

Zones de la boîte de retour.

Code source dans ultralytics/utils/instance.py
def areas(self):
    """Return box areas."""
    self.convert("xyxy")
    return (self.bboxes[:, 2] - self.bboxes[:, 0]) * (self.bboxes[:, 3] - self.bboxes[:, 1])

concatenate(boxes_list, axis=0) classmethod

Concatène une liste d'objets Bboxes en un seul objet Bboxes.

Paramètres :

Nom Type Description DĂ©faut
boxes_list List[Bboxes]

Une liste d'objets Bboxes à concaténer.

requis
axis int

L'axe le long duquel concaténer les boîtes de délimitation. La valeur par défaut est 0.

0

Retourne :

Nom Type Description
Bboxes Bboxes

Un nouvel objet Bboxes contenant les boîtes de délimitation concaténées.

Note

L'entrée doit être une liste ou un tuple d'objets Bboxes.

Code source dans ultralytics/utils/instance.py
@classmethod
def concatenate(cls, boxes_list: List["Bboxes"], axis=0) -> "Bboxes":
    """
    Concatenate a list of Bboxes objects into a single Bboxes object.

    Args:
        boxes_list (List[Bboxes]): A list of Bboxes objects to concatenate.
        axis (int, optional): The axis along which to concatenate the bounding boxes.
                               Defaults to 0.

    Returns:
        Bboxes: A new Bboxes object containing the concatenated bounding boxes.

    Note:
        The input should be a list or tuple of Bboxes objects.
    """
    assert isinstance(boxes_list, (list, tuple))
    if not boxes_list:
        return cls(np.empty(0))
    assert all(isinstance(box, Bboxes) for box in boxes_list)

    if len(boxes_list) == 1:
        return boxes_list[0]
    return cls(np.concatenate([b.bboxes for b in boxes_list], axis=axis))

convert(format)

Convertit le format de la boîte de délimitation d'un type à un autre.

Code source dans ultralytics/utils/instance.py
def convert(self, format):
    """Converts bounding box format from one type to another."""
    assert format in _formats, f"Invalid bounding box format: {format}, format must be one of {_formats}"
    if self.format == format:
        return
    elif self.format == "xyxy":
        func = xyxy2xywh if format == "xywh" else xyxy2ltwh
    elif self.format == "xywh":
        func = xywh2xyxy if format == "xyxy" else xywh2ltwh
    else:
        func = ltwh2xyxy if format == "xyxy" else ltwh2xywh
    self.bboxes = func(self.bboxes)
    self.format = format

mul(scale)

Paramètres :

Nom Type Description DĂ©faut
scale tuple | list | int

l'échelle pour quatre coordonnées.

requis
Code source dans ultralytics/utils/instance.py
def mul(self, scale):
    """
    Args:
        scale (tuple | list | int): the scale for four coords.
    """
    if isinstance(scale, Number):
        scale = to_4tuple(scale)
    assert isinstance(scale, (tuple, list))
    assert len(scale) == 4
    self.bboxes[:, 0] *= scale[0]
    self.bboxes[:, 1] *= scale[1]
    self.bboxes[:, 2] *= scale[2]
    self.bboxes[:, 3] *= scale[3]



ultralytics.utils.instance.Instances

Conteneur pour les boîtes de délimitation, les segments et les points clés des objets détectés dans une image.

Attributs :

Nom Type Description
_bboxes Bboxes

Objet interne permettant de gérer les opérations relatives à la boîte de délimitation.

keypoints ndarray

points-clés(x, y, visible) de forme [N, 17, 3]. La valeur par défaut est Aucun.

normalized bool

Drapeau indiquant si les coordonnées de la boîte de délimitation sont normalisées.

segments ndarray

Segmente le tableau de forme [N, 1000, 2] après le rééchantillonnage.

Paramètres :

Nom Type Description DĂ©faut
bboxes ndarray

Un tableau de boîtes de délimitation de forme [N, 4].

requis
segments list | ndarray

Une liste ou un tableau de segments d'objets. La valeur par défaut est Aucun.

None
keypoints ndarray

Un tableau de points clés de forme [N, 17, 3]. La valeur par défaut est Aucun.

None
bbox_format str

Le format des boîtes de délimitation ('xywh' ou 'xyxy'). La valeur par défaut est 'xywh'.

