---
title: ARNIQA
description: 'ARNIQA: leArning distoRtion maNifold for Image Quality Assessment metric.'
canonical: 'https://lightning.ai/docs/torchmetrics/stable/image/arniqa'
---
# ARNIQA {#arniqa}

## Module Interface {#module-interface}

### `class torchmetrics.image.arniqa.ARNIQA(regressor_dataset='koniq10k', reduction='mean', normalize=True, autocast=False, **kwargs)` {#torchmetrics.image.arniqa.ARNIQA}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/image/arniqa.py#L47-L216)

ARNIQA: leArning distoRtion maNifold for Image Quality Assessment metric.

[ARNIQA](https://arxiv.org/abs/2310.14918) is a No-Reference Image Quality Assessment metric that predicts the technical quality of an image with a high correlation with human opinions. ARNIQA consists of an encoder and a regressor. The encoder is a ResNet-50 model trained in a self-supervised way to model the image distortion manifold to generate similar representation for images with similar distortions, regardless of the image content. The regressor is a linear model trained on IQA datasets using the ground-truth quality scores. ARNIQA extracts the features from the full- and half-scale versions of the input image and then outputs a quality score in the \[0, 1\] range, where higher is better.

The input image is expected to have shape `(N, 3, H, W)`. The image should be in the \[0, 1\] range if normalize is set to `True`, otherwise it should be normalized with the ImageNet mean and standard deviation.

Note

Using this metric requires you to have `torchvision` package installed. Either install as `pip install torchmetrics[image]` or `pip install torchvision`.

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

*   `img` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): tensor with images of shape `(N, 3, H, W)`
    

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

*   `arniqa` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): tensor with ARNIQA score. If reduction is set to `none`, the output will have shape `(N,)`, otherwise it will be a scalar tensor. Tensor values are in the \[0, 1\] range, where higher is better.
    

Parameters:

*   **img** – the input image
    
*   **regressor\_dataset** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'kadid10k'`, `'koniq10k'`\]) – dataset used for training the regressor. Choose between \[`koniq10k`, `kadid10k`\]. `koniq10k` corresponds to the [KonIQ-10k](https://database.mmsp-kn.de/koniq-10k-database.html) dataset, which consists of real-world images with authentic distortions. `kadid10k` corresponds to the [KADID-10k](https://database.mmsp-kn.de/kadid-10k-database.html) dataset, which consists of images with synthetically generated distortions.
    
*   **reduction** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'sum'`, `'mean'`, `'none'`\]) – indicates how to reduce over the batch dimension. Choose between \[`sum`, `mean`, `none`\].
    
*   **normalize** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – by default this is `True` meaning that the input is expected to be in the \[0, 1\] range. If set to `False` will instead expect input to be already normalized with the ImageNet mean and standard deviation.
    
*   **autocast** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – if `True`, metric will convert model to mixed precision before running forward pass.
    
*   **kwargs** ([`Any`](https://docs.python.org/3/library/typing.html#typing.Any "(in Python v3.15)")) – additional keyword arguments, see [Advanced metric settings](/docs/torchmetrics/1.9.0/user-guide/overview.md#metric-kwargs) for more info.
    

Raises:

*   [**ModuleNotFoundError**](https://docs.python.org/3/builtins/exceptions.html#ModuleNotFoundError "(in Python v3.15)") – If `torchvision` package is not installed
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `regressor_dataset` is not in \[`"kadid10k"`, `"koniq10k"`\]
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `reduction` is not in \[`"sum"`, `"mean"`, `"none"`\]
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `normalize` is not a bool
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If the input image is not a valid image tensor with shape \[N, 3, H, W\].
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If the input image values are not in the \[0, 1\] range when `normalize` is set to `True`
    

Examples

```python
>>> from torch import rand
>>> from torchmetrics.image.arniqa import ARNIQA
>>> img = rand(8, 3, 224, 224)
>>> # Non-normalized input
>>> metric = ARNIQA(regressor_dataset='koniq10k', normalize=True)
>>> metric(img)
tensor(0.5308)
```

```python
>>> from torch import rand
>>> from torchmetrics.image.arniqa import ARNIQA
>>> from torchvision.transforms import Normalize
>>> img = rand(8, 3, 224, 224)
>>> img = Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])(img)
>>> # Normalized input
>>> metric = ARNIQA(regressor_dataset='koniq10k', normalize=False)
>>> metric(img)
tensor(0.5065)
```

#### `plot(val=None, ax=None)` {#torchmetrics.image.arniqa.ARNIQA.plot}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/image/arniqa.py#L176-L216)

Plot a single or multiple values from the metric.

Parameters:

*   **val** (`Union`\[[`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)"), [`Sequence`](https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence "(in Python v3.15)")\[[`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")\], [`None`](https://docs.python.org/3/builtins/constants.html#None "(in Python v3.15)")\]) – Either a single result from calling metric.forward or metric.compute or a list of these results. If no value is provided, will automatically call metric.compute and plot that result.
    
