§
    ’©ºj�  ã                   ó€   — d dl mZ d dlZd dlmZ d dlmZ 	 ddededed	eeef         d
e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_r2_score_updateTÚsum_squared_obsÚsum_obsÚsum_squared_errorÚnum_obsÚsquaredÚreturnc                 óÖ   — t          j        |j        ¦  «        j        }|t          j        | ||z  |z  z
  |¬¦  «        z  }|st          j        |¦  «        }t          j        |¦  «        S )aÊ  Computes Relative Squared Error.

    Args:
        sum_squared_obs: Sum of square of all observations
        sum_obs: Sum of all observations
        sum_squared_error: Residual sum of squares
        num_obs: Number of predictions or observations
        squared: Returns RRSE value if set to False.

    Example:
        >>> target = torch.tensor([[0.5, 1], [-1, 1], [7, -6]])
        >>> preds = torch.tensor([[0, 2], [-1, 2], [8, -5]])
        >>> # RSE uses the same update function as R2 score.
        >>> sum_squared_obs, sum_obs, rss, num_obs = _r2_score_update(preds, target)
        >>> _relative_squared_error_compute(sum_squared_obs, sum_obs, rss, num_obs, squared=True)
        tensor(0.0632)

    )Úmin)ÚtorchÚfinfoÚdtypeÚepsÚclampÚsqrtÚmean)r   r   r   r	   r
   ÚepsilonÚrses          úv/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/torchmetrics/functional/regression/rse.pyÚ_relative_squared_error_computer      sg   € õ2 ŒkÐ+Ô1Ñ2Ô2Ô6€GØ
�eœk¨/¸GÀgÑ<MÐPWÑ<WÑ*WÐ]dÐeÑeÔeÑ
e€CØð ÝŒj˜‰oŒoˆÝŒ:�c‰?Œ?Ðó    ÚpredsÚtargetc                 óT   — t          | |¦  «        \  }}}}t          |||||¬¦  «        S )a"  Computes the relative squared error (RSE).

    .. math:: \text{RSE} = \frac{\sum_i^N(y_i - \hat{y_i})^2}{\sum_i^N(y_i - \overline{y})^2}

    Where :math:`y` is a tensor of target values with mean :math:`\overline{y}`, and
    :math:`\hat{y}` is a tensor of predictions.

    If `preds` and `targets` are 2D tensors, the RSE is averaged over the second dim.

    Args:
        preds: estimated labels
        target: ground truth labels
        squared: returns RRSE value if set to False
    Return:
        Tensor with RSE

    Example:
        >>> from torchmetrics.functional.regression import relative_squared_error
        >>> target = torch.tensor([3, -0.5, 2, 7])
        >>> preds = torch.tensor([2.5, 0.0, 2, 8])
        >>> relative_squared_error(preds, target)
        tensor(0.0514)

    )r
   )r   r   )r   r   r
   r   r   Úrssr	   s          r   Úrelative_squared_errorr   6   s6   € õ2 .>¸eÀVÑ-LÔ-LÑ*€O�W˜c 7Ý*¨?¸GÀSÈ'Ð[bÐcÑcÔcÐcr   )T)
Útypingr   r   r   Ú%torchmetrics.functional.regression.r2r   ÚintÚboolr   r   © r   r   ú<module>r$      sñ   ðð Ð Ð Ð Ð Ð à €€€Ø Ð Ð Ð Ð Ð à BÐ BÐ BÐ BÐ BÐ Bð ðð Øðàðð ðð �3˜�;Ôð	ð
 ðð ðð ð ð ð@dð d &ð d°&ð dÀ4ð dÐSYð dð dð dð dð dð dr   