'xywh'
normalized bool

Si les coordonnées de la boîte de délimitation sont normalisées. La valeur par défaut est True.

True

Exemples :

# Create an Instances object
instances = Instances(
    bboxes=np.array([[10, 10, 30, 30], [20, 20, 40, 40]]),
    segments=[np.array([[5, 5], [10, 10]]), np.array([[15, 15], [20, 20]])],
    keypoints=np.array([[[5, 5, 1], [10, 10, 1]], [[15, 15, 1], [20, 20, 1]]])
)
Note

Le format de la boîte de délimitation est soit 'xywh', soit 'xyxy', et est déterminé par le paramètre bbox_format argument. Cette classe n'effectue pas de validation d'entrée et suppose que les entrées sont bien formées.

Code source dans ultralytics/utils/instance.py
class Instances:
    """
    Container for bounding boxes, segments, and keypoints of detected objects in an image.

    Attributes:
        _bboxes (Bboxes): Internal object for handling bounding box operations.
        keypoints (ndarray): keypoints(x, y, visible) with shape [N, 17, 3]. Default is None.
        normalized (bool): Flag indicating whether the bounding box coordinates are normalized.
        segments (ndarray): Segments array with shape [N, 1000, 2] after resampling.

    Args:
        bboxes (ndarray): An array of bounding boxes with shape [N, 4].
        segments (list | ndarray, optional): A list or array of object segments. Default is None.
        keypoints (ndarray, optional): An array of keypoints with shape [N, 17, 3]. Default is None.
        bbox_format (str, optional): The format of bounding boxes ('xywh' or 'xyxy'). Default is 'xywh'.
        normalized (bool, optional): Whether the bounding box coordinates are normalized. Default is True.

    Examples:
        ```python
        # Create an Instances object
        instances = Instances(
            bboxes=np.array([[10, 10, 30, 30], [20, 20, 40, 40]]),
            segments=[np.array([[5, 5], [10, 10]]), np.array([[15, 15], [20, 20]])],
            keypoints=np.array([[[5, 5, 1], [10, 10, 1]], [[15, 15, 1], [20, 20, 1]]])
        )
        ```

    Note:
        The bounding box format is either 'xywh' or 'xyxy', and is determined by the `bbox_format` argument.
        This class does not perform input validation, and it assumes the inputs are well-formed.
    """

    def __init__(self, bboxes, segments=None, keypoints=None, bbox_format="xywh", normalized=True) -> None:
        """
        Args:
            bboxes (ndarray): bboxes with shape [N, 4].
            segments (list | ndarray): segments.
            keypoints (ndarray): keypoints(x, y, visible) with shape [N, 17, 3].
        """
        self._bboxes = Bboxes(bboxes=bboxes, format=bbox_format)
        self.keypoints = keypoints
        self.normalized = normalized
        self.segments = segments

    def convert_bbox(self, format):
        """Convert bounding box format."""
        self._bboxes.convert(format=format)

    @property
    def bbox_areas(self):
        """Calculate the area of bounding boxes."""
        return self._bboxes.areas()

    def scale(self, scale_w, scale_h, bbox_only=False):
        """This might be similar with denormalize func but without normalized sign."""
        self._bboxes.mul(scale=(scale_w, scale_h, scale_w, scale_h))
        if bbox_only:
            return
        self.segments[..., 0] *= scale_w
        self.segments[..., 1] *= scale_h
        if self.keypoints is not None:
            self.keypoints[..., 0] *= scale_w
            self.keypoints[..., 1] *= scale_h

    def denormalize(self, w, h):
        """Denormalizes boxes, segments, and keypoints from normalized coordinates."""
        if not self.normalized:
            return
        self._bboxes.mul(scale=(w, h, w, h))
        self.segments[..., 0] *= w
        self.segments[..., 1] *= h
        if self.keypoints is not None:
            self.keypoints[..., 0] *= w
            self.keypoints[..., 1] *= h
        self.normalized = False

    def normalize(self, w, h):
        """Normalize bounding boxes, segments, and keypoints to image dimensions."""
        if self.normalized:
            return
        self._bboxes.mul(scale=(1 / w, 1 / h, 1 / w, 1 / h))
        self.segments[..., 0] /= w
        self.segments[..., 1] /= h
        if self.keypoints is not None:
            self.keypoints[..., 0] /= w
            self.keypoints[..., 1] /= h
        self.normalized = True

    def add_padding(self, padw, padh):
        """Handle rect and mosaic situation."""
        assert not self.normalized, "you should add padding with absolute coordinates."
        self._bboxes.add(offset=(padw, padh, padw, padh))
        self.segments[..., 0] += padw
        self.segments[..., 1] += padh
        if self.keypoints is not None:
            self.keypoints[..., 0] += padw
            self.keypoints[..., 1] += padh

    def __getitem__(self, index) -> "Instances":
        """
        Retrieve a specific instance or a set of instances using indexing.

