§
    ’©ºj¸  ã                   óX  — d dl mZmZ d dlZd dlmZmZ d dlmZ d dlm	Z	m
Z
 	 	 dded	ed
ededed         defd„Z	 ddededeeeeedf         f                  deeef         fd„Z	 	 	 ddeded
eeeeef         f         deded         deeeeedf         f                  defd„ZdS )é    )ÚOptionalÚUnionN)ÚTensorÚtensor)ÚLiteral)Úrank_zero_warnÚreduceç      $@Úelementwise_meanÚsum_squared_errorÚnum_obsÚ
data_rangeÚbaseÚ	reduction)r   ÚsumÚnoneNÚreturnc                 óÐ   — dt          j        |¦  «        z  t          j        | |z  ¦  «        z
  }|dt          j        t          |¦  «        ¦  «        z  z  }t          ||¬¦  «        S )aÃ  Compute peak signal-to-noise ratio.

    Args:
        sum_squared_error: Sum of square of errors over all observations
        num_obs: Number of predictions or observations
        data_range: the range of the data. If None, it is determined from the data (max - min).
           ``data_range`` must be given when ``dim`` is not None.
        base: a base of a logarithm to use
        reduction: a method to reduce metric score over labels.

            - ``'elementwise_mean'``: takes the mean (default)
            - ``'sum'``: takes the sum
            - ``'none'`` or ``None``: no reduction will be applied

    Example:
        >>> preds = torch.tensor([[0.0, 1.0], [2.0, 3.0]])
        >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]])
        >>> data_range = target.max() - target.min()
        >>> sum_squared_error, num_obs = _psnr_update(preds, target)
        >>> _psnr_compute(sum_squared_error, num_obs, data_range)
        tensor(2.5527)

    é   é
   )r   )ÚtorchÚlogr   r	   )r   r   r   r   r   Úpsnr_base_eÚ	psnr_valss          úr/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/image/psnr.pyÚ_psnr_computer      s_   € ð< •e”i 
Ñ+Ô+Ñ+­e¬iÐ8IÈGÑ8SÑ.TÔ.TÑT€KØ˜r¥E¤I­f°T©l¬lÑ$;Ô$;Ñ;Ñ<€IÝ�) yÐ1Ñ1Ô1Ð1ó    ÚpredsÚtargetÚdim.c                 ó  — |                       ¦   «         s|                      t          j        ¦  «        } |                      ¦   «         s|                     t          j        ¦  «        }|€Vt          j        t          j        | |z
  d¦  «        ¦  «        }t          |                     ¦   «         |j        ¬¦  «        }||fS | |z
  }t          j        ||z  |¬¦  «        }t          |t          ¦  «        r|gnt          |¦  «        }|s)t          |                     ¦   «         |j        ¬¦  «        }nUt          |                     ¦   «         |j        ¬¦  «        |                              ¦   «         }|                     |¦  «        }||fS )aZ  Update and return variables required to compute peak signal-to-noise ratio.

    Args:
        preds: Predicted tensor
        target: Ground truth tensor
        dim: Dimensions to reduce PSNR scores over provided as either an integer or a list of integers.
            Default is None meaning scores will be reduced across all dimensions.

    Nr   )Údevice©r    )Úis_floating_pointÚtor   Úfloat32r   Úpowr   Únumelr"   Ú
isinstanceÚintÚlistÚsizeÚprodÚ	expand_as)r   r   r    r   r   ÚdiffÚdim_lists          r   Ú_psnr_updater1   :   sR  € ð ×"Ò"Ñ$Ô$ð (Ø—’�œÑ'Ô'ˆØ×#Ò#Ñ%Ô%ð *Ø—’�5œ=Ñ)Ô)ˆà
€{Ý!œI¥e¤i°¸±ÀÑ&BÔ&BÑCÔCÐÝ˜Ÿš™œ°´Ð>Ñ>Ô>ˆØ  'Ð)Ð)à�6‰>€DÝœ	 $¨¡+°3Ð7Ñ7Ô7Ðå" 3­Ñ,Ô,Ð;�ˆuˆuµ$°s±)´)€HØð 7Ý˜Ÿš™œ°´Ð>Ñ>Ô>ˆˆå˜Ÿš™œ¨v¬}Ð=Ñ=Ô=¸hÔG×LÒLÑNÔNˆØ×#Ò#Ð$5Ñ6Ô6ˆà˜gÐ%Ð%r   c                 ó¶  — |€|dk    rt          d|› d�¦  «         t          |t          ¦  «        ret          j        | |d         |d         ¬¦  «        } t          j        ||d         |d         ¬¦  «        }t          |d         |d         z
  ¦  «        }nt          t          |¦  «        ¦  «        }t          | ||¬¦  «        \  }}t          |||||¬	¦  «        S )
a±  Compute the peak signal-to-noise ratio.

