# tf.keras.metrics.MeanIoU

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/iou_metrics.py#L428-L530) |

Computes the mean Intersection-Over-Union metric.

Inherits From: [`IoU`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/metrics/IoU), [`Metric`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/metrics/Metric), [`Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Module)

#### View aliases


**Main aliases**

[`tf.metrics.MeanIoU`](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/MeanIoU)
**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

\`tf.compat.v1.keras.metrics.MeanIoU\`

<br />

    tf.keras.metrics.MeanIoU(
        num_classes: int,
        name: Optional[str] = None,
        dtype: Optional[Union[str, https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/dtypes/DType]] = None,
        ignore_class: Optional[int] = None,
        sparse_y_true: bool = True,
        sparse_y_pred: bool = True,
        axis: int = -1
    )

General definition and computation:

Intersection-Over-Union is a common evaluation metric for semantic image
segmentation.

For an individual class, the IoU metric is defined as follows:

    iou = true_positives / (true_positives + false_positives + false_negatives)

To compute IoUs, the predictions are accumulated in a confusion matrix,
weighted by `sample_weight` and the metric is then calculated from it.

If `sample_weight` is `None`, weights default to 1.
Use `sample_weight` of 0 to mask values.

Note that this class first computes IoUs for all individual classes, then
returns the mean of these values.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `num_classes` | The possible number of labels the prediction task can have. This value must be provided, since a confusion matrix of dimension = \[num_classes, num_classes\] will be allocated. |
| `name` | (Optional) string name of the metric instance. |
| `dtype` | (Optional) data type of the metric result. |
| `ignore_class` | Optional integer. The ID of a class to be ignored during metric computation. This is useful, for example, in segmentation problems featuring a "void" class (commonly -1 or 255) in segmentation maps. By default (`ignore_class=None`), all classes are considered. |
| `sparse_y_true` | Whether labels are encoded using integers or dense floating point vectors. If `False`, the [`tf.argmax`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/argmax) function will be used to determine each sample's most likely associated label. |
| `sparse_y_pred` | Whether predictions are encoded using integers or dense floating point vectors. If `False`, the [`tf.argmax`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/argmax) function will be used to determine each sample's most likely associated label. |
| `axis` | (Optional) Defaults to -1. The dimension containing the logits. |

<br />

#### Standalone usage:

    # cm = [[1, 1],
    #        [1, 1]]
    # sum_row = [2, 2], sum_col = [2, 2], true_positives = [1, 1]
    # iou = true_positives / (sum_row + sum_col - true_positives))
    # result = (1 / (2 + 2 - 1) + 1 / (2 + 2 - 1)) / 2 = 0.33
    m = tf.keras.metrics.MeanIoU(num_classes=2)
    m.update_state([0, 0, 1, 1], [0, 1, 0, 1])
    m.result().numpy()
    0.33333334

    m.reset_state()
    m.update_state([0, 0, 1, 1], [0, 1, 0, 1],
                   sample_weight=[0.3, 0.3, 0.3, 0.1])
    m.result().numpy()
    0.23809525

Usage with `compile()` API:

    model.compile(
      optimizer='sgd',
      loss='mse',
      metrics=[tf.keras.metrics.MeanIoU(num_classes=2)])

## Methods

### `merge_state`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/base_metric.py#L288-L326)

    merge_state(
        metrics
    )

Merges the state from one or more metrics.

This method can be used by distributed systems to merge the state
computed by different metric instances. Typically the state will be
stored in the form of the metric's weights. For example, a
tf.keras.metrics.Mean metric contains a list of two weight values: a
total and a count. If there were two instances of a
tf.keras.metrics.Accuracy that each independently aggregated partial
state for an overall accuracy calculation, these two metric's states
could be combined as follows:

    m1 = tf.keras.metrics.Accuracy()
    _ = m1.update_state([[1], [2]], [[0], [2]])

    m2 = tf.keras.metrics.Accuracy()
    _ = m2.update_state([[3], [4]], [[3], [4]])

    m2.merge_state([m1])
    m2.result().numpy()
    0.75

<br />

<br />

<br />

| Args ||
|---|---|
| `metrics` | an iterable of metrics. The metrics must have compatible state. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If the provided iterable does not contain metrics matching the metric's required specifications. |

<br />

### `reset_state`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/iou_metrics.py#L149-L152)

    reset_state()

Resets all of the metric state variables.

This function is called between epochs/steps,
when a metric is evaluated during training.

### `result`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/iou_metrics.py#L264-L293)

    result()

Compute the intersection-over-union via the confusion matrix.

### `update_state`

[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/metrics/iou_metrics.py#L97-L147)

    update_state(
        y_true, y_pred, sample_weight=None
    )

Accumulates the confusion matrix statistics.

<br />

<br />

<br />

| Args ||
|---|---|
| `y_true` | The ground truth values. |
| `y_pred` | The predicted values. |
| `sample_weight` | Optional weighting of each example. Defaults to 1. Can be a `Tensor` whose rank is either 0, or the same rank as `y_true`, and must be broadcastable to `y_true`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Update op. ||

<br />