§
    ’©ºjöP  ã                   óœ  — d dl mZ d dlmZ d dlmZ d dlmZmZm	Z	m
Z
mZmZmZmZmZmZmZmZ d dlmZmZ d dlmZ 	 	 d)d	ed
edededeed                  ded         dedefd„Z	 	 	 	 d*dedededed         dee         dedefd„Z	 	 	 	 	 d+dedededeed                   d!eded         dee         dedefd"„Z	 	 	 	 	 d,deded#ededeed                   ded         dee         dedefd$„Z	 	 	 	 	 	 	 	 d-deded&ed'         dedee         d#ee         deed                   deed                  d!ee         dee         dedefd(„ZdS ).é    )ÚOptional)ÚTensor)ÚLiteral)Ú"_binary_stat_scores_arg_validationÚ_binary_stat_scores_formatÚ%_binary_stat_scores_tensor_validationÚ_binary_stat_scores_updateÚ&_multiclass_stat_scores_arg_validationÚ_multiclass_stat_scores_formatÚ)_multiclass_stat_scores_tensor_validationÚ_multiclass_stat_scores_updateÚ&_multilabel_stat_scores_arg_validationÚ_multilabel_stat_scores_formatÚ)_multilabel_stat_scores_tensor_validationÚ_multilabel_stat_scores_update)Ú_adjust_weights_safe_divideÚ_safe_divide)ÚClassificationTaskÚglobalFÚtpÚfpÚtnÚfnÚaverage)ÚbinaryÚmicroÚmacroÚweightedÚnoneÚmultidim_average)r   Ú
samplewiseÚ
multilabelÚreturnc                 óL  — |dk    rdt          | |z   | |z   |z   |z   ¦  «        z
  S |dk    r¯|                      |dk    rdnd¬¦  «        } |                     |dk    rdnd¬¦  «        }|r[|                     |dk    rdnd¬¦  «        }|                     |dk    rdnd¬¦  «        }dt          | |z   | |z   |z   |z   ¦  «        z
  S dt          | | |z   ¦  «        z
  S |rdt          | |z   | |z   |z   |z   ¦  «        z
  ndt          | | |z   ¦  «        z
  }t          |||| ||¦  «        S )a]  Reduce classification statistics into hamming distance.

    Args:
        tp: number of true positives
        fp: number of false positives
        tn: number of true negatives
        fn: number of false negatives
        average:
            Defines the reduction that is applied over labels. Should be one of the following:

            - ``binary``: for binary reduction
            - ``micro``: sum score over all classes/labels
            - ``macro``: salculate score for each class/label and average them
            - ``weighted``: calculates score for each class/label and computes weighted average using their support
            - ``"none"`` or ``None``: calculates score for each class/label and applies no reduction

        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.

        multilabel: If input is multilabel or not

    r   é   r   r   r   )Údim)r   Úsumr   )r   r   r   r   r   r    r"   Úscores           ú~/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/classification/hamming.pyÚ_hamming_distance_reducer*   %   sp  € ðD �(ÒÐØ•<  R¡¨¨b©°2©¸Ñ):Ñ;Ô;Ñ;Ð;Ø�'ÒÐØ�VŠVÐ-°Ò9Ð9˜˜¸qˆVÑAÔAˆØ�VŠVÐ-°Ò9Ð9˜˜¸qˆVÑAÔAˆØð 	@Ø—’Ð!1°XÒ!=Ð!=˜A˜AÀ1�ÑEÔEˆBØ—’Ð!1°XÒ!=Ð!=˜A˜AÀ1�ÑEÔEˆBØ•| B¨¡G¨R°"©W°r©\¸BÑ->Ñ?Ô?Ñ?Ð?Ø•<  B¨¡GÑ,Ô,Ñ,Ð,à<FÐiˆA•˜R "™W b¨2¡g°¡l°RÑ&7Ñ8Ô8Ñ8Ð8ÈAÕP\Ð]_ÐacÐfhÑahÑPiÔPiÑLi€EÝ& u¨g°zÀ2ÀrÈ2ÑNÔNÐNó    ç      à?NTÚpredsÚtargetÚ	thresholdÚignore_indexÚvalidate_argsc                 óÌ   — |r#t          |||¦  «         t          | |||¦  «         t          | |||¦  «        \  } }t          | ||¦  «        \  }}}}	t	          ||||	d|¬¦  «        S )aË  Compute the average `Hamming distance`_ (also known as Hamming loss) for binary tasks.

