o .wih@s ddlmZmZddlZddlmZmZddlmZddlm Z m Z   dded ed ed e d ed def ddZ ddededeee ee dffdeeeffddZ    ddeded eee ee e ffd e d ed deee ee dffdefddZdS))OptionalUnionN)Tensortensor)Literal)rank_zero_warnreduce$@elementwise_meansum_squared_errornum_obs data_rangebase reduction)r sumnoneNreturncCs>dt|t||}|dtt|}t||dS)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 rr psnr_base_e psnr_valsr_/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/image/psnr.py _psnr_computes rpredstargetdim.cCs|s |tj}|s|tj}|dur0tt||d}t||jd}||fS||}tj|||d}t |t rE|gnt |}|sXt||jd}||fSt| |jd| }||}||fS)aZUpdate and return variables required to compute peak signal-to-noise ratio. Args: preds: Predicted tensor target: Ground truth tensor 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. Nr)devicer)is_floating_pointtorfloat32rpowrnumelr isinstanceintlistsizeprod expand_as)rrrr r diffdim_listrrr _psnr_update:s"   r.cCs|dur|dkrtd|d|dur%|durtd||}n.t|trMtj||d|dd}tj||d|dd}t|d|d}ntt |}t |||d \}}t |||||d S) aCompute the peak signal-to-noise ratio. Args: preds: estimated signal target: groun truth signal data_range: the range of the data. If None, it is determined from the data (max - min). If a tuple is provided then the range is calculated as the difference and input is clamped between the values. The ``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 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 Raises: ValueError: If ``dim`` is not ``None`` and ``data_range`` is not provided. 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) tensor(2.5527) .. attention:: Half precision is only support on GPU for this metric. Nr zThe `reduction=z.` will not have any effect when `dim` is None.z6The `data_range` must be given when `dim` is not None.r)minmaxr )rr) r ValueErrorr1r0r&tuplerclamprfloatr.r)rrr rrrr r rrrpeak_signal_noise_ratio_s.  r6)r r )N)Nr r N)typingrrrrrtyping_extensionsrtorchmetrics.utilitiesrrr5rr'r3r.r6rrrrsb   &  (