---
title: Cohen Kappa
description: Calculate Cohen’s kappa score that measures inter-annotator agreement.
canonical: 'https://lightning.ai/docs/torchmetrics/stable/classification/cohen_kappa'
---
# Cohen Kappa {#cohen-kappa}

## Module Interface {#module-interface}

### `class torchmetrics.CohenKappa(**kwargs)` {#torchmetrics.CohenKappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L290-L336)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement.

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the `task` argument to either `'binary'` or `'multiclass'`. See the documentation of [`BinaryCohenKappa`](#torchmetrics.classification.BinaryCohenKappa "torchmetrics.classification.BinaryCohenKappa") and [`MulticlassCohenKappa`](#torchmetrics.classification.MulticlassCohenKappa "torchmetrics.classification.MulticlassCohenKappa") for the specific details of each argument influence and examples.

Legacy Example:

```python
>>> from torch import tensor
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0, 1, 0, 0])
>>> cohenkappa = CohenKappa(task="multiclass", num_classes=2)
>>> cohenkappa(preds, target)
tensor(0.5000)
```

#### `static __new__(cls, task, threshold=0.5, num_classes=None, weights=None, ignore_index=None, validate_args=True, **kwargs)` {#torchmetrics.CohenKappa.__new__}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L317-L336)

Initialize task metric.

Return type:

[`Metric`](/docs/torchmetrics/1.9.0/api-reference/metric.md#torchmetrics.Metric "torchmetrics.metric.Metric")

### BinaryCohenKappa {#binarycohenkappa}

### `class torchmetrics.classification.BinaryCohenKappa(threshold=0.5, ignore_index=None, weights=None, validate_args=True, **kwargs)` {#torchmetrics.classification.BinaryCohenKappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L36-L158)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement for binary tasks.

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

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

*   `preds` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): A 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` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): An int tensor of shape `(N, ...)`.
    

Tip

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

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

*   `bc_kappa` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): A tensor containing cohen kappa score
    

Parameters:

*   **threshold** ([`float`](https://docs.python.org/3/builtins/functions.html#float "(in Python v3.15)")) – Threshold for transforming probability to binary (0,1) predictions
    
*   **ignore\_index** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")\]) – Specifies a target value that is ignored and does not contribute to the metric calculation
    
*   **weights** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'linear'`, `'quadratic'`, `'none'`\]\]) –
    
    Weighting type to calculate the score. Choose from:
    
    *   `None` or `'none'`: no weighting
        
    *   `'linear'`: linear weighting
        
    *   `'quadratic'`: quadratic weighting
        
    
*   **validate\_args** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – bool indicating if input arguments and tensors should be validated for correctness. Set to `False` for faster computations.
    
*   **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.
    

Example (preds is int tensor):

```python
>>> from torch import tensor
>>> from torchmetrics.classification import BinaryCohenKappa
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0, 1, 0, 0])
>>> metric = BinaryCohenKappa()
>>> metric(preds, target)
tensor(0.5000)
```

Example (preds is float tensor):

```python
>>> from torchmetrics.classification import BinaryCohenKappa
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0.35, 0.85, 0.48, 0.01])
>>> metric = BinaryCohenKappa()
>>> metric(preds, target)
tensor(0.5000)
```

#### `plot(val=None, ax=None)` {#torchmetrics.classification.BinaryCohenKappa.plot}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L118-L158)

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 object and Axes object

Raises:

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

```python
>>> from torch import rand, randint
>>> # Example plotting a single value
>>> from torchmetrics.classification import BinaryCohenKappa
>>> metric = BinaryCohenKappa()
>>> metric.update(rand(10), randint(2,(10,)))
>>> fig_, ax_ = metric.plot()
```

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

```python
>>> from torch import rand, randint
>>> # Example plotting multiple values
>>> from torchmetrics.classification import BinaryCohenKappa
>>> metric = BinaryCohenKappa()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(rand(10), randint(2,(10,))))
>>> fig_, ax_ = metric.plot(values)
```

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

### MulticlassCohenKappa {#multiclasscohenkappa}

### `class torchmetrics.classification.MulticlassCohenKappa(num_classes, ignore_index=None, weights=None, validate_args=True, **kwargs)` {#torchmetrics.classification.MulticlassCohenKappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L161-L287)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement for multiclass tasks.

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

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

*   `preds` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): Either an int tensor of shape ```(N, ...)` or float tensor of shape ``(N, C, ..)```. If preds is a floating point we apply `torch.argmax` along the `C` dimension to automatically convert probabilities/logits into an int tensor.
    
*   `target` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): An int tensor of shape `(N, ...)`.
    

