iddlmZddlmZmZmZddlZddlmZmZddl m Z m Z ddl m Z ddlmZddlmZmZesd gZGd d e Zy) )Sequence)AnyOptionalUnionN)Tensortensor)_mean_squared_error_compute_mean_squared_error_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPEzMeanSquaredError.plotc eZdZUdZdZdZdZdZee d<e e d<e e d< dde d e d e d d ffd Zde de d d fdZd e fdZ ddeee ee fdeed efdZxZS)MeanSquaredErrora`Compute `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. num_outputs: Number of outputs in multioutput setting kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example:: Single output mse computation: >>> from torch import tensor >>> from torchmetrics.regression import MeanSquaredError >>> target = tensor([2.5, 5.0, 4.0, 8.0]) >>> preds = tensor([3.0, 5.0, 2.5, 7.0]) >>> mean_squared_error = MeanSquaredError() >>> mean_squared_error(preds, target) tensor(0.8750) Example:: Multioutput mse computation: >>> from torch import tensor >>> from torchmetrics.regression import MeanSquaredError >>> target = tensor([[0.0, 0.0, 0.0], [0.0, 0.0, 0.0]]) >>> preds = tensor([[1.0, 2.0, 3.0], [1.0, 2.0, 3.0]]) >>> mean_squared_error = MeanSquaredError(num_outputs=3) >>> mean_squared_error(preds, target) tensor([1., 4., 9.]) TFgplot_lower_boundsum_squared_errortotalsquared num_outputskwargsreturnNc Jt|di|t|tst d|||_t|t r|dkDst d|||_|jdtj|d|jdtddy) Nz4Expected argument `squared` to be a boolean but got rz6Expected num_outputs to be a positive integer but got rsum)defaultdist_reduce_fxr) super__init__ isinstancebool ValueErrorrintr add_statetorchzerosr)selfrrr __class__s p/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/regression/mse.pyrzMeanSquaredError.__init__Rs "6"'4(ST[S\]^ ^ ;,qUVaUbcd d& *EKK 4L]bc wq %Hpredstargetct|||j\}}|xj|z c_|xj|z c_y)z*Update state with predictions and targets.)rN)r rrr)r&r*r+rnum_obss r(updatezMeanSquaredError.updatees=%?v[_[k[k%l"7 "33 g r)cZt|j|j|jS)z&Compute mean squared error over state.)r)r rrr)r&s r(computezMeanSquaredError.computels"*4+A+A4::W[WcWcddr)valaxc&|j||S)aPlot 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 >>> from torch import randn >>> # Example plotting a single value >>> from torchmetrics.regression import MeanSquaredError >>> metric = MeanSquaredError() >>> metric.update(randn(10,), randn(10,)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> from torch import randn >>> # Example plotting multiple values >>> from torchmetrics.regression import MeanSquaredError >>> metric = MeanSquaredError() >>> values = [] >>> for _ in range(10): ... values.append(metric(randn(10,), randn(10,))) >>> fig, ax = metric.plot(values) )_plot)r&r1r2s r(plotzMeanSquaredError.plotpsPzz#r""r))T)NN)__name__ __module__ __qualname____doc__is_differentiablehigher_is_betterfull_state_updaterfloat__annotations__rr r"rrr.r0rrrr rr5 __classcell__)r's@r(rrs*X!e! MIII I  I&FFtee _c(#E&(6*:":;<(#IQRZI[(# (#r)r)collections.abcrtypingrrrr$rr&torchmetrics.functional.regression.mser r torchmetrics.metricr torchmetrics.utilities.importsr torchmetrics.utilities.plotr r__doctest_skip__rrr)r(rHs<%'' j&@@/0{#v{#r)