Multiclassconfusionmatrix

---
name: multiclassconfusionmatrix
description: Compute the MulticlassConfusionMatrix metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute MulticlassConfusionMatrix, or asks how to score with MulticlassConfusionMatrix.
metadata:
  skill_kind: metric
  source_lib: torchmetrics
  import_path: torchmetrics.classification.MulticlassConfusionMatrix
  source: library_introspection
---

# multiclassconfusionmatrix

> Metric `MulticlassConfusionMatrix` from `torchmetrics` (torchmetrics.classification.MulticlassConfusionMatrix)

## When to invoke this skill

The user has predictions + ground truth and asks to evaluate with MulticlassConfusionMatrix, or
mentions `torchmetrics.classification.MulticlassConfusionMatrix` directly, or wants the standard torchmetrics implementation.

## Reference signature

```python
from torchmetrics.classification import MulticlassConfusionMatrix

# MulticlassConfusionMatrix(num_classes: int, ignore_index: Optional[int] = None, normalize: Optional[Literal['true', 'pred', 'all', 'none']] = None, validate_args: bool = True, **kwargs: Any) -> None
```

## Library docstring

```
Compute the `confusion matrix`_ for multiclass tasks.

The confusion matrix :math:`C` is constructed such that :math:`C_{i, j}` is equal to the number of observations
known to be in class :math:`i` but predicted to be in class :math:`j`. Thus row indices of the confusion matrix
correspond to the true class labels and column indices correspond to the predicted class labels.

For multiclass tasks, the confusion matrix is a NxN matrix, where:

- :math:`C_{i, i}` represents the number of true positives for class :math:`i`
- :math:`\sum_{j=1, j\neq i}^N C_{i, j}` represents the number of false negatives for class :math:`i`
- :math:`\sum_{j=1, j\neq i}^N C_{j, i}` represents the number of false positives for class :math:`i`
- the sum of the remaining cells in the matrix represents the number of true negatives for class :math:`i`

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

- ``preds`` (:class:`~torch.Tensor`): An 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. Additionally, we convert to int tensor with thresholding using the value in ``threshold``.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``.

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

- ``confusion_matrix``: [num_classes, num_classes] matrix

Args:
    num_classes: Integer specifying the number of classes
    ignore_index:
        Specifies a target value that is ignored and does not contribute to the metric calculation
    normalize: Normalization mode for confusion matrix. Choose from:

        - ``None`` or ``'none'``: no normalization (default)
        - ``'true'``: normalization over the targets (most commonly used)
        - ``'pred'``: normalization over the predictions
        - ``'all'``: normalization over the whole matrix
    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.

Exampl
```

## Quick recipe

```python
import torchmetrics.classification as _m
score = _m.MulticlassConfusionMatrix(y_true, y_pred)
```

## Don'ts

- Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
- Always check the library version's argument order — sklearn is `(y_true, y_pred)` while torchmetrics is `(preds, target)`.