Dice

Module Interface

class torchmetrics.Dice(zero_division=0, num_classes=None, threshold=0.5, average='micro', mdmc_average='global', ignore_index=None, top_k=None, multiclass=None, **kwargs)[source]

Compute Dice.

\[\text{Dice} = \frac{\text{2 * TP}}{\text{2 * TP} + \text{FP} + \text{FN}}\]

Where \(\text{TP}\) and \(\text{FP}\) 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 (Tensor): Predictions from model (probabilities, logits or labels)

  • target (Tensor): Ground truth values

As output to forward and compute the metric returns the following output:

  • dice (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

Parameters:
  • num_classes – Number of classes. Necessary for 'macro', 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 Advanced metric settings for more info.

Raises:
  • ValueError – If average is none of "micro", "macro", "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

>>> from torch import tensor
>>> from torchmetrics.classification import Dice
>>> preds  = tensor([2, 0, 2, 1])
>>> target = tensor([1, 1, 2, 0])
>>> dice = Dice(average='micro')
>>> dice(preds, target)
tensor(0.2500)
plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

Parameters:
  • val (Union[Tensor, Sequence[Tensor], None]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.

  • ax (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

Tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure object and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> from torch import randint
>>> from torchmetrics.classification import Dice
>>> metric = Dice()
>>> metric.update(randint(2,(10,)), randint(2,(10,)))
>>> fig_, ax_ = metric.plot()
../_images/dice-1.png
>>> # Example plotting multiple values
>>> from torch import randint
>>> from torchmetrics.classification import Dice
>>> metric = Dice()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(randint(2,(10,)), randint(2,(10,))))
>>> fig_, ax_ = metric.plot(values)
../_images/dice-2.png

Functional Interface

torchmetrics.functional.dice(preds, target, zero_division=0, average='micro', mdmc_average='global', threshold=0.5, top_k=None, num_classes=None, multiclass=None, ignore_index=None)[source]

Compute Dice.

\[\text{Dice} = \frac{\text{2 * TP}}{\text{2 * TP} + \text{FP} + \text{FN}}\]

Where \(\text{TP}\) and \(\text{FN}\) represent the number of true positives and false negatives respecitively.

It is recommend set ignore_index to index of background class.

The reduction method (how the recall scores are aggregated) is controlled by the average parameter, and additionally by the mdmc_average parameter in the multi-dimensional multi-class case.

Parameters:
  • preds (Tensor) – Predictions from model (probabilities, logits or labels)

  • target (Tensor) – Ground truth values

  • zero_division (int) – The value to use for the score if denominator equals zero

  • average (Optional[str]) –

    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.

    Note

    If 'none' and a given class doesn’t occur in the preds or target, the value for the class will be nan.

  • mdmc_average (Optional[str]) –

    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 (Optional[int]) – 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.

  • num_classes (Optional[int]) – Number of classes. Necessary for 'macro', 'weighted' and None average methods.

  • threshold (float) – 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.

  • top_k (Optional[int]) –

    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 (Optional[bool]) – Used only in certain special cases, where you want to treat inputs as a different type than what they appear to be.

Return type:

Tensor

Returns:

The shape of the returned tensor depends on the average parameter

  • 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

Raises:
  • ValueError – If average is not one of "micro", "macro", "weighted", "samples", "none" or 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

>>> from torchmetrics.functional.classification import dice
>>> preds = torch.tensor([2, 0, 2, 1])
>>> target = torch.tensor([1, 1, 2, 0])
>>> dice(preds, target, average='micro')
tensor(0.2500)