a  d1@sddlmZmZmZmZddlmZmZddlm Z m Z m Z ddl m Z ddlmZddlmZmZespgdZGdd d e ZGd d d e ZGd d d e ZdS))AnyOptionalSequenceUnion)Tensortensor)*complex_scale_invariant_signal_noise_ratio"scale_invariant_signal_noise_ratiosignal_noise_ratio)Metric)_MATPLOTLIB_AVAILABLE)_AX_TYPE_PLOT_OUT_TYPE)SignalNoiseRatio.plot#ScaleInvariantSignalNoiseRatio.plot*ComplexScaleInvariantSignalNoiseRatio.plotcseZdZUdZdZeed<dZeed<dZeed<e ed<e ed<d Z e e ed <d Z e e ed <deed d fd d Ze e d dddZe dddZde ee ee fe eedddZZS)SignalNoiseRatioa3Calculate `Signal-to-noise ratio`_ (SNR_) meric for evaluating quality of audio. .. math:: \text{SNR} = \frac{P_{signal}}{P_{noise}} where :math:`P` denotes the power of each signal. The SNR metric compares the level of the desired signal to the level of background noise. Therefore, a high value of SNR means that the audio is clear. As input to `forward` and `update` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): float tensor with shape ``(...,time)`` - ``target`` (:class:`~torch.Tensor`): float tensor with shape ``(...,time)`` As output of `forward` and `compute` the metric returns the following output - ``snr`` (:class:`~torch.Tensor`): float scalar tensor with average SNR value over samples Args: zero_mean: if to zero mean target and preds or not kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: TypeError: if target and preds have a different shape Example: >>> from torch import tensor >>> from torchmetrics.audio import SignalNoiseRatio >>> target = tensor([3.0, -0.5, 2.0, 7.0]) >>> preds = tensor([2.5, 0.0, 2.0, 8.0]) >>> snr = SignalNoiseRatio() >>> snr(preds, target) tensor(16.1805) Ffull_state_updateTis_differentiablehigher_is_bettersum_snrtotalNplot_lower_boundplot_upper_bound zero_meankwargsreturnc sDtjfi|||_|jdtddd|jdtddddS)NrsumdefaultZdist_reduce_fxrr)super__init__r add_staterselfrr __class___/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/audio/snr.pyr#OszSignalNoiseRatio.__init__predstargetrcCs8t|||jd}|j|7_|j|7_dS*Update state with predictions and targets.)r,r-rN)r rrrrnumel)r&r,r-Z snr_batchr)r)r*updateZszSignalNoiseRatio.updatercCs |j|jSzCompute metric.)rrr&r)r)r*computeaszSignalNoiseRatio.computevalaxrcCs |||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 >>> # Example plotting a single value >>> import torch >>> from torchmetrics.audio import SignalNoiseRatio >>> metric = SignalNoiseRatio() >>> metric.update(torch.rand(4), torch.rand(4)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.audio import SignalNoiseRatio >>> metric = SignalNoiseRatio() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(4), torch.rand(4))) >>> fig_, ax_ = metric.plot(values) Z_plotr&r7r8r)r)r*plotes(r)F)NN)__name__ __module__ __qualname____doc__rbool__annotations__rrrrrfloatrrr#r1r5rrr rr; __classcell__r)r)r'r*r#s* #    rcseZdZUdZdZeed<eed<dZdZe e ed<dZ e e ed<e ddfd d Z eedd d d ZedddZdeeeedfe eedddZZS)ScaleInvariantSignalNoiseRatioa7Calculate `Scale-invariant signal-to-noise ratio`_ (SI-SNR) metric for evaluating quality of audio. As input to `forward` and `update` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): float tensor with shape ``(...,time)`` - ``target`` (:class:`~torch.Tensor`): float tensor with shape ``(...,time)`` As output of `forward` and `compute` the metric returns the following output - ``si_snr`` (:class:`~torch.Tensor`): float scalar tensor with average SI-SNR value over samples Args: kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: TypeError: if target and preds have a different shape Example: >>> import torch >>> from torch import tensor >>> from torchmetrics.audio import ScaleInvariantSignalNoiseRatio >>> target = tensor([3.0, -0.5, 2.0, 7.0]) >>> preds = tensor([2.5, 0.0, 2.0, 8.0]) >>> si_snr = ScaleInvariantSignalNoiseRatio() >>> si_snr(preds, target) tensor(15.0918) T sum_si_snrrNrr)rrc s>tjfi||jdtddd|jdtddddS)NrErrr rr)r"r#r$r)r&rr'r)r*r#sz'ScaleInvariantSignalNoiseRatio.