Binaryhammingdistance

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

# binaryhammingdistance

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

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics.classification import BinaryHammingDistance

# BinaryHammingDistance(threshold: float = 0.5, multidim_average: Literal['global', 'samplewise'] = 'global', ignore_index: Optional[int] = None, validate_args: bool = True, **kwargs: Any) -> None
```

## Library docstring

```
Compute the average `Hamming distance`_ (also known as Hamming loss) for binary tasks.

.. math::
    \text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})

Where :math:`y` is a tensor of target values, :math:`\hat{y}` is a tensor of predictions,
and :math:`\bullet_{il}` refers to the :math:`l`-th label of the :math:`i`-th sample of that
tensor.

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:

- ``bhd`` (:class:`~torch.Tensor`): A tensor whose returned shape depends on the ``multidim_average`` arguments:

    - If ``multidim_average`` is set to ``global``, the metric returns a scalar value.
    - If ``multidim_average`` is set to ``samplewise``, the metric returns ``(N,)`` vector consisting of a
      scalar value per sample.

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:
    threshold: Threshold for transforming probability to binary {0,1} predictions
    multidim_average:
        Defines how additionally dimensions ``...`` should be handled. Should be one of the following:

        - ``global``: Additional dimensions are flatted along the batch dimension
        - ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
          The statistics in this case are calculated over the additional dimensions.

    ignore_index:
        Specifies a target value that is ignored and does not contribute to the metric calculation
    validate_args: bool indicating if input arguments and tensors should be validated for correctness.
 
```

## Quick recipe

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