o yi\5@sddlmZmZddlZddlmZddlmZddlmZm Z m Z ddl m Z m Z mZddlmZGdd d eZGd d d e ZGd d d e ZGdddZdS))AnyOptionalN)Tensor)Literal)BinaryConfusionMatrixMulticlassConfusionMatrixMultilabelConfusionMatrix)_jaccard_index_reduce(_multiclass_jaccard_index_arg_validation(_multilabel_jaccard_index_arg_validation)Metricc sveZdZUdZdZeed<dZeed<dZeed<   dd e d e e d ed e d df fdd Z d efddZZS)BinaryJaccardIndexaCalculates the Jaccard index for binary tasks. The `Jaccard index`_ (also known as the intersetion over union or jaccard similarity coefficient) is an statistic that can be used to determine the similarity and diversity of a sample set. It is defined as the size of the intersection divided by the union of the sample sets: .. math:: J(A,B) = \frac{|A\cap B|}{|A\cup B|} As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A int or float tensor of shape ``(N, ...)``. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value in ``threshold``. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``bji`` (:class:`~torch.Tensor`): A tensor containing the Binary Jaccard Index. Args: threshold: Threshold for transforming probability to binary (0,1) predictions ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example (preds is int tensor): >>> from torchmetrics.classification import BinaryJaccardIndex >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0, 1, 0, 0]) >>> metric = BinaryJaccardIndex() >>> metric(preds, target) tensor(0.5000) Example (preds is float tensor): >>> from torchmetrics.classification import BinaryJaccardIndex >>> target = torch.tensor([1, 1, 0, 0]) >>> preds = torch.tensor([0.35, 0.85, 0.48, 0.01]) >>> metric = BinaryJaccardIndex() >>> metric(preds, target) tensor(0.5000) Fis_differentiableThigher_is_betterfull_state_update?N threshold ignore_index validate_argskwargsreturnc s tjd||d|d|dS)N)rr normalizer)super__init__)selfrrrr __class__rW/home/ubuntu/.local/lib/python3.10/site-packages/torchmetrics/classification/jaccard.pyrOs  zBinaryJaccardIndex.__init__cCst|jddS)Nbinaryaverage)r confmatrrrrcomputeZszBinaryJaccardIndex.compute)rNT)__name__ __module__ __qualname____doc__rbool__annotations__rrfloatrintrrrr$ __classcell__rrrrr s(  -   r c seZdZUdZdZeed<dZeed<dZeed<   dd e d e e d d e e d ede ddf fdd Z defddZZS)MulticlassJaccardIndexa Calculates the Jaccard index for multiclass tasks. The `Jaccard index`_ (also known as the intersetion over union or jaccard similarity coefficient) is an statistic that can be used to determine the similarity and diversity of a sample set. It is defined as the size of the intersection divided by the union of the sample sets: .. math:: J(A,B) = \frac{|A\cap B|}{|A\cup B|} As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A int tensor of shape ``(N, ...)`` or float tensor of shape ``(N, C, ..)``. If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically convert probabilities/logits into an int tensor. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``. .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mcji`` (:class:`~torch.Tensor`): A tensor containing the Multi-class Jaccard Index. Args: num_classes: Integer specifing the number of classes ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum statistics over all labels - ``macro``: Calculate statistics for each label and average them - ``weighted``: Calculates statistics for each label and computes weighted average using their support - ``"none"`` or ``None``: Calculates statistic for each label and applies no reduction validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example (pred is integer tensor): >>> from torchmetrics.classification import MulticlassJaccardIndex >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([2, 1, 0, 1]) >>> metric = MulticlassJaccardIndex(num_classes=3) >>> metric(preds, target) tensor(0.6667) Example (pred is float tensor): >>> from torchmetrics.classification import MulticlassJaccardIndex >>> target = torch.tensor([2, 1, 0, 0]) >>> preds = torch.tensor([ ... [0.16, 0.26, 0.58], ... [0.22, 0.61, 0.17], ... [0.71, 0.09, 0.20], ... [0.05, 0.82, 0.13], ... ]) >>> metric = MulticlassJaccardIndex(num_classes=3) >>> metric(preds, target) tensor(0.6667) FrTrrmacroN num_classesr!micror/weightednonerrrrc s<tjd||ddd||rt|||||_||_dS)NF)r0rrrr)rrr rr!)rr0r!rrrrrrrs  zMulticlassJaccardIndex.__init__cCst|j|j|jdS)N)r!r)r r"r!rr#rrrr$szMulticlassJaccardIndex.compute)r/NT)r%r&r'r(rr)r*rrr,rrrrrr$r-rrrrr.^s,  ;   r.cseZdZUdZdZeed<dZeed<dZeed<   dd e d e d e e d de e dede dd ffdd ZdefddZZS)MultilabelJaccardIndexa? Calculates the Jaccard index for multilabel tasks. The `Jaccard index`_ (also known as the intersetion over union or jaccard similarity coefficient) is an statistic that can be used to determine the similarity and diversity of a sample set. It is defined as the size of the intersection divided by the union of the sample sets: .. math:: J(A,B) = \frac{|A\cap B|}{|A\cup B|} As input to ``forward`` and ``update`` the metric accepts the following input: - ``preds`` (:class:`~torch.Tensor`): A int tensor or float tensor of shape ``(N, C, ...)``. If preds is a floating point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid per element. Addtionally, we convert to int tensor with thresholding using the value in ``threshold``. - ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)`` .. note:: Additional dimension ``...`` will be flattened into the batch dimension. As output to ``forward`` and ``compute`` the metric returns the following output: - ``mlji`` (:class:`~torch.Tensor`): A tensor containing the Multi-label Jaccard Index loss. Args: num_classes: Integer specifing the number of labels threshold: Threshold for transforming probability to binary (0,1) predictions ignore_index: Specifies a target value that is ignored and does not contribute to the metric calculation average: Defines the reduction that is applied over labels. Should be one of the following: - ``micro``: Sum statistics over all labels - ``macro``: Calculate statistics for each label and average them - ``weighted``: Calculates statistics for each label and computes weighted average using their support - ``"none"`` or ``None``: Calculates statistic for each label and applies no reduction validate_args: bool indicating if input arguments and tensors should be validated for correctness. Set to ``False`` for faster computations. kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info. Example (preds is int tensor): >>> from torchmetrics.classification import MultilabelJaccardIndex >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0, 0, 1], [1, 0, 1]]) >>> metric = MultilabelJaccardIndex(num_labels=3) >>> metric(preds, target) tensor(0.5000) Example (preds is float tensor): >>> from torchmetrics.classification import MultilabelJaccardIndex >>> target = torch.tensor([[0, 1, 0], [1, 0, 1]]) >>> preds = torch.tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]]) >>> metric = MultilabelJaccardIndex(num_labels=3) >>> metric(preds, target) tensor(0.5000) FrTrrrr/N num_labelsrr!r1rrrrc s@tjd|||ddd||rt||||||_||_dS)NF)r6rrrrr)rrr rr!)rr6rr!rrrrrrrs  zMultilabelJaccardIndex.__init__cCst|j|jdS)Nr )r r"r!r#rrrr$szMultilabelJaccardIndex.compute)rr/NT)r%r&r'r(rr)r*rrr,r+rrrrrr$r-rrrrr5s2  7   r5c@sdeZdZdZ      ddedded eed eed eed d eedede de fddZ dS) JaccardIndexaBCalculates the Jaccard index for multilabel tasks. The `Jaccard index`_ (also known as the intersetion over union or jaccard similarity coefficient) is an statistic that can be used to determine the similarity and diversity of a sample set. It is defined as the size of the intersection divided by the union of the sample sets: .. math:: J(A,B) = \frac{|A\cap B|}{|A\cup B|} This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the ``task`` argument to either ``'binary'``, ``'multiclass'`` or ``multilabel``. See the documentation of :mod:`BinaryJaccardIndex`, :mod:`MulticlassJaccardIndex` and :mod:`MultilabelJaccardIndex` for the specific details of each argument influence and examples. Legacy Example: >>> target = torch.randint(0, 2, (10, 25, 25)) >>> pred = torch.tensor(target) >>> pred[2:5, 7:13, 9:15] = 1 - pred[2:5, 7:13, 9:15] >>> jaccard = JaccardIndex(task="multiclass", num_classes=2) >>> jaccard(pred, target) tensor(0.9660) rNr/Ttask)r multiclass multilabelrr0r6r!r1rrrrc Ks|t||d|dkrt|fi|S|dkr)t|ts Jt||fi|S|dkr>t|ts4Jt|||fi|Std|)N)rrrr9r:z[Expected argument `task` to either be `'binary'`, `'multiclass'` or `'multilabel'` but got )updatedictr isinstancer,r.r5 ValueError) clsr8rr0r6r!rrrrrr__new__s zJaccardIndex.__new__)rNNr/NT) r%r&r'r(rr+rr,r)rr r@rrrrr7s6   r7)typingrrtorchrtyping_extensionsrtorchmetrics.classificationrrr.torchmetrics.functional.classification.jaccardr r r torchmetrics.metricr r r.r5r7rrrrs    ATV