Multilabelroc

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

# multilabelroc

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

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics.classification import MultilabelROC

# MultilabelROC(num_labels: int, thresholds: Union[int, list[float], torch.Tensor, NoneType] = None, ignore_index: Optional[int] = None, validate_args: bool = True, **kwargs: Any) -> None
```

## Library docstring

```
Compute the Receiver Operating Characteristic (ROC) for binary tasks.

The curve consist of multiple pairs of true positive rate (TPR) and false positive rate (FPR) values evaluated at
different thresholds, such that the tradeoff between the two values can be seen.

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

- ``preds`` (:class:`~torch.Tensor`): A float tensor of shape ``(N, C, ...)``. Preds should be a tensor
  containing probabilities or logits for each observation. If preds has values outside [0,1] range we consider
  the input to be logits and will auto apply sigmoid per element.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)``. Target should be a tensor
  containing ground truth labels, and therefore only contain {0,1} values (except if `ignore_index` is specified).

.. tip::
   Additional dimension ``...`` will be flattened into the batch dimension.

As output to ``forward`` and ``compute`` the metric returns a tuple of either 3 tensors or 3 lists containing

- ``fpr`` (:class:`~torch.Tensor`): if `thresholds=None` a list for each label is returned with an 1d tensor of
  size ``(n_thresholds+1, )`` with false positive rate values (length may differ between labels). If `thresholds` is
  set to something else, then a single 2d tensor of size ``(n_labels, n_thresholds+1)`` with false positive rate
  values is returned.
- ``tpr`` (:class:`~torch.Tensor`): if `thresholds=None` a list for each label is returned with an 1d tensor of
  size ``(n_thresholds+1, )`` with true positive rate values (length may differ between labels). If `thresholds` is
  set to something else, then a single 2d tensor of size ``(n_labels, n_thresholds+1)`` with true positive rate
  values is returned.
- ``thresholds`` (:class:`~torch.Tensor`): if `thresholds=None` a list for each label is returned with an 1d
  tensor of size ``(n_thresholds, )`` with decreasing threshold values (length may differ between labels). If
  `threshold` is set to something else, then a single 1d tensor of size ``(n_thresholds, )`` is returned with shared
  threshold values for all labels.

.. note::
   The implementation both supports calculatin
```

## Quick recipe

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