        Args:
            index (int, slice, or np.ndarray): The index, slice, or boolean array to select
                                               the desired instances.

        Returns:
            Instances: A new Instances object containing the selected bounding boxes,
                       segments, and keypoints if present.

        Note:
            When using boolean indexing, make sure to provide a boolean array with the same
            length as the number of instances.
        """
        segments = self.segments[index] if len(self.segments) else self.segments
        keypoints = self.keypoints[index] if self.keypoints is not None else None
        bboxes = self.bboxes[index]
        bbox_format = self._bboxes.format
        return Instances(
            bboxes=bboxes,
            segments=segments,
            keypoints=keypoints,
            bbox_format=bbox_format,
            normalized=self.normalized,
        )

    def flipud(self, h):
        """Flips the coordinates of bounding boxes, segments, and keypoints vertically."""
        if self._bboxes.format == "xyxy":
            y1 = self.bboxes[:, 1].copy()
            y2 = self.bboxes[:, 3].copy()
            self.bboxes[:, 1] = h - y2
            self.bboxes[:, 3] = h - y1
        else:
            self.bboxes[:, 1] = h - self.bboxes[:, 1]
        self.segments[..., 1] = h - self.segments[..., 1]
        if self.keypoints is not None:
            self.keypoints[..., 1] = h - self.keypoints[..., 1]

    def fliplr(self, w):
        """Reverses the order of the bounding boxes and segments horizontally."""
        if self._bboxes.format == "xyxy":
            x1 = self.bboxes[:, 0].copy()
            x2 = self.bboxes[:, 2].copy()
            self.bboxes[:, 0] = w - x2
            self.bboxes[:, 2] = w - x1
        else:
            self.bboxes[:, 0] = w - self.bboxes[:, 0]
        self.segments[..., 0] = w - self.segments[..., 0]
        if self.keypoints is not None:
            self.keypoints[..., 0] = w - self.keypoints[..., 0]

    def clip(self, w, h):
        """Clips bounding boxes, segments, and keypoints values to stay within image boundaries."""
        ori_format = self._bboxes.format
        self.convert_bbox(format="xyxy")
        self.bboxes[:, [0, 2]] = self.bboxes[:, [0, 2]].clip(0, w)
        self.bboxes[:, [1, 3]] = self.bboxes[:, [1, 3]].clip(0, h)
        if ori_format != "xyxy":
            self.convert_bbox(format=ori_format)
        self.segments[..., 0] = self.segments[..., 0].clip(0, w)
        self.segments[..., 1] = self.segments[..., 1].clip(0, h)
        if self.keypoints is not None:
            self.keypoints[..., 0] = self.keypoints[..., 0].clip(0, w)
            self.keypoints[..., 1] = self.keypoints[..., 1].clip(0, h)

    def remove_zero_area_boxes(self):
        """
        Remove zero-area boxes, i.e. after clipping some boxes may have zero width or height.

        This removes them.
        """
        good = self.bbox_areas > 0
        if not all(good):
            self._bboxes = self._bboxes[good]
            if len(self.segments):
                self.segments = self.segments[good]
            if self.keypoints is not None:
                self.keypoints = self.keypoints[good]
        return good

    def update(self, bboxes, segments=None, keypoints=None):
        """Updates instance variables."""
        self._bboxes = Bboxes(bboxes, format=self._bboxes.format)
        if segments is not None:
            self.segments = segments
        if keypoints is not None:
            self.keypoints = keypoints

    def __len__(self):
        """Return the length of the instance list."""
        return len(self.bboxes)

    @classmethod
    def concatenate(cls, instances_list: List["Instances"], axis=0) -> "Instances":
        """
        Concatenates a list of Instances objects into a single Instances object.

