o .wi@sddlmZddlZddlmZddlmZddlmZ ddededed ee d e eeeff d d Z d ededed efddZ ddededed ee d ef ddZ dS))OptionalN)Tensor)_check_same_shape _safe_dividepredstarget thresholdkeep_sequence_dimreturnc st||dur d}n%dkr|jks#ntd|jdtfddt|jD}||k}||k}durat||@}t||A|@}t||A|@} n%tj||@|d}tj||A|@|d}tj||A|@|d} ||| fS)a%Update and return variables required to compute Critical Success Index. Checks for same shape of tensors. Args: preds: Predicted tensor target: Ground truth tensor threshold: Values above or equal to threshold are replaced with 1, below by 0 keep_sequence_dim: Index of the sequence dimension if the inputs are sequences of images. If specified, the score will be calculated separately for each image in the sequence. If ``None``, the score will be calculated across all dimensions. Nrz.Expected keep_sequence dim to be in range [0, z ] but got c3s|] }|kr|VqdSN).0ir r c/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/regression/csi.py ,sz1_critical_success_index_update..)dim) rndim ValueErrortuplerangebooltorchsumint) rrr r sum_dims preds_bin target_binhitsmisses false_alarmsr rr_critical_success_index_updates    r"rr r!cCst||||S)aCompute critical success index. Args: hits: Number of true positives after binarization misses: Number of false negatives after binarization false_alarms: Number of false positives after binarization Returns: If input tensors are 5-dimensional and ``keep_sequence_dim=True``, the metric returns a ``(S,)`` vector with CSI scores for each image in the sequence. Otherwise, it returns a scalar tensor with the CSI score. r)rr r!r r r_critical_success_index_compute=s r#cCs t||||\}}}t|||S)aYCompute critical success index. Args: preds: Predicted tensor target: Ground truth tensor threshold: Values above or equal to threshold are replaced with 1, below by 0 keep_sequence_dim: Index of the sequence dimension if the inputs are sequences of images. If specified, the score will be calculated separately for each image in the sequence. If ``None``, the score will be calculated across all dimensions. Returns: If ``keep_sequence_dim`` is specified, the metric returns a vector of with CSI scores for each image in the sequence. Otherwise, it returns a scalar tensor with the CSI score. Example: >>> import torch >>> from torchmetrics.functional.regression import critical_success_index >>> x = torch.Tensor([[0.2, 0.7], [0.9, 0.3]]) >>> y = torch.Tensor([[0.4, 0.2], [0.8, 0.6]]) >>> critical_success_index(x, y, 0.5) tensor(0.3333) Example: >>> import torch >>> from torchmetrics.functional.regression import critical_success_index >>> x = torch.Tensor([[[0.2, 0.7], [0.9, 0.3]], [[0.2, 0.7], [0.9, 0.3]]]) >>> y = torch.Tensor([[[0.4, 0.2], [0.8, 0.6]], [[0.4, 0.2], [0.8, 0.6]]]) >>> critical_success_index(x, y, 0.5, keep_sequence_dim=0) tensor([0.3333, 0.3333]) )r"r#)rrr r rr r!r r rcritical_success_indexMs" r$r )typingrrrtorchmetrics.utilities.checksrtorchmetrics.utilities.computerfloatrrr"r#r$r r r rs<      &