Qualitywithnoreference

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

# qualitywithnoreference

> Metric `QualityWithNoReference` from `torchmetrics` (torchmetrics.image.QualityWithNoReference)

## When to invoke this skill

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

## Reference signature

```python
from torchmetrics.image import QualityWithNoReference

# QualityWithNoReference(alpha: float = 1, beta: float = 1, norm_order: int = 1, window_size: int = 7, reduction: Literal['elementwise_mean', 'sum', 'none'] = 'elementwise_mean', **kwargs: Any) -> None
```

## Library docstring

```
Compute Quality with No Reference (QualityWithNoReference_) also now as QNR.

The metric is used to compare the joint spectral and spatial distortion between two images.

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

- ``preds`` (:class:`~torch.Tensor`): High resolution multispectral image of shape ``(N,C,H,W)``.
- ``target`` (:class:`~Dict`): A dictionary containing the following keys:

  - ``ms`` (:class:`~torch.Tensor`): Low resolution multispectral image of shape ``(N,C,H',W')``.
  - ``pan`` (:class:`~torch.Tensor`): High resolution panchromatic image of shape ``(N,C,H,W)``.
  - ``pan_lr`` (:class:`~torch.Tensor`): (optional) Low resolution panchromatic image of shape ``(N,C,H',W')``.

where H and W must be multiple of H' and W'.

When ``pan_lr`` is ``None``, a uniform filter will be applied on ``pan`` to produce a degraded image. The degraded
image is then resized to match the size of ``ms`` and served as ``pan_lr`` in the calculation.

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

- ``qnr`` (:class:`~torch.Tensor`): if ``reduction!='none'`` returns float scalar tensor with average QNR value
  over sample else returns tensor of shape ``(N,)`` with QNR values per sample

Args:
    alpha: Relevance of spectral distortion.
    beta: Relevance of spatial distortion.
    norm_order: Order of the norm applied on the difference.
    window_size: Window size of the filter applied to degrade the high resolution panchromatic image.
    reduction: a method to reduce metric score over labels.

        - ``'elementwise_mean'``: takes the mean (default)
        - ``'sum'``: takes the sum
        - ``'none'``: no reduction will be applied

    kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.

Example:
    >>> from torch import rand
    >>> from torchmetrics.image import QualityWithNoReference
    >>> preds = rand([16, 3, 32, 32])
    >>> target = {
    ...     'ms': rand([16, 3, 16, 16]),
    ...     'pan': rand([16, 3, 32, 32]),
    ... }
    >>> qnr = QualityWithNoReference()
    >>> qnr(preds, target)
    tensor(0.9694)
```

## Quick recipe

```python
import torchmetrics.image as _m
score = _m.QualityWithNoReference(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)`.