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds`` (int or float tensor): ``(N, ...)``. If preds is a floating point tensor with values outside
      [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Additionally,
      we convert to int tensor with thresholding using the value in ``threshold``.
    - ``target`` (int tensor): ``(N, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        threshold: Threshold for transforming probability to binary {0,1} predictions
        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        If ``multidim_average`` is set to ``global``, the metric returns a scalar value. If ``multidim_average``
        is set to ``samplewise``, the metric returns ``(N,)`` vector consisting of a scalar value per sample.

    Example (preds is int tensor):
        >>> from torch import tensor
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = tensor([0, 1, 0, 1, 0, 1])
        >>> preds = tensor([0, 0, 1, 1, 0, 1])
        >>> binary_hamming_distance(preds, target)
        tensor(0.3333)

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = tensor([0, 1, 0, 1, 0, 1])
        >>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
        >>> binary_hamming_distance(preds, target)
        tensor(0.3333)

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import binary_hamming_distance
        >>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
        >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
        ...                 [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
        >>> binary_hamming_distance(preds, target, multidim_average='samplewise')
        tensor([0.6667, 0.8333])

    r   ©r   r    )r   r   r   r	   r*   )
r-   r.   r/   r    r0   r1   r   r   r   r   s
             r)   Úbinary_hamming_distancer4   V   sƒ   € ðH ð ]Ý*¨9Ð6FÈÑUÔUÐUÝ-¨e°VÐ=MÈ|Ñ\Ô\Ð\Ý.¨u°f¸iÈÑVÔV�M€Eˆ6Ý/°°vÐ?OÑPÔP�N€BˆˆB�Ý# B¨¨B°¸HÐWgÐhÑhÔhÐhr+   r   r%   Únum_classes)r   r   r   r   Útop_kc           	      óØ   — |r&t          |||||¦  «         t          | ||||¦  «         t          | ||¦  «        \  } }t          | ||||||¦  «        \  }}	}
}t	          ||	|
|||¬¦  «        S )a^  Compute the average `Hamming distance`_ (also known as Hamming loss) for multiclass tasks.

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds``: ``(N, ...)`` (int tensor) or ``(N, C, ..)`` (float tensor). If preds is a floating point
      we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into
      an int tensor.
    - ``target`` (int tensor): ``(N, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        num_classes: Integer specifying the number of classes
        average:
            Defines the reduction that is applied over labels. Should be one of the following:

            - ``micro``: Sum statistics over all labels
            - ``macro``: Calculate statistics for each label and average them
            - ``weighted``: calculates statistics for each label and computes weighted average using their support
            - ``"none"`` or ``None``: calculates statistic for each label and applies no reduction

        top_k:
            Number of highest probability or logit score predictions considered to find the correct label.
            Only works when ``preds`` contain probabilities/logits.
        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        The returned shape depends on the ``average`` and ``multidim_average`` arguments:

        - If ``multidim_average`` is set to ``global``:

          - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
          - If ``average=None/'none'``, the shape will be ``(C,)``

        - If ``multidim_average`` is set to ``samplewise``:

          - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
          - If ``average=None/'none'``, the shape will be ``(N, C)``

    Example (preds is int tensor):
        >>> from torch import tensor
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = tensor([2, 1, 0, 0])
        >>> preds = tensor([2, 1, 0, 1])
        >>> multiclass_hamming_distance(preds, target, num_classes=3)
        tensor(0.1667)
        >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
        tensor([0.5000, 0.0000, 0.0000])

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = tensor([2, 1, 0, 0])
        >>> preds = tensor([[0.16, 0.26, 0.58],
        ...                 [0.22, 0.61, 0.17],
        ...                 [0.71, 0.09, 0.20],
        ...                 [0.05, 0.82, 0.13]])
        >>> multiclass_hamming_distance(preds, target, num_classes=3)
        tensor(0.1667)
        >>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
        tensor([0.5000, 0.0000, 0.0000])

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import multiclass_hamming_distance
        >>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
        >>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
        >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise')
        tensor([0.5000, 0.7222])
        >>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise', average=None)
        tensor([[0.0000, 1.0000, 0.5000],
                [1.0000, 0.6667, 0.5000]])

    r3   )r
   r   r   r   r*   )r-   r.   r5   r   r6   r    r0   r1   r   r   r   r   s               r)   Úmulticlass_hamming_distancer8   ¢   s˜   € ðF ð nÝ.¨{¸EÀ7ÐL\Ð^jÑkÔkÐkÝ1°%¸ÀÐN^Ð`lÑmÔmÐmÝ2°5¸&À%ÑHÔH�M€Eˆ6Ý3Øˆv�{ E¨7Ð4DÀlñô �N€BˆˆB�õ $ B¨¨B°¸GÐVfÐgÑgÔgÐgr+   Ú
num_labelsc           	      óÖ   — |r&t          |||||¦  «         t          | ||||¦  «         t          | ||||¦  «        \  } }t          | ||¦  «        \  }}	}
}t	          ||	|
|||d¬¦  «        S )a  Compute the average `Hamming distance`_ (also known as Hamming loss) for multilabel tasks.