    Args:
        preds: estimated signal
        target: groun truth signal
        data_range:
            the range of the data. If a tuple is provided then the range is calculated as the difference and
            input is clamped between the values.
        base: a base of a logarithm to use
        reduction: a method to reduce metric score over labels.

            - ``'elementwise_mean'``: takes the mean (default)
            - ``'sum'``: takes the sum
            - ``'none'`` or None``: no reduction will be applied

        dim:
            Dimensions to reduce PSNR scores over provided as either an integer or a list of integers. Default is
            None meaning scores will be reduced across all dimensions.

    Return:
        Tensor with PSNR score

    Example:
        >>> from torchmetrics.functional.image import peak_signal_noise_ratio
        >>> pred = torch.tensor([[0.0, 1.0], [2.0, 3.0]])
        >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]])
        >>> peak_signal_noise_ratio(pred, target, data_range=3.0)
        tensor(2.5527)

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

    Nr   zThe `reduction=z.` will not have any effect when `dim` is None.r   é   )ÚminÚmaxr#   )r   r   )	r   r)   Útupler   Úclampr   Úfloatr1   r   )	r   r   r   r   r   r    Údata_range_valr   r   s	            r   Úpeak_signal_noise_ratior:   _   sã   € ðR €{�yÐ$6Ò6Ð6ÝÐb¨ÐbÐbÐbÑcÔcÐcå�*�eÑ$Ô$ð 3Ý”˜E z°!¤}¸*ÀQ¼-ÐHÑHÔHˆÝ”˜V¨°A¬¸JÀq¼MÐJÑJÔJˆÝ 
¨1¤°
¸1´Ñ =Ñ>Ô>ˆˆå¥ jÑ 1Ô 1Ñ2Ô2ˆå!-¨e°VÀÐ!EÑ!EÔ!EÑÐ�wÝÐ*¨G°^È$ÐZcÐdÑdÔdÐdr   )r
   r   )N)r
   r   N)Útypingr   r   r   r   r   Útyping_extensionsr   Útorchmetrics.utilitiesr   r	   r8   r   r*   r6   r1   r:   © r   r   ú<module>r?      sÛ  ðð #Ð "Ð "Ð "Ð "Ð "Ð "Ð "à €€€Ø  Ð  Ð  Ð  Ð  Ð  Ð  Ð  Ø %Ð %Ð %Ð %Ð %Ð %à 9Ð 9Ð 9Ð 9Ð 9Ð 9Ð 9Ð 9ð ØBTð 2ð  2Øð 2àð 2ð ð 2ð ð	 2ð
 Ð>Ô?ð 2ð ð 2ð  2ð  2ð  2ðL 26ð"&ð "&Øð"&àð"&ð 
�%˜˜U 3¨ 8œ_Ð,Ô-Ô	.ð"&ð ˆ6�6ˆ>Ôð	"&ð "&ð "&ð "&ðR ØBTØ15ð4eð 4eØð4eàð4eð �e˜U 5¨% <Ô0Ð0Ô1ð4eð ð	4eð
 Ð>Ô?ð4eð 
�%˜˜U 3¨ 8œ_Ð,Ô-Ô	.ð4eð ð4eð 4eð 4eð 4eð 4eð 4er   