__init__r+cCs4t||d}|j|7_|j|7_dS)r/)r,r-N)r rErrr0)r&r,r-Z si_snr_batchr)r)r*r1s z%ScaleInvariantSignalNoiseRatio.updater2cCs |j|jSr3)rErr4r)r)r*r5sz&ScaleInvariantSignalNoiseRatio.computer6cCs |||S)a6Plot 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.audio import ScaleInvariantSignalNoiseRatio >>> metric = ScaleInvariantSignalNoiseRatio() >>> metric.update(torch.rand(4), torch.rand(4)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.audio import ScaleInvariantSignalNoiseRatio >>> metric = ScaleInvariantSignalNoiseRatio() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(4), torch.rand(4))) >>> fig_, ax_ = metric.plot(values) r9r:r)r)r*r;s&r)NN)r<r=r>r?rrrArrrrBrrr#r1r5rrr rr;rCr)r)r'r*rDs  rDcseZdZUdZdZeed<eed<dZdZe e ed<dZ e e ed<de e dd fd d Zeedd d dZedddZdeeeedfe eedddZZS)%ComplexScaleInvariantSignalNoiseRatioa!Calculate `Complex scale-invariant signal-to-noise ratio`_ (C-SI-SNR) metric for evaluating quality of audio. As input to `forward` and `update` the metric accepts the following input - ``preds`` (:class:`~torch.Tensor`): real float tensor with shape ``(...,frequency,time,2)`` or complex float tensor with shape ``(..., frequency,time)`` - ``target`` (:class:`~torch.Tensor`): real float tensor with shape ``(...,frequency,time,2)`` or complex float tensor with shape ``(..., frequency,time)`` As output of `forward` and `compute` the metric returns the following output - ``c_si_snr`` (:class:`~torch.Tensor`): float scalar tensor with average C-SI-SNR value over samples Args: zero_mean: if to zero mean target and preds or not kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``zero_mean`` is not an bool TypeError: If ``preds`` is not the shape (..., frequency, time, 2) (after being converted to real if it is complex). If ``preds`` and ``target`` does not have the same shape. Example: >>> import torch >>> from torch import tensor >>> from torchmetrics.audio import ComplexScaleInvariantSignalNoiseRatio >>> g = torch.manual_seed(1) >>> preds = torch.randn((1,257,100,2)) >>> target = torch.randn((1,257,100,2)) >>> c_si_snr = ComplexScaleInvariantSignalNoiseRatio() >>> c_si_snr(preds, target) tensor(-63.4849) T ci_snr_sumnumNrrFrc s\tjfi|t|ts*td|||_|jdtddd|jdtddddS)Nz5Expected argument `zero_mean` to be an bool, but got rGrrr rHr)r"r# isinstancer@ ValueErrorrr$rr%r'r)r*r#!s  z.ComplexScaleInvariantSignalNoiseRatio.__init__r+cCs8t|||jd}|j|7_|j|7_dSr.)rrrGrrHr0)r&r,r-vr)r)r*r1.sz,ComplexScaleInvariantSignalNoiseRatio.updater2cCs |j|jSr3)rGrHr4r)r)r*r55sz-ComplexScaleInvariantSignalNoiseRatio.computer6cCs |||S)azPlot 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.audio import ComplexScaleInvariantSignalNoiseRatio >>> metric = ComplexScaleInvariantSignalNoiseRatio() >>> metric.update(torch.rand(1,257,100,2), torch.rand(1,257,100,2)) >>> fig_, ax_ = metric.plot() .. plot:: :scale: 75 >>> # Example plotting multiple values >>> import torch >>> from torchmetrics.audio import ComplexScaleInvariantSignalNoiseRatio >>> metric = ComplexScaleInvariantSignalNoiseRatio() >>> values = [ ] >>> for _ in range(10): ... values.append(metric(torch.rand(1,257,100,2), torch.rand(1,257,100,2))) >>> fig_, ax_ = metric.plot(values) r9r:r)r)r*r;9s&r)F)NN)r<r=r>r?rrrArrrrBrr@rr#r1r5rrr rr;rCr)r)r'r*rFs & rFN)typingrrrrZtorchrrZ!torchmetrics.functional.audio.snrrr r Ztorchmetrics.metricr Ztorchmetrics.utilities.importsr Ztorchmetrics.utilities.plotr rZ__doctest_skip__rrDrFr)r)r)r*s  mc