o
    .wi5                     @   s   d dl mZ d dlmZmZmZ d dl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mZ es;d	gZG d
d deZdS )    )Sequence)AnyOptionalUnionN)Tensor)_rmse_sw_compute_rmse_sw_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE+RootMeanSquaredErrorUsingSlidingWindow.plotc                       s   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d	< d
Zee ed< eed< 	ddedeeef dd
f fddZdededd
fddZdee fddZ	
ddeeeee f  dee defddZ  ZS )&RootMeanSquaredErrorUsingSlidingWindowa@  Computes Root Mean Squared Error (RMSE) using sliding window.

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

    - ``preds`` (:class:`~torch.Tensor`): Predictions from model of shape ``(N,C,H,W)``
    - ``target`` (:class:`~torch.Tensor`): Ground truth values of shape ``(N,C,H,W)``

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

    - ``rmse_sw`` (:class:`~torch.Tensor`): returns float scalar tensor with average RMSE-SW value over sample

    Args:
        window_size: Sliding window used for rmse calculation
        kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

    Example:
        >>> from torch import rand
        >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
        >>> preds = rand(4, 3, 16, 16)
        >>> target = rand(4, 3, 16, 16)
        >>> rmse_sw = RootMeanSquaredErrorUsingSlidingWindow()
        >>> rmse_sw(preds, target)
        tensor(0.4158)

    Raises:
        ValueError: If ``window_size`` is not a positive integer.

    Fhigher_is_betterTis_differentiablefull_state_update        plot_lower_boundrmse_val_sumNrmse_maptotal_images   window_sizekwargsreturnc                    sl   t  jdi | t|trt|tr|dk rtd|| _| jdtddd | jdtddd d S )	N   z<Argument `window_size` is expected to be a positive integer.r   r   sum)defaultdist_reduce_fxr    )	super__init__
isinstanceint
ValueErrorr   	add_statetorchtensor)selfr   r   	__class__r   W/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/image/rmse_sw.pyr!   E   s   z/RootMeanSquaredErrorUsingSlidingWindow.__init__predstargetc                 C   sX   | j du r|jdd }tj||j|jd| _ t||| j| j| j | j	\| _| _ | _	dS )z*Update state with predictions and targets.Nr   )dtypedevice)
r   shaper&   zerosr.   r/   r   r   r   r   )r(   r,   r-   
_img_shaper   r   r+   updateR   s   
z-RootMeanSquaredErrorUsingSlidingWindow.updatec                 C   s(   | j dusJ t| j| j | j\}}|S )zWCompute Root Mean Squared Error (using sliding window) and potentially return RMSE map.N)r   r   r   r   )r(   rmse_r   r   r+   compute\   s   z.RootMeanSquaredErrorUsingSlidingWindow.computevalaxc                 C   s   |  ||S )a  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

            >>> # Example plotting a single value
            >>> import torch
            >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
            >>> metric = RootMeanSquaredErrorUsingSlidingWindow()
            >>> metric.update(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16))
            >>> fig_, ax_ = metric.plot()

        .. plot::
            :scale: 75

            >>> # Example plotting multiple values
            >>> import torch
            >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
            >>> metric = RootMeanSquaredErrorUsingSlidingWindow()
            >>> values = [ ]
            >>> for _ in range(10):
            ...     values.append(metric(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16)))
            >>> fig_, ax_ = metric.plot(values)

        )_plot)r(   r7   r8   r   r   r+   plotb   s   (r   )r   )NN)__name__
__module____qualname____doc__r   bool__annotations__r   r   r   floatr   r   r   r#   dictstrr   r!   r3   r6   r   r   r   r   r:   __classcell__r   r   r)   r+   r      s6   
 

r   )collections.abcr   typingr   r   r   r&   r   %torchmetrics.functional.image.rmse_swr   r   torchmetrics.metricr	   torchmetrics.utilities.importsr
   torchmetrics.utilities.plotr   r   __doctest_skip__r   r   r   r   r+   <module>   s   