tf.compat.v1.keras.layers.experimental.preprocessing.Normalization

View source on GitHub

Class Normalization

Feature-wise normalization of the data.

Inherits From: Normalization

This layer will coerce its inputs into a normal 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.

What happens in adapt: Compute mean and variance of the data and store them as the layer's weights. adapt should be called before fit, evaluate, or predict.

Attributes:

  • axis: Integer or tuple of integers, the axis or axes that should be normalized (typically the features axis). We will normalize each element in the specified axis. The default is '-1' (the innermost axis); 0 (the batch axis) is not allowed.

__init__

View source

__init__(
    axis=-1,
    dtype=None,
    **kwargs
)

Methods

adapt

View source

adapt(
    data,
    reset_state=True
)

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

Arguments:

  • data: The data to train on. It can be passed either as a tf.data Dataset, or as a numpy array.
  • 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. Subclasses may choose to throw if reset_state is set to 'False'.