§
    ’©ºj  ã                   ó¸   — d dl mZ d dlmZmZmZmZmZ d dlZd dlm	Z	 d dl
mZ d dlmZmZ d dlmZ d dlmZ d d	lmZ d d
lmZmZ esdgZ G d„ de¦  «        ZdS )é    )ÚSequence)ÚAnyÚListÚOptionalÚUnionÚcastN)ÚTensor)ÚLiteral)Ú_kld_computeÚ_kld_update)ÚMetric)Údim_zero_cat)Ú_MATPLOTLIB_AVAILABLE)Ú_AX_TYPEÚ_PLOT_OUT_TYPEzKLDivergence.plotc            	       ó  ‡ — e Zd ZU dZdZeed<   dZeed<   dZeed<   dZ	e
ed<   eeee         f         ed	<   eed
<   	 	 ddeded         deddfˆ fd„Zdededdfd„Zdefd„Z	 ddeeeee         f                  dee         defd„Zˆ xZS )ÚKLDivergenceaµ  Compute the `KL divergence`_.

    .. math::
        D_{KL}(P||Q) = \sum_{x\in\mathcal{X}} P(x) \log\frac{P(x)}{Q{x}}

    Where :math:`P` and :math:`Q` are probability distributions where :math:`P` usually represents a distribution
    over data and :math:`Q` is often a prior or approximation of :math:`P`. It should be noted that the KL divergence
    is a non-symmetrical metric i.e. :math:`D_{KL}(P||Q) \neq D_{KL}(Q||P)`.

    As input to ``forward`` and ``update`` the metric accepts the following input:

    - ``p`` (:class:`~torch.Tensor`): a data distribution with shape ``(N, d)``
    - ``q`` (:class:`~torch.Tensor`): prior or approximate distribution with shape ``(N, d)``

    As output of ``forward`` and ``compute`` the metric returns the following output:

    - ``kl_divergence`` (:class:`~torch.Tensor`): A tensor with the KL divergence

    Args:
        log_prob: bool indicating if input is log-probabilities or probabilities. If given as probabilities,
            will normalize to make sure the distributes sum to 1.
        reduction:
            Determines how to reduce over the ``N``/batch dimension:

            - ``'mean'`` [default]: Averages score across samples
            - ``'sum'``: Sum score across samples
            - ``'none'`` or ``None``: Returns score per sample

        kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

    Raises:
        TypeError:
            If ``log_prob`` is not an ``bool``.
        ValueError:
            If ``reduction`` is not one of ``'mean'``, ``'sum'``, ``'none'`` or ``None``.

    .. attention::
        Half precision is only support on GPU for this metric.

    Example:
        >>> from torch import tensor
        >>> from torchmetrics.regression import KLDivergence
        >>> p = tensor([[0.36, 0.48, 0.16]])
        >>> q = tensor([[1/3, 1/3, 1/3]])
        >>> kl_divergence = KLDivergence()
        >>> kl_divergence(p, q)
        tensor(0.0853)

    TÚis_differentiableFÚhigher_is_betterÚfull_state_updateç        Úplot_lower_boundÚmeasuresÚtotalÚmeanÚlog_probÚ	reduction©r   ÚsumÚnoneNÚkwargsÚreturnNc                 óÊ  •—  t          ¦   «         j        di |¤Ž t          |t          ¦  «        st	          d|› �¦  «        ‚|| _        g d¢}||vrt          d|› d|› �¦  «        ‚|| _        | j        dv r+|                      dt          j
        d¦  «        d¬	¦  «         n|                      dg d
¬	¦  «         |                      dt          j
        d¦  «        d¬	¦  «         d S )Nz0Expected argument `log_prob` to be bool but got r   z+Expected argument `reduction` to be one of z	 but got )r   r   r   r   r   )Údist_reduce_fxÚcatr   r   © )ÚsuperÚ__init__Ú
isinstanceÚboolÚ	TypeErrorr   Ú
ValueErrorr   Ú	add_stateÚtorchÚtensor)Úselfr   r   r!   Úallowed_reductionÚ	__class__s        €úu/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/regression/kl_divergence.pyr(   zKLDivergence.__init__\   s  ø€ ð 	�‰ŒÔÐ"Ð"˜6Ð"Ð"Ð"Ý˜(¥DÑ)Ô)ð 	[ÝÐYÈxÐYÐYÑZÔZÐZØ ˆŒà9Ð9Ð9ÐØÐ-Ð-Ð-ÝÐrÐK\ÐrÐrÐgpÐrÐrÑsÔsÐsØ"ˆŒàŒ>˜_Ð,Ð,Ø�NŠN˜:¥u¤|°CÑ'8Ô'8ÈˆNÑOÔOÐOÐOà�NŠN˜: r¸%ˆNÑ@Ô@Ð@Ø�Š�w¥¤¨Q¡¤ÀˆÑFÔFÐFÐFÐFó    ÚpÚqc                 óX  — t          ||| j        ¦  «        \  }}| j        �| j        dk    r:t          t          t
                   | j        ¦  «                             |¦  «         dS t          t
          | j        ¦  «        |                     ¦   «         z   | _        | xj	        |z  c_	        dS )z2Update metric states with predictions and targets.Nr    )
r   r   r   r   r   r	   r   Úappendr   r   )r0   r5   r6   r   r   s        r3   ÚupdatezKLDivergence.updater   s‹   € å% a¨¨D¬MÑ:Ô:‰ˆ�%ØŒ>Ð! T¤^°vÒ%=Ð%=Ý••f”˜tœ}Ñ-Ô-×4Ò4°XÑ>Ô>Ð>Ð>Ð>å ¥¨¬Ñ7Ô7¸(¿,º,¹.¼.ÑHˆDŒMØˆJŒJ˜%ÑˆJŒJˆJˆJr4   c                 óâ   — | j         dv r2t          t          t          t                   | j        ¦  «        ¦  «        nt          t          | j        ¦  «        }t          || j        | j         ¦  «        S )zCompute metric.)r    N)r   r   r   r   r	   r   r   r   )r0   r   s     r3   ÚcomputezKLDivergence.compute{   s]   € ð Œ~ Ð/Ð/õ ��d¥6œl¨D¬MÑ:Ô:Ñ;Ô;Ð;å•f˜dœmÑ,Ô,ð 	õ
 ˜H d¤j°$´.ÑAÔAÐAr4   ÚvalÚaxc                 ó.   — |                       ||¦  «        S )aC  Plot a single or multiple values from the metric.