Tip

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

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

*   `mcck` ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")): A tensor containing cohen kappa score
    

Parameters:

*   **num\_classes** ([`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")) – Integer specifying the number of classes
    
*   **ignore\_index** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")\]) – Specifies a target value that is ignored and does not contribute to the metric calculation
    
*   **weights** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'linear'`, `'quadratic'`, `'none'`\]\]) –
    
    Weighting type to calculate the score. Choose from:
    
    *   `None` or `'none'`: no weighting
        
    *   `'linear'`: linear weighting
        
    *   `'quadratic'`: quadratic weighting
        
    
*   **validate\_args** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – bool indicating if input arguments and tensors should be validated for correctness. Set to `False` for faster computations.
    
*   **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.
    

Example (pred is integer tensor):

```python
>>> from torch import tensor
>>> from torchmetrics.classification import MulticlassCohenKappa
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> metric = MulticlassCohenKappa(num_classes=3)
>>> metric(preds, target)
tensor(0.6364)
```

Example (pred is float tensor):

```python
>>> from torchmetrics.classification import MulticlassCohenKappa
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([[0.16, 0.26, 0.58],
...                 [0.22, 0.61, 0.17],
...                 [0.71, 0.09, 0.20],
...                 [0.05, 0.82, 0.13]])
>>> metric = MulticlassCohenKappa(num_classes=3)
>>> metric(preds, target)
tensor(0.6364)
```

#### `plot(val=None, ax=None)` {#torchmetrics.classification.MulticlassCohenKappa.plot}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/classification/cohen_kappa.py#L247-L287)

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 object and Axes object

Raises:

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

```python
>>> from torch import randn, randint
>>> # Example plotting a single value
>>> from torchmetrics.classification import MulticlassCohenKappa
>>> metric = MulticlassCohenKappa(num_classes=3)
>>> metric.update(randn(20,3).softmax(dim=-1), randint(3, (20,)))
>>> fig_, ax_ = metric.plot()
```

[![../../\_images/cohen\_kappa-3.png](/docs/torchmetrics/1.9.0/static/_images/cohen_kappa-3.png)](/docs/torchmetrics/1.9.0/static/_images/cohen_kappa-3.png)

```python
>>> from torch import randn, randint
>>> # Example plotting a multiple values
>>> from torchmetrics.classification import MulticlassCohenKappa
>>> metric = MulticlassCohenKappa(num_classes=3)
>>> values = []
>>> for _ in range(20):
...     values.append(metric(randn(20,3).softmax(dim=-1), randint(3, (20,))))
>>> fig_, ax_ = metric.plot(values)
```

[![../../\_images/cohen\_kappa-4.png](/docs/torchmetrics/1.9.0/static/_images/cohen_kappa-4.png)](/docs/torchmetrics/1.9.0/static/_images/cohen_kappa-4.png)

## Functional Interface {#functional-interface}

### cohen_kappa {#cohen-kappa}

### `torchmetrics.functional.cohen_kappa(preds, target, task, threshold=0.5, num_classes=None, weights=None, ignore_index=None, validate_args=True)` {#torchmetrics.functional.cohen_kappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/classification/cohen_kappa.py#L230-L271)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement. It is defined as. :rtype: [`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the `task` argument to either `'binary'` or `'multiclass'`. See the documentation of [`binary_cohen_kappa()`](#torchmetrics.functional.classification.binary_cohen_kappa "torchmetrics.functional.classification.binary_cohen_kappa") and [`multiclass_cohen_kappa()`](#torchmetrics.functional.classification.multiclass_cohen_kappa "torchmetrics.functional.classification.multiclass_cohen_kappa") for the specific details of each argument influence and examples.

Legacy Example:

```python
>>> from torch import tensor
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0, 1, 0, 0])
>>> cohen_kappa(preds, target, task="multiclass", num_classes=2)
tensor(0.5000)
```

### binary_cohen_kappa {#binary-cohen-kappa}

### `torchmetrics.functional.classification.binary_cohen_kappa(preds, target, threshold=0.5, weights=None, ignore_index=None, validate_args=True)` {#torchmetrics.functional.classification.binary_cohen_kappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/classification/cohen_kappa.py#L75-L138)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement for binary tasks.

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

Accepts the following input tensors:

*   `preds` (int or float tensor): `(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` (int tensor): `(N, ...)`
    

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

Parameters:

*   **preds** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Tensor with predictions
    
*   **target** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Tensor with true labels
    
*   **threshold** ([`float`](https://docs.python.org/3/builtins/functions.html#float "(in Python v3.15)")) – Threshold for transforming probability to binary (0,1) predictions
    
*   **weights** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'linear'`, `'quadratic'`, `'none'`\]\]) –
    
    Weighting type to calculate the score. Choose from:
    
    *   `None` or `'none'`: no weighting
        
    *   `'linear'`: linear weighting
        
    *   `'quadratic'`: quadratic weighting
        
    
*   **ignore\_index** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")\]) – Specifies a target value that is ignored and does not contribute to the metric calculation
    
*   **validate\_args** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – bool indicating if input arguments and tensors should be validated for correctness. Set to `False` for faster computations.
    