        Args:
            instances_list (List[Instances]): A list of Instances objects to concatenate.
            axis (int, optional): The axis along which the arrays will be concatenated. Defaults to 0.

        Returns:
            Instances: A new Instances object containing the concatenated bounding boxes,
                       segments, and keypoints if present.

        Note:
            The `Instances` objects in the list should have the same properties, such as
            the format of the bounding boxes, whether keypoints are present, and if the
            coordinates are normalized.
        """
        assert isinstance(instances_list, (list, tuple))
        if not instances_list:
            return cls(np.empty(0))
        assert all(isinstance(instance, Instances) for instance in instances_list)

        if len(instances_list) == 1:
            return instances_list[0]

        use_keypoint = instances_list[0].keypoints is not None
        bbox_format = instances_list[0]._bboxes.format
        normalized = instances_list[0].normalized

        cat_boxes = np.concatenate([ins.bboxes for ins in instances_list], axis=axis)
        cat_segments = np.concatenate([b.segments for b in instances_list], axis=axis)
        cat_keypoints = np.concatenate([b.keypoints for b in instances_list], axis=axis) if use_keypoint else None
        return cls(cat_boxes, cat_segments, cat_keypoints, bbox_format, normalized)

    @property
    def bboxes(self):
        """Return bounding boxes."""
        return self._bboxes.bboxes

bbox_areas property

Calcule la surface des boîtes de délimitation.

bboxes property

Retourne les boîtes de délimitation.

__getitem__(index)

Récupère une instance spécifique ou un ensemble d'instances à l'aide de l'indexation.

Paramètres :

Nom Type Description DĂ©faut
index int, slice, or np.ndarray

L'index, la tranche ou le tableau booléen permettant de sélectionner les instances souhaitées.

requis

Retourne :

Nom Type Description
Instances Instances

Un nouvel objet Instances contenant les boîtes de délimitation sélectionnées, les segments et les points clés sélectionnés, le cas échéant.

Note

Lorsque tu utilises l'indexation booléenne, assure-toi de fournir un tableau booléen ayant la même longueur que le nombre d'instances. que le nombre d'instances.

Code source dans ultralytics/utils/instance.py
def __getitem__(self, index) -> "Instances":
    """
    Retrieve a specific instance or a set of instances using indexing.

    Args:
        index (int, slice, or np.ndarray): The index, slice, or boolean array to select
                                           the desired instances.

    Returns:
        Instances: A new Instances object containing the selected bounding boxes,
                   segments, and keypoints if present.

    Note:
        When using boolean indexing, make sure to provide a boolean array with the same
        length as the number of instances.
    """
    segments = self.segments[index] if len(self.segments) else self.segments
    keypoints = self.keypoints[index] if self.keypoints is not None else None
    bboxes = self.bboxes[index]
    bbox_format = self._bboxes.format
    return Instances(
        bboxes=bboxes,
        segments=segments,
        keypoints=keypoints,
        bbox_format=bbox_format,
        normalized=self.normalized,
    )

__init__(bboxes, segments=None, keypoints=None, bbox_format='xywh', normalized=True)

Paramètres :

Nom Type Description DĂ©faut
bboxes ndarray

bboxes de forme [N, 4].

requis
segments list | ndarray

segments.

None
keypoints ndarray

keypoints(x, y, visible) avec la forme [N, 17, 3].

None
Code source dans ultralytics/utils/instance.py
def __init__(self, bboxes, segments=None, keypoints=None, bbox_format="xywh", normalized=True) -> None:
    """
    Args:
        bboxes (ndarray): bboxes with shape [N, 4].
        segments (list | ndarray): segments.
        keypoints (ndarray): keypoints(x, y, visible) with shape [N, 17, 3].
    """
    self._bboxes = Bboxes(bboxes=bboxes, format=bbox_format)
    self.keypoints = keypoints
    self.normalized = normalized
    self.segments = segments

__len__()

Renvoie la longueur de la liste d'instances.

Code source dans ultralytics/utils/instance.py
def __len__(self):
    """Return the length of the instance list."""
    return len(self.bboxes)

add_padding(padw, padh)

Traite les situations de rect et de mosaĂŻque.

