§
    ’©ºj'  ã            
       ó˜   — d dl mZ d dlZd dlmZ d dlmZ dedededeeef         fd	„Zd
edeeef         defd„Z	ddedededefd„Z
dS )é    )ÚUnionN)ÚTensor)Ú_check_same_shapeÚpredsÚtargetÚnum_outputsÚreturnc                 ój  — t          | |¦  «         |dk    r*|                      d¦  «        } |                     d¦  «        }| j        r| n|                      ¦   «         } |j        r|n|                     ¦   «         }t	          j        t	          j        | |z
  ¦  «        d¬¦  «        }||j        d         fS )a  Update and returns variables required to compute Mean Absolute Error.

    Check for same shape of input tensors.

    Args:
        preds: Predicted tensor
        target: Ground truth tensor
        num_outputs: Number of outputs in multioutput setting

    é   éÿÿÿÿr   )Údim)r   ÚviewÚis_floating_pointÚfloatÚtorchÚsumÚabsÚshape)r   r   r   Úsum_abs_errors       úv/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/regression/mae.pyÚ_mean_absolute_error_updater      s¢   € õ �e˜VÑ$Ô$Ð$Ø�aÒÐØ—
’
˜2‘”ˆØ—’˜R‘”ˆØÔ,Ð?ˆEˆE°%·+²+±-´-€EØÔ/ÐCˆVˆV°V·\²\±^´^€FÝ”I�eœi¨°©Ñ7Ô7¸QÐ?Ñ?Ô?€MØ˜&œ, qœ/Ð)Ð)ó    r   Únum_obsc                 ó   — | |z  S )a×  Compute Mean Absolute Error.

    Args:
        sum_abs_error: Sum of absolute value of errors over all observations
        num_obs: Number of predictions or observations

    Example:
        >>> preds = torch.tensor([0., 1, 2, 3])
        >>> target = torch.tensor([0., 1, 2, 2])
        >>> sum_abs_error, num_obs = _mean_absolute_error_update(preds, target, num_outputs=1)
        >>> _mean_absolute_error_compute(sum_abs_error, num_obs)
        tensor(0.2500)

    © )r   r   s     r   Ú_mean_absolute_error_computer   +   s   € ð ˜7Ñ"Ð"r   r   c                 óL   — t          | ||¬¦  «        \  }}t          ||¦  «        S )aÆ  Compute mean absolute error.

    Args:
        preds: estimated labels
        target: ground truth labels
        num_outputs: Number of outputs in multioutput setting

    Return:
        Tensor with MAE

    Example:
        >>> from torchmetrics.functional.regression import mean_absolute_error
        >>> x = torch.tensor([0., 1, 2, 3])
        >>> y = torch.tensor([0., 1, 2, 2])
        >>> mean_absolute_error(x, y)
        tensor(0.2500)

    )r   )r   r   )r   r   r   r   r   s        r   Úmean_absolute_errorr   =   s.   € õ& 9¸ÀÐT_Ð`Ñ`Ô`Ñ€M�7Ý'¨°wÑ?Ô?Ð?r   )r   )Útypingr   r   r   Útorchmetrics.utilities.checksr   ÚintÚtupler   r   r   r   r   r   ú<module>r#      s  ðð Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à ;Ð ;Ð ;Ð ;Ð ;Ð ;ð* vð *°vð *ÈCð *ÐTYÐZ`ÐbeÐZeÔTfð *ð *ð *ð *ð*#°ð #ÀÀsÈFÀ{ÔASð #ÐX^ð #ð #ð #ð #ð$@ð @˜vð @¨vð @ÀCð @ÐPVð @ð @ð @ð @ð @ð @r   