Multilabelstatscores

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

# multilabelstatscores

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

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics.classification import MultilabelStatScores

# MultilabelStatScores(num_labels: int, threshold: float = 0.5, average: Optional[Literal['micro', 'macro', 'weighted', 'none']] = 'macro', multidim_average: Literal['global', 'samplewise'] = 'global', ignore_index: Optional[int] = None, validate_args: bool = True, **kwargs: Any) -> None
```

## Library docstring

```
Compute true positives, false positives, true negatives, false negatives and the support for multilabel tasks.

Related to `Type I and Type II errors`_.

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

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

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

- ``mlss`` (:class:`~torch.Tensor`): A tensor of shape ``(..., 5)``, where the last dimension corresponds
  to ``[tp, fp, tn, fn, sup]`` (``sup`` stands for support and equals ``tp + fn``). The shape
  depends on ``average`` and ``multidim_average`` parameters:

  - If ``multidim_average`` is set to ``global``:

    - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(5,)``
    - If ``average=None/'none'``, the shape will be ``(C, 5)``

  - If ``multidim_average`` is set to ``samplewise``:

    - If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N, 5)``
    - If ``average=None/'none'``, the shape will be ``(N, C, 5)``

If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present,
which the reduction will then be applied over instead of the sample dimension ``N``.

Args:
    num_labels: Integer specifying the number of labels
    threshold: Threshold for transforming probability to binary (0,1) predictions
    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

    multidim_average:
        Defines ho
```

## Quick recipe

```python
import torchmetrics.classification as _m
score = _m.MultilabelStatScores(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)`.