o .wi @s~ddlZddlmZddlmZddlmZddededed efd d Zdeded efd d Zddededed efddZ dS)N)Tensor'scale_invariant_signal_distortion_ratio)_check_same_shapeFpredstarget zero_meanreturncCst||t|jj}|r"|tj|ddd}|tj|ddd}||}tj|ddd|tj|ddd|}dt|S)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)rrrrnoise snr_valuer^/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/audio/snr.pysignal_noise_ratios ,rcCst||ddS)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) Trrrr)rrrrr"scale_invariant_signal_noise_ratio@srcCs|r t|}|rt|}|jdks*|jddks*|jdks*|jddkr7td|jd|jd|jg|jdddR}|jg|jdddR}t|||d 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 r zZPredictions and targets are expected to have the shape (..., frequency, time, 2), but got z and .Nr) is_complexr view_as_realndimshape RuntimeErrorreshaperrrrr*complex_scale_invariant_signal_noise_ratioZs  0r&)F) rr!torchmetrics.functional.audio.sdrrtorchmetrics.utilities.checksrboolrrr&rrrrs   *