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    Accepts the following input tensors:

    - ``preds`` (int or float tensor): ``(N, C, ...)``. If preds is a floating point tensor with values outside
      [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Additionally,
      we convert to int tensor with thresholding using the value in ``threshold``.
    - ``target`` (int tensor): ``(N, C, ...)``

    Args:
        preds: Tensor with predictions
        target: Tensor with true labels
        num_labels: Integer specifying the number of labels
        threshold: Threshold for transforming probability to binary (0,1) predictions
        average:
            Defines the reduction that is applied over labels. Should be one of the following:

            - ``micro``: Sum statistics over all labels
            - ``macro``: Calculate statistics for each label and average them
            - ``weighted``: calculates statistics for each label and computes weighted average using their support
            - ``"none"`` or ``None``: calculates statistic for each label and applies no reduction

        multidim_average:
            Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

            - ``global``: Additional dimensions are flatted along the batch dimension
            - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
              The statistics in this case are calculated over the additional dimensions.

        ignore_index:
            Specifies a target value that is ignored and does not contribute to the metric calculation
        validate_args: bool indicating if input arguments and tensors should be validated for correctness.
            Set to ``False`` for faster computations.

    Returns:
        The returned shape depends on the ``average`` and ``multidim_average`` arguments:

        - If ``multidim_average`` is set to ``global``:

          - If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
          - If ``average=None/'none'``, the shape will be ``(C,)``

        - If ``multidim_average`` is set to ``samplewise``:

          - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
          - If ``average=None/'none'``, the shape will be ``(N, C)``

    Example (preds is int tensor):
        >>> from torch import tensor
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = tensor([[0, 1, 0], [1, 0, 1]])
        >>> preds = tensor([[0, 0, 1], [1, 0, 1]])
        >>> multilabel_hamming_distance(preds, target, num_labels=3)
        tensor(0.3333)
        >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
        tensor([0.0000, 0.5000, 0.5000])

    Example (preds is float tensor):
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = tensor([[0, 1, 0], [1, 0, 1]])
        >>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
        >>> multilabel_hamming_distance(preds, target, num_labels=3)
        tensor(0.3333)
        >>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
        tensor([0.0000, 0.5000, 0.5000])

    Example (multidim tensors):
        >>> from torchmetrics.functional.classification import multilabel_hamming_distance
        >>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
        >>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
        ...                 [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
        >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise')
        tensor([0.6667, 0.8333])
        >>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise', average=None)
        tensor([[0.5000, 0.5000, 1.0000],
                [1.0000, 1.0000, 0.5000]])

    T)r   r    r"   )r   r   r   r   r*   )r-   r.   r9   r/   r   r    r0   r1   r   r   r   r   s               r)   Úmultilabel_hamming_distancer;     s‘   € ð~ ð mÝ.¨z¸9ÀgÐO_ÐamÑnÔnÐnÝ1°%¸ÀÐM]Ð_kÑlÔlÐlÝ2°5¸&À*ÈiÐYeÑfÔf�M€Eˆ6Ý3°E¸6ÐCSÑTÔT�N€BˆˆB�Ý# B¨¨B°¸GÐVfÐswÐxÑxÔxÐxr+   r   Útask)r   Ú
multiclassr"   c           
      ót  — t          j        |¦  «        }|€J ‚|t           j        k    rt          | ||||	|
¦  «        S |t           j        k    r€t          |t          ¦  «        s t          dt          |¦  «        › d�¦  «        ‚t          |t          ¦  «        s t          dt          |¦  «        › d�¦  «        ‚t          | ||||||	|
¦  «        S |t           j
        k    rKt          |t          ¦  «        s t          dt          |¦  «        › d�¦  «        ‚t          | ||||||	|
¦  «        S t          d|› �¦  «        ‚)a‹  Compute the average `Hamming distance`_ (also known as Hamming loss).

