tf.keras.layers.experimental.preprocessing.Normalization

View source on GitHub

Feature-wise normalization of the data.

tf.keras.layers.experimental.preprocessing.Normalization(
    axis=-1, dtype=None, **kwargs
)

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:

Methods

adapt

View source

adapt(
    data, reset_state=True
)

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

Arguments: