Shortcuts

Jaccard Index

Module Interface

class torchmetrics.JaccardIndex(num_classes, average='macro', ignore_index=None, absent_score=0.0, threshold=0.5, multilabel=False, **kwargs)[source]

Computes Intersection over union, or Jaccard index:

J(A,B) = \frac{|A\cap B|}{|A\cup B|}

Where: A and B are both tensors of the same size, containing integer class values. They may be subject to conversion from input data (see description below). Note that it is different from box IoU.

Works with binary, multiclass and multi-label data. Accepts probabilities from a model output or integer class values in prediction. Works with multi-dimensional preds and target.

Forward accepts

  • preds (float or long tensor): (N, ...) or (N, C, ...) where C is the number of classes

  • target (long tensor): (N, ...)

If preds and target are the same shape and preds is a float tensor, we use the self.threshold argument to convert into integer labels. This is the case for binary and multi-label probabilities.

If preds has an extra dimension as in the case of multi-class scores we perform an argmax on dim=1.

Parameters
  • num_classes (int) – Number of classes in the dataset.

  • average (Optional[str]) –

    Defines the reduction that is applied. Should be one of the following:

    • 'macro' [default]: Calculate the metric for each class separately, and average the metrics across classes (with equal weights for each class).

    • 'micro': Calculate the metric globally, across all samples and classes.

    • '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. Note that if a given class doesn’t occur in the preds or target, the value for the class will be nan.

  • ignore_index (Optional[int]) – optional int specifying a target class to ignore. If given, this class index does not contribute to the returned score, regardless of reduction method. Has no effect if given an int that is not in the range [0, num_classes-1]. By default, no index is ignored, and all classes are used.

  • absent_score (float) – score to use for an individual class, if no instances of the class index were present in preds AND no instances of the class index were present in target. For example, if we have 3 classes, [0, 0] for preds, and [0, 2] for target, then class 1 would be assigned the absent_score.

  • threshold (float) – Threshold value for binary or multi-label probabilities.

  • multilabel (bool) – determines if data is multilabel or not.

  • kwargs (Dict[str, Any]) – Additional keyword arguments, see Advanced metric settings for more info.

Example

>>> from torchmetrics import JaccardIndex
>>> 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(num_classes=2)
>>> jaccard(pred, target)
tensor(0.9660)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

compute()[source]

Computes intersection over union (IoU)

Return type

Tensor

Functional Interface

torchmetrics.functional.jaccard_index(preds, target, num_classes, average='macro', ignore_index=None, absent_score=0.0, threshold=0.5)[source]

Computes Jaccard index

J(A,B) = \frac{|A\cap B|}{|A\cup B|}

Where: A and B are both tensors of the same size, containing integer class values. They may be subject to conversion from input data (see description below).

Note that it is different from box IoU.

If preds and target are the same shape and preds is a float tensor, we use the self.threshold argument to convert into integer labels. This is the case for binary and multi-label probabilities.

If pred has an extra dimension as in the case of multi-class scores we perform an argmax on dim=1.

Parameters
  • preds (Tensor) – tensor containing predictions from model (probabilities, or labels) with shape [N, d1, d2, ...]

  • target (Tensor) – tensor containing ground truth labels with shape [N, d1, d2, ...]

  • num_classes (int) – Specify the number of classes

  • average (Optional[str]) –

    Defines the reduction that is applied. Should be one of the following:

    • 'macro' [default]: Calculate the metric for each class separately, and average the metrics across classes (with equal weights for each class).

    • 'micro': Calculate the metric globally, across all samples and classes.

    • '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. Note that if a given class doesn’t occur in the preds or target, the value for the class will be nan.

  • ignore_index (Optional[int]) – optional int specifying a target class to ignore. If given, this class index does not contribute to the returned score, regardless of reduction method. Has no effect if given an int that is not in the range [0, num_classes-1], where num_classes is either given or derived from pred and target. By default, no index is ignored, and all classes are used.

  • absent_score (float) – score to use for an individual class, if no instances of the class index were present in preds AND no instances of the class index were present in target. For example, if we have 3 classes, [0, 0] for preds, and [0, 2] for target, then class 1 would be assigned the absent_score.

  • threshold (float) – Threshold value for binary or multi-label probabilities.

Return type

Tensor

Returns

The shape of the returned tensor depends on the average parameter

  • If average in ['micro', 'macro', 'weighted'], 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

Example

>>> from torchmetrics.functional import jaccard_index
>>> 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_index(pred, target, num_classes=2)
tensor(0.9660)