    .. math::
        \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

    Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
    and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
    tensor.

    This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the
    ``task`` argument to either ``'binary'``, ``'multiclass'`` or ``'multilabel'``. See the documentation of
    :func:`~torchmetrics.functional.classification.binary_hamming_distance`,
    :func:`~torchmetrics.functional.classification.multiclass_hamming_distance` and
    :func:`~torchmetrics.functional.classification.multilabel_hamming_distance` for
    the specific details of each argument influence and examples.

    Legacy Example:
        >>> from torch import tensor
        >>> target = tensor([[0, 1], [1, 1]])
        >>> preds = tensor([[0, 1], [0, 1]])
        >>> hamming_distance(preds, target, task="binary")
        tensor(0.2500)

    Nz+`num_classes` is expected to be `int` but `z was passed.`z%`top_k` is expected to be `int` but `z*`num_labels` is expected to be `int` but `zNot handled value: )r   Úfrom_strÚBINARYr4   Ú
MULTICLASSÚ
isinstanceÚintÚ
ValueErrorÚtyper8   Ú
MULTILABELr;   )r-   r.   r<   r/   r5   r9   r   r    r6   r0   r1   s              r)   Úhamming_distancerG   v  sl  € õJ Ô& tÑ,Ô,€DØÐ'Ð'Ð'ØÕ!Ô(Ò(Ð(Ý& u¨f°iÐAQÐS_ÐanÑoÔoÐoØÕ!Ô,Ò,Ð,Ý˜+¥sÑ+Ô+ð 	mÝÐkÍ4ÐP[ÑK\ÔK\ÐkÐkÐkÑlÔlÐlÝ˜%¥Ñ%Ô%ð 	aÝÐ_ÅTÈ%Á[Ä[Ð_Ð_Ð_Ñ`Ô`Ð`Ý*Ø�6˜;¨°Ð8HÈ,ÐXeñ
ô 
ð 	
ð Õ!Ô,Ò,Ð,Ý˜*¥cÑ*Ô*ð 	kÝÐiÍ$ÈzÑJZÔJZÐiÐiÐiÑjÔjÐjÝ*Ø�6˜: y°'Ð;KÈ\Ð[hñ
ô 
ð 	
õ Ð1¨4Ð1Ð1Ñ
2Ô
2Ð2r+   )r   F)r,   r   NT)r   r%   r   NT)r,   r   r   NT)r,   NNr   r   r%   NT) Útypingr   Útorchr   Útyping_extensionsr   Ú2torchmetrics.functional.classification.stat_scoresr   r   r   r	   r
   r   r   r   r   r   r   r   Útorchmetrics.utilities.computer   r   Útorchmetrics.utilities.enumsr   Úboolr*   ÚfloatrC   r4   r8   r;   rG   © r+   r)   ú<module>rQ      sR  ðð Ð Ð Ð Ð Ð à Ð Ð Ð Ð Ð Ø %Ð %Ð %Ð %Ð %Ð %ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð UÐ TÐ TÐ TÐ TÐ TÐ TÐ TØ ;Ð ;Ð ;Ð ;Ð ;Ð ;ð 9AØð.Oð .OØð.Oàð.Oð 	ð.Oð 	ð	.Oð
 �gÐLÔMÔNð.Oð Ð4Ô5ð.Oð ð.Oð ð.Oð .Oð .Oð .Oðh Ø8@Ø"&ØðIið IiØðIiàðIið ðIið Ð4Ô5ð	Iið
 ˜3”-ðIið ðIið ðIið Iið Iið Iið` HOØØ8@Ø"&Øðjhð jhØðjhàðjhð ðjhð �gÐBÔCÔDð	jhð
 ðjhð Ð4Ô5ðjhð ˜3”-ðjhð ðjhð ðjhð jhð jhð jhðb ØGNØ8@Ø"&Øðdyð dyØðdyàðdyð ðdyð ð	dyð
 �gÐBÔCÔDðdyð Ð4Ô5ðdyð ˜3”-ðdyð ðdyð ðdyð dyð dyð dyðV Ø!%Ø $ØGNØBJØØ"&Øð73ð 73Øð73àð73ð Ð6Ô
7ð73ð ð	73ð
 ˜#”ð73ð ˜”ð73ð �gÐBÔCÔDð73ð ˜wÐ'=Ô>Ô?ð73ð �CŒ=ð73ð ˜3”-ð73ð ð73ð ð73ð 73ð 73ð 73ð 73ð 73r+   