a  d!@sddlmZmZmZmZddlZddlmZddlmZm Z ddl m Z ddl m Z ddlmZmZe sndgZGd d d e ZdS) )AnyOptionalSequenceUnionN)Tensor)_log_cosh_error_compute_log_cosh_error_update)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPELogCoshError.plotcseZdZUdZdZdZdZdZee d<e e d<e e d<de e d d fd d Z e e d d ddZe dddZdeee ee feeedddZZS) LogCoshErroraOCompute the `LogCosh Error`_. .. math:: \text{LogCoshError} = \log\left(\frac{\exp(\hat{y} - y) + \exp(\hat{y - y})}{2}\right) 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`): Estimated labels with shape ``(batch_size,)`` or ``(batch_size, num_outputs)`` - ``target`` (:class:`~torch.Tensor`): Ground truth labels with shape ``(batch_size,)`` or ``(batch_size, num_outputs)`` As output of ``forward`` and ``compute`` the metric returns the following output: - ``log_cosh_error`` (:class:`~torch.Tensor`): A tensor with the log cosh error Args: num_outputs: Number of outputs in multioutput setting kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example (single output regression):: >>> from torchmetrics.regression import LogCoshError >>> preds = torch.tensor([3.0, 5.0, 2.5, 7.0]) >>> target = torch.tensor([2.5, 5.0, 4.0, 8.0]) >>> log_cosh_error = LogCoshError() >>> log_cosh_error(preds, target) tensor(0.3523) Example (multi output regression):: >>> from torchmetrics.regression import LogCoshError >>> preds = torch.tensor([[3.0, 5.0, 1.2], [-2.1, 2.5, 7.0]]) >>> target = torch.tensor([[2.5, 5.0, 1.3], [0.3, 4.0, 8.0]]) >>> log_cosh_error = LogCoshError(num_outputs=3) >>> log_cosh_error(preds, target) tensor([0.9176, 0.4277, 0.2194]) TFgplot_lower_boundsum_log_cosh_errortotalN) num_outputskwargsreturnc shtjfi|t|ts2|dkr2td|||_|jdt|dd|jdt ddddS)NrzDExpected argument `num_outputs` to be an int larger than 0, but got rsum)defaultZdist_reduce_fxrr) super__init__ isinstanceint ValueErrorrZ add_statetorchzerosZtensor)selfrr __class__i/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/regression/log_cosh.pyrLs zLogCoshError.__init__)predstargetrcCs2t|||j\}}|j|7_|j|7_dS)zUpdate state with predictions and targets. Raises: ValueError: If ``preds`` or ``target`` has multiple outputs when ``num_outputs=1`` N)rrrr)rr$r%rZn_obsr"r"r#updateUszLogCoshError.update)rcCst|j|jS)z!Compute LogCosh error over state.)rrr)rr"r"r#computeaszLogCoshError.compute)valaxrcCs |||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 LogCoshError >>> metric = LogCoshError() >>> 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 LogCoshError >>> metric = LogCoshError() >>> values = [] >>> for _ in range(10): ... values.append(metric(randn(10,), randn(10,))) >>> fig, ax = metric.plot(values) )Z_plot)rr(r)r"r"r#plotes(r )r)NN)__name__ __module__ __qualname____doc__Zis_differentiableZhigher_is_betterZfull_state_updaterfloat__annotations__rrrrr&r'rrrr r r* __classcell__r"r"r r#rs '   r)typingrrrrrrZ+torchmetrics.functional.regression.log_coshrrZtorchmetrics.metricr Ztorchmetrics.utilities.importsr Ztorchmetrics.utilities.plotr r Z__doctest_skip__rr"r"r"r#s