*   **ax** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`Axes`](https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.html#matplotlib.axes.Axes "(in Matplotlib v3.11.2)")\]) – An matplotlib axis object. If provided will add plot to that axis
    

Return type:

[`tuple`](https://docs.python.org/3/builtins/stdtypes.html#tuple "(in Python v3.15)")\[[`Figure`](https://matplotlib.org/stable/api/_as_gen/matplotlib.figure.Figure.html#matplotlib.figure.Figure "(in Matplotlib v3.11.2)"), `Union`\[[`Axes`](https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.html#matplotlib.axes.Axes "(in Matplotlib v3.11.2)"), [`ndarray`](https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray "(in NumPy v2.5)")\]\]

Returns:

Figure and Axes object

Raises:

[**ModuleNotFoundError**](https://docs.python.org/3/builtins/exceptions.html#ModuleNotFoundError "(in Python v3.15)") – If matplotlib is not installed

```python
>>> # Example plotting a single value
>>> import torch
>>> from torchmetrics.image.arniqa import ARNIQA
>>> metric = ARNIQA(regressor_dataset='koniq10k')
>>> metric.update(torch.rand(8, 3, 224, 224))
>>> fig_, ax_ = metric.plot()
```

[![../../\_images/arniqa-1.png](/docs/torchmetrics/1.9.0/static/_images/arniqa-1.png)](/docs/torchmetrics/1.9.0/static/_images/arniqa-1.png)

```python
>>> # Example plotting multiple values
>>> import torch
>>> from torchmetrics.image.arniqa import ARNIQA
>>> metric = ARNIQA(regressor_dataset='koniq10k')
>>> values = [ ]
>>> for _ in range(3):
...     values.append(metric(torch.rand(8, 3, 224, 224)))
>>> fig_, ax_ = metric.plot(values)
```

[![../../\_images/arniqa-2.png](/docs/torchmetrics/1.9.0/static/_images/arniqa-2.png)](/docs/torchmetrics/1.9.0/static/_images/arniqa-2.png)

## Functional Interface {#functional-interface}

### `torchmetrics.functional.image.arniqa(img, regressor_dataset='koniq10k', reduction='mean', normalize=True, autocast=False)` {#torchmetrics.functional.image.arniqa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/image/arniqa.py#L198-L279)

ARNIQA: leArning distoRtion maNifold for Image Quality Assessment metric.

[ARNIQA](https://arxiv.org/abs/2310.14918) is a No-Reference Image Quality Assessment metric that predicts the technical quality of an image with a high correlation with human opinions. ARNIQA consists of an encoder and a regressor. The encoder is a ResNet-50 model trained in a self-supervised way to model the image distortion manifold to generate similar representation for images with similar distortions, regardless of the image content. The regressor is a linear model trained on IQA datasets using the ground-truth quality scores. ARNIQA extracts the features from the full- and half-scale versions of the input image and then outputs a quality score in the \[0, 1\] range, where higher is better.

The input image is expected to have shape `(N, 3, H, W)`. The image should be in the \[0, 1\] range if normalize is set to `True`, otherwise it should be normalized with the ImageNet mean and standard deviation.

Note

Using this metric requires you to have `torchvision` package installed. Either install as `pip install torchmetrics[image]` or `pip install torchvision`.

Parameters:

*   **img** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – the input image
    
*   **regressor\_dataset** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'kadid10k'`, `'koniq10k'`\]) – dataset used for training the regressor. Choose between \[`koniq10k`, `kadid10k`\]. `koniq10k` corresponds to the [KonIQ-10k](https://database.mmsp-kn.de/koniq-10k-database.html) dataset, which consists of real-world images with authentic distortions. `kadid10k` corresponds to the [KADID-10k](https://database.mmsp-kn.de/kadid-10k-database.html) dataset, which consists of images with synthetically generated distortions.
    
*   **reduction** ([`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'sum'`, `'mean'`, `'none'`\]) – indicates how to reduce over the batch dimension. Choose between \[`sum`, `mean`, `none`\].
    
*   **normalize** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – by default this is `True` meaning that the input is expected to be in the \[0, 1\] range. If set to `False` will instead expect input to be already normalized with the ImageNet mean and standard deviation.
    
*   **autocast** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – boolean indicating whether to use automatic mixed precision
    

Return type:

[`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")

Returns:

A tensor in the \[0, 1\] range, where higher is better, representing the ARNIQA score of the input image. If reduction is set to `none`, the output will have shape `(N,)`, otherwise it will be a scalar tensor.

Raises:

*   [**ModuleNotFoundError**](https://docs.python.org/3/builtins/exceptions.html#ModuleNotFoundError "(in Python v3.15)") – If `torchvision` package is not installed
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `regressor_dataset` is not in \[`"kadid10k"`, `"koniq10k"`\]
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `reduction` is not in \[`"sum"`, `"mean"`, `"none"`\]
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If `normalize` is not a bool
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If the input image is not a valid image tensor with shape \[N, 3, H, W\].
    
*   [**ValueError**](https://docs.python.org/3/builtins/exceptions.html#ValueError "(in Python v3.15)") – If the input image values are not in the \[0, 1\] range when `normalize` is set to `True`
    

Examples

```python
>>> from torch import rand
>>> from torchmetrics.functional.image.arniqa import arniqa
>>> img = rand(8, 3, 224, 224)
>>> # Non-normalized input
>>> arniqa(img, regressor_dataset='koniq10k', normalize=True)
tensor(0.5308)
```

```python
>>> from torch import rand
>>> from torchmetrics.functional.image.arniqa import arniqa
>>> from torchvision.transforms import Normalize
>>> img = rand(8, 3, 224, 224)
>>> img = Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])(img)
>>> # Normalized input
>>> arniqa(img, regressor_dataset='koniq10k', normalize=False)
tensor(0.5065)
```

---

**Navigation**

- Parent: [Image](/docs/torchmetrics/1.9.0/image.md)