# tf.keras.layers.Normalization

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.7.0/keras/layers/preprocessing/normalization.py#L28-L279) |

A preprocessing layer which normalizes continuous features.

Inherits From: [`PreprocessingLayer`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer), [`Layer`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/Module)

#### View aliases


**Main aliases**

[`tf.keras.layers.experimental.preprocessing.Normalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization)
**Compat aliases for migration**

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

[`tf.compat.v1.keras.layers.Normalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization), [`tf.compat.v1.keras.layers.experimental.preprocessing.Normalization`](https://www.tensorflow.org/api_docs/python/tf/keras/layers/Normalization)

<br />

    tf.keras.layers.Normalization(
        axis=-1, mean=None, variance=None, **kwargs
    )

This layer will shift and scale inputs into a distribution centered around
0 with standard deviation 1. It accomplishes this by precomputing the mean and
variance of the data, and calling `(input - mean) / sqrt(var)` at runtime.

The mean and variance values for the layer must be either supplied on
construction or learned via `adapt()`. `adapt()` will compute the mean and
variance of the data and store them as the layer's weights. `adapt()` should
be called before `fit()`, `evaluate()`, or `predict()`.

For an overview and full list of preprocessing layers, see the preprocessing
[guide](https://www.tensorflow.org/guide/keras/preprocessing_layers).

<br />

<br />

<br />

| ## Args ||
|---|---|
| `axis` | Integer, tuple of integers, or None. The axis or axes that should have a separate mean and variance for each index in the shape. For example, if shape is `(None, 5)` and `axis=1`, the layer will track 5 separate mean and variance values for the last axis. If `axis` is set to `None`, the layer will normalize all elements in the input by a scalar mean and variance. Defaults to -1, where the last axis of the input is assumed to be a feature dimension and is normalized per index. Note that in the specific case of batched scalar inputs where the only axis is the batch axis, the default will normalize each index in the batch separately. In this case, consider passing `axis=None`. |
| `mean` | The mean value(s) to use during normalization. The passed value(s) will be broadcast to the shape of the kept axes above; if the value(s) cannot be broadcast, an error will be raised when this layer's `build()` method is called. |
| `variance` | The variance value(s) to use during normalization. The passed value(s) will be broadcast to the shape of the kept axes above; if the value(s) cannot be broadcast, an error will be raised when this layer's `build()` method is called. |

<br />

#### Examples:

Calculate a global mean and variance by analyzing the dataset in `adapt()`.

    adapt_data = np.array([1., 2., 3., 4., 5.], dtype='float32')
    input_data = np.array([1., 2., 3.], dtype='float32')
    layer = tf.keras.layers.Normalization(axis=None)
    layer.adapt(adapt_data)
    layer(input_data)
    <tf.Tensor: shape=(3,), dtype=float32, numpy=
    array([-1.4142135, -0.70710677, 0.], dtype=float32)>

Calculate a mean and variance for each index on the last axis.

    adapt_data = np.array([[0., 7., 4.],
                           [2., 9., 6.],
                           [0., 7., 4.],
                           [2., 9., 6.]], dtype='float32')
    input_data = np.array([[0., 7., 4.]], dtype='float32')
    layer = tf.keras.layers.Normalization(axis=-1)
    layer.adapt(adapt_data)
    layer(input_data)
    <tf.Tensor: shape=(1, 3), dtype=float32, numpy=
    array([0., 0., 0.], dtype=float32)>

Pass the mean and variance directly.

    input_data = np.array([[1.], [2.], [3.]], dtype='float32')
    layer = tf.keras.layers.Normalization(mean=3., variance=2.)
    layer(input_data)
    <tf.Tensor: shape=(3, 1), dtype=float32, numpy=
    array([[-1.4142135 ],
           [-0.70710677],
           [ 0.        ]], dtype=float32)>

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `is_adapted` | Whether the layer has been fit to data already. |

<br />

## Methods

### `adapt`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/engine/base_preprocessing_layer.py#L156-L248)

    adapt(
        data, batch_size=None, steps=None
    )

Fits the state of the preprocessing layer to the data being passed.

