Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes.

# tf.keras.metrics.MeanSquaredError

## Class `MeanSquaredError`

Computes the mean squared error between `y_true` and `y_pred`.

### Aliases:

• Class `tf.compat.v1.keras.metrics.MeanSquaredError`
• Class `tf.compat.v2.keras.metrics.MeanSquaredError`
• Class `tf.compat.v2.metrics.MeanSquaredError`

For example, if `y_true` is [0., 0., 1., 1.], and `y_pred` is [1., 1., 1., 0.] the mean squared error is 3/4 (0.75).

#### Usage:

``````m = tf.keras.metrics.MeanSquaredError()
m.update_state([0., 0., 1., 1.], [1., 1., 1., 0.])
print('Final result: ', m.result().numpy())  # Final result: 0.75
``````

Usage with tf.keras API:

``````model = tf.keras.Model(inputs, outputs)
model.compile('sgd', metrics=[tf.keras.metrics.MeanSquaredError()])
``````

## `__init__`

View source

``````__init__(
name='mean_squared_error',
dtype=None
)
``````

## Methods

### `reset_states`

View source

``````reset_states()
``````

Resets all of the metric state variables.

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

### `result`

View source

``````result()
``````

### `update_state`

View source

``````update_state(
y_true,
y_pred,
sample_weight=None
)
``````

Accumulates metric statistics.

`y_true` and `y_pred` should have the same shape.

#### 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`.

Update op.