a  d@sddlmZddlZddlmZddlmZddlmZddlm Z eeeeefddd Z deeed ed d dZ deeed ed ddZ dS))TupleN)Tensor)Literal)_check_same_shape)reduce)predstargetreturncCs|j|jkr&td|jd|jdt||t|jdkrXtd|jd|jd|jddkst|jddkrtd|jdd|jdd||fS)zUpdate and returns variables required to compute Spectral Angle Mapper. Args: preds: Predicted tensor target: Ground truth tensor zEExpected `preds` and `target` to have the same data type. Got preds: z and target: .z@Expected `preds` and `target` to have BxCxHxW shape. Got preds: zSExpected channel dimension of `preds` and `target` to be larger than 1. Got preds: )Zdtype TypeErrorrlenshape ValueError)rrrj/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchmetrics/functional/image/sam.py _sam_updates4  relementwise_mean)rsumnoneN)rr reductionr cCsL||jdd}|jdd}|jdd}t|||dd}t||S)aCompute Spectral Angle Mapper. Args: preds: estimated image target: ground truth image 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: >>> gen = torch.manual_seed(42) >>> preds = torch.rand([16, 3, 16, 16], generator=gen) >>> target = torch.rand([16, 3, 16, 16], generator=gen) >>> preds, target = _sam_update(preds, target) >>> _sam_compute(preds, target) tensor(0.5914) r )Zdim)rZnormtorchclampacosr)rrrZ dot_productZ preds_normZ target_normZ sam_scorerrr _sam_compute3s   rcCst||\}}t|||S)aUniversal Spectral Angle Mapper. Args: preds: estimated image target: ground truth image 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 Return: Tensor with Spectral Angle Mapper score Raises: TypeError: If ``preds`` and ``target`` don't have the same data type. ValueError: If ``preds`` and ``target`` don't have ``BxCxHxW shape``. Example: >>> from torchmetrics.functional.image import spectral_angle_mapper >>> gen = torch.manual_seed(42) >>> preds = torch.rand([16, 3, 16, 16], generator=gen) >>> target = torch.rand([16, 3, 16, 16], generator=gen) >>> spectral_angle_mapper(preds, target) tensor(0.5914) References: [1] Roberta H. Yuhas, Alexander F. H. Goetz and Joe W. Boardman, "Discrimination among semi-arid landscape endmembers using the Spectral Angle Mapper (SAM) algorithm" in PL, Summaries of the Third Annual JPL Airborne Geoscience Workshop, vol. 1, June 1, 1992. )rr)rrrrrrspectral_angle_mapperSs'r)r)r) typingrrrZtyping_extensionsrZtorchmetrics.utilities.checksrZ"torchmetrics.utilities.distributedrrrrrrrrs(      #