:jddlmZmZddlZddlmZmZddlmZddlm Z m Z  ddededed e d ed d ef d Z ddededeee ee dffd eeeffdZ ddededee ee e ffd e d ed deee ee dffd efdZy))OptionalUnionN)Tensortensor)Literal)rank_zero_warnreducesum_squared_errornum_obs data_rangebase reduction)elementwise_meansumnoneNreturncdtj|ztj||z z }|dtjt|z z}t||S)aCompute peak signal-to-noise ratio. Args: sum_squared_error: Sum of square of errors over all observations num_obs: Number of predictions or observations data_range: the range of the data. If None, it is determined from the data (max - min). ``data_range`` must be given when ``dim`` is not None. base: a base of a logarithm to use reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'`` or ``None``: no reduction will be applied Example: >>> preds = torch.tensor([[0.0, 1.0], [2.0, 3.0]]) >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]]) >>> data_range = target.max() - target.min() >>> sum_squared_error, num_obs = _psnr_update(preds, target) >>> _psnr_compute(sum_squared_error, num_obs, data_range) tensor(2.5527)  )r)torchlogrr )r r r r r psnr_base_e psnr_valss w/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/functional/image/psnr.py _psnr_computersT<eii ++eii8IG8S.TTKrEIIfTl$;; ')) 6>D $+37"3,u$s)H  > g %%v}}=hGLLN##$56 g %%rcZ||dk7rtd|dt|trQtj||d|d}tj||d|d}t |d|dz }nt t |}t|||\}}t|||||S) aCompute the peak signal-to-noise ratio. Args: preds: estimated signal target: groun truth signal data_range: the range of the data. If a tuple is provided then the range is calculated as the difference and input is clamped between the values. base: a base of a logarithm to use reduction: a method to reduce metric score over labels. - ``'elementwise_mean'``: takes the mean (default) - ``'sum'``: takes the sum - ``'none'`` or None``: no reduction will be applied dim: Dimensions to reduce PSNR scores over provided as either an integer or a list of integers. Default is None meaning scores will be reduced across all dimensions. Return: Tensor with PSNR score Example: >>> from torchmetrics.functional.image import peak_signal_noise_ratio >>> pred = torch.tensor([[0.0, 1.0], [2.0, 3.0]]) >>> target = torch.tensor([[3.0, 2.0], [1.0, 0.0]]) >>> peak_signal_noise_ratio(pred, target, data_range=3.0) tensor(2.5527) .. attention:: Half precision is only support on GPU for this metric. rzThe `reduction=z.` will not have any effect when `dim` is None.r)minmaxr")r r) rr(tuplerclamprfloatr0r) rrr r rrdata_range_valr r s rpeak_signal_noise_ratior9_sR {y$66 3abc*e$ Ez!}*Q-HVAJqMJ 1 1 =>j 12!-eV!Ew *G^$Zc ddr)$@r)N)r:rN)typingrrrrrtyping_extensionsrtorchmetrics.utilitiesrr r7rr)r5r0r9rrr?s;# %9BT 2 2  2 2  2 >? 2  2L26"& "& "& %U38_,- ."& 66> "&RBT15 4e 4e 4eeU5%<0014e  4e >? 4e %U38_,- . 4e 4er