After calling `adapt` on a layer, a preprocessing layer's state will not
update during training. In order to make preprocessing layers efficient in
any distribution context, they are kept constant with respect to any
compiled [`tf.Graph`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/Graph)s that call the layer. This does not affect the layer use
when adapting each layer only once, but if you adapt a layer multiple times
you will need to take care to re-compile any compiled functions as follows:

- If you are adding a preprocessing layer to a [`keras.Model`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/Model), you need to call `model.compile` after each subsequent call to `adapt`.
- If you are calling a preprocessing layer inside [`tf.data.Dataset.map`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/data/Dataset#map), you should call `map` again on the input [`tf.data.Dataset`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/data/Dataset) after each `adapt`.
- If you are using a [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function) directly which calls a preprocessing layer, you need to call [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function) again on your callable after each subsequent call to `adapt`.

[`tf.keras.Model`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/Model) example with multiple adapts:

    layer = tf.keras.layers.experimental.preprocessing.Normalization(
        axis=None)
    layer.adapt([0, 2])
    model = tf.keras.Sequential(layer)
    model.predict([0, 1, 2])
    array([-1.,  0.,  1.], dtype=float32)
    layer.adapt([-1, 1])
    model.compile() # This is needed to re-compile model.predict!
    model.predict([0, 1, 2])
    array([0., 1., 2.], dtype=float32)

[`tf.data.Dataset`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/data/Dataset) example with multiple adapts:

    layer = tf.keras.layers.experimental.preprocessing.Normalization(
        axis=None)
    layer.adapt([0, 2])
    input_ds = tf.data.Dataset.range(3)
    normalized_ds = input_ds.map(layer)
    list(normalized_ds.as_numpy_iterator())
    [array([-1.], dtype=float32),
     array([0.], dtype=float32),
     array([1.], dtype=float32)]
    layer.adapt([-1, 1])
    normalized_ds = input_ds.map(layer) # Re-map over the input dataset.
    list(normalized_ds.as_numpy_iterator())
    [array([0.], dtype=float32),
     array([1.], dtype=float32),
     array([2.], dtype=float32)]

<br />

<br />

<br />

| Arguments ||
|---|---|
| `data` | The data to train on. It can be passed either as a tf.data Dataset, or as a numpy array. |
| `batch_size` | Integer or `None`. Number of samples per state update. If unspecified, `batch_size` will default to 32. Do not specify the `batch_size` if your data is in the form of datasets, generators, or [`keras.utils.Sequence`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/utils/Sequence) instances (since they generate batches). |
| `steps` | Integer or `None`. Total number of steps (batches of samples) When training with input tensors such as TensorFlow data tensors, the default `None` is equal to the number of samples in your dataset divided by the batch size, or 1 if that cannot be determined. If x is a [`tf.data`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/data) dataset, and 'steps' is None, the epoch will run until the input dataset is exhausted. When passing an infinitely repeating dataset, you must specify the `steps` argument. This argument is not supported with array inputs. |

<br />

### `compile`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/engine/base_preprocessing_layer.py#L134-L154)

    compile(
        run_eagerly=None, steps_per_execution=None
    )

Configures the layer for `adapt`.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `run_eagerly` | Bool. Defaults to `False`. If `True`, this `Model`'s logic will not be wrapped in a [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function). Recommended to leave this as `None` unless your `Model` cannot be run inside a [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function). steps_per_execution: Int. Defaults to 1. The number of batches to run during each [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function) call. Running multiple batches inside a single [`tf.function`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/function) call can greatly improve performance on TPUs or small models with a large Python overhead. |

<br />

### `reset_state`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/layers/preprocessing/normalization.py#L233-L239)

    reset_state()

Resets the statistics of the preprocessing layer.

### `update_state`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/layers/preprocessing/normalization.py#L196-L231)

    update_state(
        data
    )

Accumulates statistics for the preprocessing layer.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `data` | A mini-batch of inputs to the layer. |

<br />