o .wi@sddlmZddlZddlmZddlmZddlmZddlm Z ddl m Z de d e d e d ed d edddf ddZ  d dedede d e d ed d eddeeeffddZd!deded e defddZ    d"dedede d e d e d ed d eddefddZdS)#)TupleN)Tensor)Literal)_ignore_background)_check_same_shape) _safe_divide num_classesinclude_background per_class weight_typesquaresimplelinear input_formatone-hotindexreturncCst|tr |dkrtd|dt|tstd|dt|ts+td|d|dvr7td|d|dvrCtd |dd S) z%Validate the arguments of the metric.rzDExpected argument `num_classes` must be a positive integer, but got .zBExpected argument `include_background` must be a boolean, but got z9Expected argument `per_class` must be a boolean, but got r zSExpected argument `weight_type` to be one of 'square', 'simple', 'linear', but got rzJExpected argument `input_format` to be one of 'one-hot', 'index', but got N) isinstanceint ValueErrorbool)rr r r rrr/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/torchmetrics/functional/segmentation/generalized_dice.py_generalized_dice_validate_argss   rr rpredstargetcCsxt|||dkr#tjjj||ddd}tjjj||ddd}|jdkr1td|jd|s:t||\}}t t d|j}tj |||d }tj ||d }tj ||d } || } |d krfd |} n|d krpt |} n|d kr{d |d} ntd|d| j } | } t| }d| |<t| dj| ddj}||| |<| | } d|| }| | }||fS)z8Update the state with the current prediction and target.r)rzJExpected both `preds` and `target` to have at least 3 dimensions, but got r)dimrg?rr zSExpected argument `weight_type` to be one of 'simple', 'linear', 'square', but got rg@)rtorchnn functionalone_hotmovedimndimrrlistrangesum ones_likeshapeflattenisinfmaxvaluesrepeatTreshape)rrrr r r reduce_axis intersection target_sumpred_sum cardinalityweightsw_shapeweights_flatteninfsw_max numerator denominatorrrr_generalized_dice_update/s@          rBTr@rAcCs&|st|d}t|d}t||S)z#Compute the generalized dice score.r )r$r,r)r@rAr rrr_generalized_dice_computeas   rCFc Cs2t|||||t||||||\}}t|||S)aCompute the Generalized Dice Score for semantic segmentation. Args: preds: Predictions from model target: Ground truth values num_classes: Number of classes include_background: Whether to include the background class in the computation per_class: Whether to compute the score for each class separately, else average over all classes weight_type: Type of weight factor to apply to the classes. One of ``"square"``, ``"simple"``, or ``"linear"`` input_format: What kind of input the function receives. Choose between ``"one-hot"`` for one-hot encoded tensors or ``"index"`` for index tensors Returns: The Generalized Dice Score Example (with one-hot encoded tensors): >>> from torch import randint >>> from torchmetrics.functional.segmentation import generalized_dice_score >>> preds = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 prediction >>> target = randint(0, 2, (4, 5, 16, 16)) # 4 samples, 5 classes, 16x16 target >>> generalized_dice_score(preds, target, num_classes=5) tensor([0.4830, 0.4935, 0.5044, 0.4880]) >>> generalized_dice_score(preds, target, num_classes=5, per_class=True) tensor([[0.4724, 0.5185, 0.4710, 0.5062, 0.4500], [0.4571, 0.4980, 0.5191, 0.4380, 0.5649], [0.5428, 0.4904, 0.5358, 0.4830, 0.4724], [0.4715, 0.4925, 0.4797, 0.5267, 0.4788]]) Example (with index tensors): >>> from torch import randint >>> from torchmetrics.functional.segmentation import generalized_dice_score >>> preds = randint(0, 5, (4, 16, 16)) # 4 samples, 5 classes, 16x16 prediction >>> target = randint(0, 5, (4, 16, 16)) # 4 samples, 5 classes, 16x16 target >>> generalized_dice_score(preds, target, num_classes=5, input_format="index") tensor([0.1991, 0.1971, 0.2350, 0.2216]) >>> generalized_dice_score(preds, target, num_classes=5, per_class=True, input_format="index") tensor([[0.1714, 0.2500, 0.1304, 0.2524, 0.2069], [0.1837, 0.2162, 0.0962, 0.2692, 0.1895], [0.3866, 0.1348, 0.2526, 0.2301, 0.2083], [0.1978, 0.2804, 0.1714, 0.1915, 0.2783]]) )rrBrC) rrrr r r rr@rArrrgeneralized_dice_scoreis 3  rD)r r)T)TFr r)typingrr$rtyping_extensionsr*torchmetrics.functional.segmentation.utilsrtorchmetrics.utilities.checksrtorchmetrics.utilities.computerrrrrBrCrDrrrrsv         2