# tf.keras.layers.experimental.preprocessing.PreprocessingLayer

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L47-L279) |

Base class for Preprocessing Layers.

Inherits From: [`Layer`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/Module)

#### View aliases


**Compat aliases for migration**

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

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

<br />

    tf.keras.layers.experimental.preprocessing.PreprocessingLayer(
        stateful=False, streaming=True, **kwargs
    )

**Don't use this class directly: it's an abstract base class!** You may
be looking for one of the many built-in
[preprocessing layers](https://keras.io/guides/preprocessing_layers/)
instead.

Preprocessing layers are layers whose state gets computed before model
training starts. They do not get updated during training.
Most preprocessing layers implement an `adapt()` method for state computation.

The `PreprocessingLayer` class is the base class you would subclass to
implement your own preprocessing layers.

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `stateful` | Whether the layer contains state that needs to be adapted via [`PreprocessingLayer.adapt`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer#adapt). |
| `streaming` | Whether a layer can be adapted multiple times without resetting the state of the layer. |
| `is_adapted` | Whether the layer has been fit to data already. |

<br />

## Methods

### `adapt`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L191-L246)

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

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

<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/r2.5/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/r2.5/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. |
| `reset_state` | Optional argument specifying whether to clear the state of the layer at the start of the call to `adapt`, or whether to start from the existing state. This argument may not be relevant to all preprocessing layers: a subclass of PreprocessingLayer may choose to throw if 'reset_state' is set to False. |

<br />

### `compile`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L169-L189)

    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/r2.5/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/r2.5/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/r2.5/api_docs/python/tf/function) call. Running multiple batches inside a single [`tf.function`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/function) call can greatly improve performance on TPUs or small models with a large Python overhead. |

<br />

### `finalize_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L119-L126)

    finalize_state()

Finalize the statistics for the preprocessing layer.

This method is called at the end of `adapt`. This method
handles any one-time operations that should occur after all
data has been seen.

### `make_adapt_function`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L128-L167)

    make_adapt_function()

Creates a function to execute one step of `adapt`.

This method can be overridden to support custom adapt logic.
This method is called by [`PreprocessingLayer.adapt`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer#adapt).

Typically, this method directly controls [`tf.function`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/function) settings,
and delegates the actual state update logic to
[`PreprocessingLayer.update_state`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer#update_state).

This function is cached the first time [`PreprocessingLayer.adapt`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer#adapt)
is called. The cache is cleared whenever [`PreprocessingLayer.compile`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/keras/layers/experimental/preprocessing/PreprocessingLayer#compile)
is called.

<br />

<br />

<br />

| Returns ||
|---|---|
| Function. The function created by this method should accept a [`tf.data.Iterator`](https://www.tensorflow.org/versions/r2.5/api_docs/python/tf/data/Iterator), retrieve a batch, and update the state of the layer. ||

<br />

### `merge_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L107-L117)

    merge_state(
        layers
    )

Merge the statistics of multiple preprocessing layers.

This layer will contain the merged state.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `layers` | Layers whose statistics should be merge with the statistics of this layer. |

<br />

### `reset_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L102-L105)

    reset_state()

Resets the statistics of the preprocessing layer.

### `update_state`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.5.0/tensorflow/python/keras/engine/base_preprocessing_layer.py#L93-L100)

    update_state(
        data
    )

Accumulates statistics for the preprocessing layer.

<br />

<br />

<br />

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

<br />