*   **kwargs** – Additional keyword arguments, see [Advanced metric settings](/docs/torchmetrics/1.9.0/user-guide/overview.md#metric-kwargs) for more info.
    

Return type:

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

Example (preds is int tensor):

```python
>>> from torch import tensor
>>> from torchmetrics.functional.classification import binary_cohen_kappa
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0, 1, 0, 0])
>>> binary_cohen_kappa(preds, target)
tensor(0.5000)
```

Example (preds is float tensor):

```python
>>> from torchmetrics.functional.classification import binary_cohen_kappa
>>> target = tensor([1, 1, 0, 0])
>>> preds = tensor([0.35, 0.85, 0.48, 0.01])
>>> binary_cohen_kappa(preds, target)
tensor(0.5000)
```

### multiclass_cohen_kappa {#multiclass-cohen-kappa}

### `torchmetrics.functional.classification.multiclass_cohen_kappa(preds, target, num_classes, weights=None, ignore_index=None, validate_args=True)` {#torchmetrics.functional.classification.multiclass_cohen_kappa}

[\[source\]](https://github.com/Lightning-AI/torchmetrics/blob/v1.9.0/src/torchmetrics/functional/classification/cohen_kappa.py#L159-L227)

Calculate [Cohen’s kappa score](https://en.wikipedia.org/wiki/Cohen%27s_kappa) that measures inter-annotator agreement for multiclass tasks.

```math
\kappa = (p_o - p_e) / (1 - p_e)
```

where $`p_o`$ is the empirical probability of agreement and $`p_e`$ is the expected agreement when both annotators assign labels randomly. Note that $`p_e`$ is estimated using a per-annotator empirical prior over the class labels.

Accepts the following input tensors:

*   `preds`: `(N, ...)` (int tensor) or `(N, C, ..)` (float tensor). If preds is a floating point we apply `torch.argmax` along the `C` dimension to automatically convert probabilities/logits into an int tensor.
    
*   `target` (int tensor): `(N, ...)`
    

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

Parameters:

*   **preds** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Tensor with predictions
    
*   **target** ([`Tensor`](https://docs.pytorch.org/docs/stable/tensors.html#torch.Tensor "(in PyTorch v2.15)")) – Tensor with true labels
    
*   **num\_classes** ([`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")) – Integer specifying the number of classes
    
*   **weights** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`Literal`](https://docs.python.org/3/library/typing.html#typing.Literal "(in Python v3.15)")\[`'linear'`, `'quadratic'`, `'none'`\]\]) –
    
    Weighting type to calculate the score. Choose from:
    
    *   `None` or `'none'`: no weighting
        
    *   `'linear'`: linear weighting
        
    *   `'quadratic'`: quadratic weighting
        
    
*   **ignore\_index** ([`Optional`](https://docs.python.org/3/library/typing.html#typing.Optional "(in Python v3.15)")\[[`int`](https://docs.python.org/3/builtins/functions.html#int "(in Python v3.15)")\]) – Specifies a target value that is ignored and does not contribute to the metric calculation
    
*   **validate\_args** ([`bool`](https://docs.python.org/3/builtins/functions.html#bool "(in Python v3.15)")) – bool indicating if input arguments and tensors should be validated for correctness. Set to `False` for faster computations.
    
*   **kwargs** – Additional keyword arguments, see [Advanced metric settings](/docs/torchmetrics/1.9.0/user-guide/overview.md#metric-kwargs) for more info.
    

Return type:

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

Example (pred is integer tensor):

```python
>>> from torch import tensor
>>> from torchmetrics.functional.classification import multiclass_cohen_kappa
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> multiclass_cohen_kappa(preds, target, num_classes=3)
tensor(0.6364)
```

Example (pred is float tensor):

```python
>>> from torchmetrics.functional.classification import multiclass_cohen_kappa
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([[0.16, 0.26, 0.58],
...                 [0.22, 0.61, 0.17],
...                 [0.71, 0.09, 0.20],
...                 [0.05, 0.82, 0.13]])
>>> multiclass_cohen_kappa(preds, target, num_classes=3)
tensor(0.6364)
```

---

**Navigation**

- Parent: [Classification](/docs/torchmetrics/1.9.0/classification.md)