Code source dans ultralytics/utils/instance.py
def add_padding(self, padw, padh):
    """Handle rect and mosaic situation."""
    assert not self.normalized, "you should add padding with absolute coordinates."
    self._bboxes.add(offset=(padw, padh, padw, padh))
    self.segments[..., 0] += padw
    self.segments[..., 1] += padh
    if self.keypoints is not None:
        self.keypoints[..., 0] += padw
        self.keypoints[..., 1] += padh

clip(w, h)

Coupe les boîtes de délimitation, les segments et les valeurs des points clés pour qu'ils restent dans les limites de l'image.

Code source dans ultralytics/utils/instance.py
def clip(self, w, h):
    """Clips bounding boxes, segments, and keypoints values to stay within image boundaries."""
    ori_format = self._bboxes.format
    self.convert_bbox(format="xyxy")
    self.bboxes[:, [0, 2]] = self.bboxes[:, [0, 2]].clip(0, w)
    self.bboxes[:, [1, 3]] = self.bboxes[:, [1, 3]].clip(0, h)
    if ori_format != "xyxy":
        self.convert_bbox(format=ori_format)
    self.segments[..., 0] = self.segments[..., 0].clip(0, w)
    self.segments[..., 1] = self.segments[..., 1].clip(0, h)
    if self.keypoints is not None:
        self.keypoints[..., 0] = self.keypoints[..., 0].clip(0, w)
        self.keypoints[..., 1] = self.keypoints[..., 1].clip(0, h)

concatenate(instances_list, axis=0) classmethod

Concatène une liste d'objets Instances en un seul objet Instances.

Paramètres :

Nom Type Description DĂ©faut
instances_list List[Instances]

Une liste d'objets Instances à concaténer.

requis
axis int

L'axe le long duquel les tableaux seront concaténés. La valeur par défaut est 0.

0

Retourne :

Nom Type Description
Instances Instances

Un nouvel objet Instances contenant les boîtes de délimitation concaténées, les segments et les points clés s'ils sont présents.

Note

Le Instances Les objets de la liste doivent avoir les mêmes propriétés, telles que le format des boîtes de délimitation, la présence ou non de points clés et la normalisation des coordonnées. sont normalisées.

Code source dans ultralytics/utils/instance.py
@classmethod
def concatenate(cls, instances_list: List["Instances"], axis=0) -> "Instances":
    """
    Concatenates a list of Instances objects into a single Instances object.

    Args:
        instances_list (List[Instances]): A list of Instances objects to concatenate.
        axis (int, optional): The axis along which the arrays will be concatenated. Defaults to 0.

    Returns:
        Instances: A new Instances object containing the concatenated bounding boxes,
                   segments, and keypoints if present.

    Note:
        The `Instances` objects in the list should have the same properties, such as
        the format of the bounding boxes, whether keypoints are present, and if the
        coordinates are normalized.
    """
    assert isinstance(instances_list, (list, tuple))
    if not instances_list:
        return cls(np.empty(0))
    assert all(isinstance(instance, Instances) for instance in instances_list)

    if len(instances_list) == 1:
        return instances_list[0]

    use_keypoint = instances_list[0].keypoints is not None
    bbox_format = instances_list[0]._bboxes.format
    normalized = instances_list[0].normalized

    cat_boxes = np.concatenate([ins.bboxes for ins in instances_list], axis=axis)
    cat_segments = np.concatenate([b.segments for b in instances_list], axis=axis)
    cat_keypoints = np.concatenate([b.keypoints for b in instances_list], axis=axis) if use_keypoint else None
    return cls(cat_boxes, cat_segments, cat_keypoints, bbox_format, normalized)

convert_bbox(format)

Convertir le format de la boîte de délimitation.

Code source dans ultralytics/utils/instance.py
def convert_bbox(self, format):
    """Convert bounding box format."""
    self._bboxes.convert(format=format)

denormalize(w, h)

Dénormalise les boîtes, les segments et les points clés à partir de coordonnées normalisées.

Code source dans ultralytics/utils/instance.py
def denormalize(self, w, h):
    """Denormalizes boxes, segments, and keypoints from normalized coordinates."""
    if not self.normalized:
        return
    self._bboxes.mul(scale=(w, h, w, h))
    self.segments[..., 0] *= w
    self.segments[..., 1] *= h
    if self.keypoints is not None:
        self.keypoints[..., 0] *= w
        self.keypoints[..., 1] *= h
    self.normalized = False

fliplr(w)

Inverse l'ordre des boîtes englobantes et des segments horizontalement.