        Args:
            val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
                If no value is provided, will automatically call `metric.compute` and plot that result.
            ax: An matplotlib axis object. If provided will add plot to that axis

        Returns:
            Figure and Axes object

        Raises:
            ModuleNotFoundError:
                If `matplotlib` is not installed

        .. plot::
            :scale: 75

            >>> from torch import randn
            >>> # Example plotting a single value
            >>> from torchmetrics.regression import KLDivergence
            >>> metric = KLDivergence()
            >>> metric.update(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1))
            >>> fig_, ax_ = metric.plot()

        .. plot::
            :scale: 75

            >>> from torch import randn
            >>> # Example plotting multiple values
            >>> from torchmetrics.regression import KLDivergence
            >>> metric = KLDivergence()
            >>> values = []
            >>> for _ in range(10):
            ...     values.append(metric(randn(10,3).softmax(dim=-1), randn(10,3).softmax(dim=-1)))
            >>> fig, ax = metric.plot(values)

        )Ú_plot)r0   r<   r=   s      r3   ÚplotzKLDivergence.plot„   s   € ðP �zŠz˜#˜rÑ"Ô"Ð"r4   )Fr   )NN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__r   r*   Ú__annotations__r   r   r   Úfloatr   r	   r   r
   r   r(   r9   r;   r   r   r   r   r@   Ú__classcell__)r2   s   @r3   r   r      s’  ø€ € € € € € ð0ð 0ðd #Ð�tÐ"Ð"Ñ"Ø"Ð�dÐ"Ð"Ñ"Ø#Ð�tÐ#Ð#Ñ#Ø!Ð�eÐ!Ð!Ñ!à�F˜D œLÐ(Ô)Ð)Ð)Ñ)Ø€M€M�Mð Ø:@ðGð GàðGð Ð6Ô7ðGð ð	Gð
 
ðGð Gð Gð Gð Gð Gð, ˜ð   6ð  ¨dð  ð  ð  ð  ðB˜ð Bð Bð Bð Bð _cð(#ð (#Ø˜E &¨(°6Ô*:Ð":Ô;Ô<ð(#ØIQÐRZÔI[ð(#à	ð(#ð (#ð (#ð (#ð (#ð (#ð (#ð (#r4   r   )Úcollections.abcr   Útypingr   r   r   r   r   r.   r	   Útyping_extensionsr
   Ú0torchmetrics.functional.regression.kl_divergencer   r   Útorchmetrics.metricr   Útorchmetrics.utilities.datar   Útorchmetrics.utilities.importsr   Útorchmetrics.utilities.plotr   r   Ú__doctest_skip__r   r&   r4   r3   ú<module>rQ      s%  ðð %Ð $Ð $Ð $Ð $Ð $Ø 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3Ð 3à €€€Ø Ð Ð Ð Ð Ð Ø %Ð %Ð %Ð %Ð %Ð %à VÐ VÐ VÐ VÐ VÐ VÐ VÐ VØ &Ð &Ð &Ð &Ð &Ð &Ø 4Ð 4Ð 4Ð 4Ð 4Ð 4Ø @Ð @Ð @Ð @Ð @Ð @Ø @Ð @Ð @Ð @Ð @Ð @Ð @Ð @àð -Ø+Ð,ÐðM#ð M#ð M#ð M#ð M#�6ñ M#ô M#ð M#ð M#ð M#r4   