Normalized Mutual Information Score

Module Interface

class torchmetrics.clustering.NormalizedMutualInfoScore(average_method='arithmetic', **kwargs)[source]

Compute Normalized Mutual Information Score.

\[NMI(U,V) = \frac{MI(U,V)}{M_p(U,V)}\]

Where \(U\) is a tensor of target values, \(V\) is a tensor of predictions, \(M_p(U,V)\) is the generalized mean of order \(p\) of \(U\) and \(V\), and \(MI(U,V)\) is the mutual information score between clusters \(U\) and \(V\). The metric is symmetric, therefore swapping \(U\) and \(V\) yields the same mutual information score.

This clustering metric is an extrinsic measure, because it requires ground truth clustering labels, which may not be available in practice since clustering in generally is used for unsupervised learning.

As input to forward and update the metric accepts the following input:

  • preds (Tensor): single integer tensor with shape (N,) with predicted cluster labels

  • target (Tensor): single integer tensor with shape (N,) with ground truth cluster labels

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

  • nmi_score (Tensor): A tensor with the Normalized Mutual Information Score

  • average_method (Literal['min', 'geometric', 'arithmetic', 'max']) – Method used to calculate generalized mean for normalization

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

>>> import torch
>>> from torchmetrics.clustering import NormalizedMutualInfoScore
>>> preds = torch.tensor([2, 1, 0, 1, 0])
>>> target = torch.tensor([0, 2, 1, 1, 0])
>>> nmi_score = NormalizedMutualInfoScore("arithmetic")
>>> nmi_score(preds, target)
plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

  • 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]]


Figure and Axes object


ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> import torch
>>> from torchmetrics.clustering import NormalizedMutualInfoScore
>>> metric = NormalizedMutualInfoScore()
>>> metric.update(torch.randint(0, 4, (10,)), torch.randint(0, 4, (10,)))
>>> fig_, ax_ = metric.plot(metric.compute())
>>> # Example plotting multiple values
>>> import torch
>>> from torchmetrics.clustering import NormalizedMutualInfoScore
>>> metric = NormalizedMutualInfoScore()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(torch.randint(0, 4, (10,)), torch.randint(0, 4, (10,))))
>>> fig_, ax_ = metric.plot(values)
higher_is_better: Optional[bool] = None

Functional Interface

torchmetrics.functional.clustering.normalized_mutual_info_score(preds, target, average_method='arithmetic')[source]

Compute normalized mutual information between two clusterings.

  • preds (Tensor) – predicted cluster labels

  • target (Tensor) – ground truth cluster labels

  • average_method (Literal['min', 'geometric', 'arithmetic', 'max']) – normalizer computation method

Return type:



Scalar tensor with normalized mutual info score between 0.0 and 1.0


>>> from torchmetrics.functional.clustering import normalized_mutual_info_score
>>> target = torch.tensor([0, 3, 2, 2, 1])
>>> preds = torch.tensor([1, 3, 2, 0, 1])
>>> normalized_mutual_info_score(preds, target, "arithmetic")