Code source dans ultralytics/utils/instance.py
def fliplr(self, w):
    """Reverses the order of the bounding boxes and segments horizontally."""
    if self._bboxes.format == "xyxy":
        x1 = self.bboxes[:, 0].copy()
        x2 = self.bboxes[:, 2].copy()
        self.bboxes[:, 0] = w - x2
        self.bboxes[:, 2] = w - x1
    else:
        self.bboxes[:, 0] = w - self.bboxes[:, 0]
    self.segments[..., 0] = w - self.segments[..., 0]
    if self.keypoints is not None:
        self.keypoints[..., 0] = w - self.keypoints[..., 0]

flipud(h)

Retourne verticalement les coordonnées des boîtes de délimitation, des segments et des points clés.

Code source dans ultralytics/utils/instance.py
def flipud(self, h):
    """Flips the coordinates of bounding boxes, segments, and keypoints vertically."""
    if self._bboxes.format == "xyxy":
        y1 = self.bboxes[:, 1].copy()
        y2 = self.bboxes[:, 3].copy()
        self.bboxes[:, 1] = h - y2
        self.bboxes[:, 3] = h - y1
    else:
        self.bboxes[:, 1] = h - self.bboxes[:, 1]
    self.segments[..., 1] = h - self.segments[..., 1]
    if self.keypoints is not None:
        self.keypoints[..., 1] = h - self.keypoints[..., 1]

normalize(w, h)

Normalise les boîtes de délimitation, les segments et les points clés en fonction des dimensions de l'image.

Code source dans ultralytics/utils/instance.py
def normalize(self, w, h):
    """Normalize bounding boxes, segments, and keypoints to image dimensions."""
    if self.normalized:
        return
    self._bboxes.mul(scale=(1 / w, 1 / h, 1 / w, 1 / h))
    self.segments[..., 0] /= w
    self.segments[..., 1] /= h
    if self.keypoints is not None:
        self.keypoints[..., 0] /= w
        self.keypoints[..., 1] /= h
    self.normalized = True

remove_zero_area_boxes()

Supprime les cases à surface nulle, c'est-à-dire qu'après l'écrêtage, certaines cases peuvent avoir une largeur ou une hauteur nulle.

Cela les supprime.

Code source dans ultralytics/utils/instance.py
def remove_zero_area_boxes(self):
    """
    Remove zero-area boxes, i.e. after clipping some boxes may have zero width or height.

    This removes them.
    """
    good = self.bbox_areas > 0
    if not all(good):
        self._bboxes = self._bboxes[good]
        if len(self.segments):
            self.segments = self.segments[good]
        if self.keypoints is not None:
            self.keypoints = self.keypoints[good]
    return good

scale(scale_w, scale_h, bbox_only=False)

Cela pourrait être similaire à la fonction de dénormalisation, mais sans le signe normalisé.

Code source dans ultralytics/utils/instance.py
def scale(self, scale_w, scale_h, bbox_only=False):
    """This might be similar with denormalize func but without normalized sign."""
    self._bboxes.mul(scale=(scale_w, scale_h, scale_w, scale_h))
    if bbox_only:
        return
    self.segments[..., 0] *= scale_w
    self.segments[..., 1] *= scale_h
    if self.keypoints is not None:
        self.keypoints[..., 0] *= scale_w
        self.keypoints[..., 1] *= scale_h

update(bboxes, segments=None, keypoints=None)

Met Ă  jour les variables d'instance.

Code source dans ultralytics/utils/instance.py
def update(self, bboxes, segments=None, keypoints=None):
    """Updates instance variables."""
    self._bboxes = Bboxes(bboxes, format=self._bboxes.format)
    if segments is not None:
        self.segments = segments
    if keypoints is not None:
        self.keypoints = keypoints



ultralytics.utils.instance._ntuple(n)

Ă€ partir de PyTorch internals.

Code source dans ultralytics/utils/instance.py
def _ntuple(n):
    """From PyTorch internals."""

    def parse(x):
        """Parse bounding boxes format between XYWH and LTWH."""
        return x if isinstance(x, abc.Iterable) else tuple(repeat(x, n))

    return parse





Créé le 2023-11-12, Mis à jour le 2023-11-25
Auteurs : glenn-jocher (3), Laughing-q (1)