o yi)@sddlmZmZmZmZmZddlZddlmZddlm Z ddl m Z ddl m Z ddlmZddlmZmZGd d d eZdS) )AnyCallableOptionalTuple no_type_checkN)Tensor)Literal) _dice_compute)_stat_scores_update)Metric) AverageMethodMDMCAverageMethodcseZdZUdZdZeed<dZeed<dZeed<e     d!d e d e e de de e dde ede e de e de ededdffdd Ze dededdfddZe deeeeeffddZe defdd ZZS)"DiceaComputes `Dice`_: .. math:: \text{Dice} = \frac{\text{2 * TP}}{\text{2 * TP} + \text{FP} + \text{FN}} Where :math:`\text{TP}` and :math:`\text{FP}` represent the number of true positives and false positives respecitively. It is recommend set `ignore_index` to index of background class. The reduction method (how the precision scores are aggregated) is controlled by the ``average`` parameter, and additionally by the ``mdmc_average`` parameter in the multi-dimensional multi-class case. As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): Predictions from model (probabilities, logits or labels) - ``target`` (:class:`~torch.Tensor`): Ground truth values As output to ``forward`` and ``compute`` the metric returns the following output: - ``dice`` (:class:`~torch.Tensor`): A tensor containing the dice score. - If ``average in ['micro', 'macro', 'weighted', 'samples']``, a one-element tensor will be returned - If ``average in ['none', None]``, the shape will be ``(C,)``, where ``C`` stands for the number of classes Args: num_classes: Number of classes. Necessary for ``'macro'``, ``'weighted'`` and ``None`` average methods. threshold: Threshold for transforming probability or logit predictions to binary (0,1) predictions, in the case of binary or multi-label inputs. Default value of 0.5 corresponds to input being probabilities. zero_division: The value to use for the score if denominator equals zero. average: Defines the reduction that is applied. Should be one of the following: - ``'micro'`` [default]: Calculate the metric globally, across all samples and classes. - ``'macro'``: Calculate the metric for each class separately, and average the metrics across classes (with equal weights for each class). - ``'weighted'``: Calculate the metric for each class separately, and average the metrics across classes, weighting each class by its support (``tp + fn``). - ``'none'`` or ``None``: Calculate the metric for each class separately, and return the metric for every class. - ``'samples'``: Calculate the metric for each sample, and average the metrics across samples (with equal weights for each sample). .. note:: What is considered a sample in the multi-dimensional multi-class case depends on the value of ``mdmc_average``. mdmc_average: Defines how averaging is done for multi-dimensional multi-class inputs (on top of the ``average`` parameter). Should be one of the following: - ``None`` [default]: Should be left unchanged if your data is not multi-dimensional multi-class. - ``'samplewise'``: In this case, the statistics are computed separately for each sample on the ``N`` axis, and then averaged over samples. The computation for each sample is done by treating the flattened extra axes ``...`` as the ``N`` dimension within the sample, and computing the metric for the sample based on that. - ``'global'``: In this case the ``N`` and ``...`` dimensions of the inputs are flattened into a new ``N_X`` sample axis, i.e. the inputs are treated as if they were ``(N_X, C)``. From here on the ``average`` parameter applies as usual. ignore_index: Integer specifying a target class to ignore. If given, this class index does not contribute to the returned score, regardless of reduction method. If an index is ignored, and ``average=None`` or ``'none'``, the score for the ignored class will be returned as ``nan``. top_k: Number of the highest probability or logit score predictions considered finding the correct label, relevant only for (multi-dimensional) multi-class inputs. The default value (``None``) will be interpreted as 1 for these inputs. Should be left at default (``None``) for all other types of inputs. multiclass: Used only in certain special cases, where you want to treat inputs as a different type than what they appear to be. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Raises: ValueError: If ``average`` is none of ``"micro"``, ``"macro"``, ``"weighted"``, ``"samples"``, ``"none"``, ``None``. ValueError: If ``mdmc_average`` is not one of ``None``, ``"samplewise"``, ``"global"``. ValueError: If ``average`` is set but ``num_classes`` is not provided. ValueError: If ``num_classes`` is set and ``ignore_index`` is not in the range ``[0, num_classes)``. Example: >>> import torch >>> from torchmetrics import Dice >>> preds = torch.tensor([2, 0, 2, 1]) >>> target = torch.tensor([1, 1, 2, 0]) >>> dice = Dice(average='micro') >>> dice(preds, target) tensor(0.2500) Fis_differentiableThigher_is_betterfull_state_updaterN?microglobal zero_division num_classes thresholdaverage)rmacroweightednone mdmc_average ignore_indextop_k multiclasskwargsreturnc  stjdi| d} || vrtd| d|dtjtjdf} d| vr0|| vr,tjn|| d<d| vr8|| d<||_||_||_ ||_ ||_ ||_ ||_ |dvrYtd|d |d vretd |d |d krs|ro|d krstd|r|dur||kr|d krtd|d|ddd} d} |dkr|dkr|dkrgn|d kr|gntd|dfdd} d} dD] }|j|| | dq||_||_dS)N)rrrsamplesrNzThe `average` has to be one of z, got .reduce mdmc_reduce)rrr"z The `reduce` z is not valid.)N samplewiserzThe `mdmc_reduce` rzMWhen you set `average` as 'macro', you have to provide the number of classes.zThe `ignore_index` z is not valid for inputs with z classescSsgS)Nr(r(r(T/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/classification/dice.pyszDice.__init__..catr&r"rzWrong reduce=""cstjtjdS)N)dtype)torchzeroslongr( zeros_shaper(r)r*ssum)tpfptnfn)defaultdist_reduce_fxr()super__init__ ValueErrorr WEIGHTEDNONEMACROr$r%rrrrr add_staterr)selfrrrrrrrrr allowed_average_reduce_optionsr8 reduce_fns __class__r1r)r;sL   z Dice.__init__predstargetc Cst|||j|j|j|j|j|j|jd \}}}}|jtj krB|jt j krB|j |7_ |j |7_ |j|7_|j|7_dS|j ||j ||j||j|dS)z*Update state with predictions and targets.)r$r%rrrrrN)r r$r%rrrrrr SAMPLESr SAMPLEWISEr4r5r6r7append)rArHrIr4r5r6r7r(r(r)updates(    z Dice.updatecCst|jtr t|jn|j}t|jtrt|jn|j}t|jtr*t|jn|j}t|jtr9t|jn|j}||||fS)zbPerforms concatenation on the stat scores if neccesary, before passing them to a compute function.) isinstancer4listr.r+r5r6r7)rAr4r5r6r7r(r(r)_get_final_statss  zDice._get_final_statscCs(|\}}}}t||||j|j|jS)zComputes metric.)rPr rr%r)rAr4r5_r7r(r(r)computesz Dice.compute)rNrrrNNN)__name__ __module__ __qualname____doc__rbool__annotations__rrrintrfloatrstrrr;rrMrrPrR __classcell__r(r(rFr)rsR  h      =r)typingrrrrrr.rtyping_extensionsr+torchmetrics.functional.classification.dicer 2torchmetrics.functional.classification.stat_scoresr torchmetrics.metricr torchmetrics.utilities.enumsr r rr(r(r(r)s