o
    yi2                     @   sT   d dl mZ d dlZd dlmZmZ d dlmZmZ d dlm	Z	 G dd de	Z
dS )    )AnyN)Tensortensor)_mean_squared_error_compute_mean_squared_error_update)Metricc                       st   e Zd ZU dZdZdZdZeed< eed< 	dde	de
dd	f fd
dZdededd	fddZdefddZ  ZS )MeanSquaredErrora/  Computes `mean squared error`_ (MSE):

    .. math:: \text{MSE} = \frac{1}{N}\sum_i^N(y_i - \hat{y_i})^2

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

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

    - ``preds`` (:class:`~torch.Tensor`): Predictions from model
    - ``target`` (:class:`~torch.Tensor`): Ground truth values

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

    - ``mean_squared_error`` (:class:`~torch.Tensor`): A tensor with the mean squared error

    Args:
        squared: If True returns MSE value, if False returns RMSE value.
        kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

    Example:
        >>> from torchmetrics import MeanSquaredError
        >>> target = torch.tensor([2.5, 5.0, 4.0, 8.0])
        >>> preds = torch.tensor([3.0, 5.0, 2.5, 7.0])
        >>> mean_squared_error = MeanSquaredError()
        >>> mean_squared_error(preds, target)
        tensor(0.8750)
    TFsum_squared_errortotalsquaredkwargsreturnNc                    sD   t  jdi | | jdtddd | jdtddd || _d S )Nr	   g        sum)defaultdist_reduce_fxr
   r    )super__init__	add_stater   r   )selfr   r   	__class__r   O/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/regression/mse.pyr   9   s   
zMeanSquaredError.__init__predstargetc                 C   s.   t ||\}}|  j|7  _|  j|7  _dS )z*Update state with predictions and targets.N)r   r	   r
   )r   r   r   r	   n_obsr   r   r   updateD   s   zMeanSquaredError.updatec                 C   s   t | j| j| jdS )z'Computes mean squared error over state.)r   )r   r	   r
   r   )r   r   r   r   computeK   s   zMeanSquaredError.compute)T)__name__
__module____qualname____doc__is_differentiablehigher_is_betterfull_state_updater   __annotations__boolr   r   r   r   __classcell__r   r   r   r   r      s"   
 r   )typingr   torchr   r   &torchmetrics.functional.regression.mser   r   torchmetrics.metricr   r   r   r   r   r   <module>   s   