i xddlZddlmZddlmZddlmZd dedededefd Zdededefd Zd dedededefd Z y) N)Tensor'scale_invariant_signal_distortion_ratio)_check_same_shapepredstarget zero_meanreturnct||tj|jj}|r6|tj |ddz }|tj |ddz }||z }tj |dzd|ztj |dzd|zz }dtj|zS)aCalculate `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. Args: preds: float tensor with shape ``(...,time)`` target: float tensor with shape ``(...,time)`` zero_mean: if to zero mean target and preds or not Returns: Float tensor with shape ``(...,)`` of SNR values per sample Raises: RuntimeError: If ``preds`` and ``target`` does not have the same shape Example: >>> from torchmetrics.functional.audio import signal_noise_ratio >>> target = torch.tensor([3.0, -0.5, 2.0, 7.0]) >>> preds = torch.tensor([2.5, 0.0, 2.0, 8.0]) >>> signal_noise_ratio(preds, target) tensor(16.1805) T)dimkeepdim)r )rtorchfinfodtypeepsmeansumlog10)rrr rnoise snr_values v/Volumes/fast/ai/experiments/voice-extract-mac/.venv/lib/python3.12/site-packages/torchmetrics/functional/audio/snr.pysignal_noise_ratiors:eV$ ++ekk " & &C%**VTBB 5b$?? UNE619"-3 %(PR8SVY8YZI  I& &&ct||dS)a`Scale-invariant signal-to-noise ratio`_ (SI-SNR). Args: preds: float tensor with shape ``(...,time)`` target: float tensor with shape ``(...,time)`` Returns: Float tensor with shape ``(...,)`` of SI-SNR values per sample Raises: RuntimeError: If ``preds`` and ``target`` does not have the same shape Example: >>> import torch >>> from torchmetrics.functional.audio import scale_invariant_signal_noise_ratio >>> target = torch.tensor([3.0, -0.5, 2.0, 7.0]) >>> preds = torch.tensor([2.5, 0.0, 2.0, 8.0]) >>> scale_invariant_signal_noise_ratio(preds, target) tensor(15.0918) Trrr r)rrs r"scale_invariant_signal_noise_ratior@s. 3vY] ^^rc|jrtj|}|jrtj|}|jdks3|jddk7s!|jdks|jddk7r&t d|jd|jd|j g|jddd}|j g|jddd}t||| S) aX`Complex scale-invariant signal-to-noise ratio`_ (C-SI-SNR). Args: preds: real float tensor with shape ``(...,frequency,time,2)`` or complex float tensor with shape ``(..., frequency,time)`` target: real float tensor with shape ``(...,frequency,time,2)`` or complex float tensor with shape ``(..., frequency,time)`` zero_mean: When set to True, the mean of all signals is subtracted prior to computation of the metrics Returns: Float tensor with shape ``(...,)`` of C-SI-SNR values per sample Raises: RuntimeError: 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: >>> from torch import randn >>> from torchmetrics.functional.audio import complex_scale_invariant_signal_noise_ratio >>> preds = randn((1,257,100,2)) >>> target = randn((1,257,100,2)) >>> complex_scale_invariant_signal_noise_ratio(preds, target) tensor([-38.8832]) r rzZPredictions and targets are expected to have the shape (..., frequency, time, 2), but got z and .Nr) is_complexr view_as_realndimshape RuntimeErrorreshaperrs r*complex_scale_invariant_signal_noise_ratior*Zs6 ""5) ##F+ Q%++b/Q.FKK!Ov||TVGW[\G\  }E&,,q :  EMM 05;;s+ 0R 0E V^^ 3V\\#2. 3 3F 2vYb ccr)F) rr!torchmetrics.functional.audio.sdrrtorchmetrics.utilities.checksrboolrrr*rrr/s| U;''f''f''''RX''T_f_f__4)df)df)dY])djp)dr