ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more


View source on GitHub

Feature-wise normalization of the data.

This layer will coerce its 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.

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.


Calculate the mean and variance by analyzing the dataset in adapt.

adapt_data = np.array([[1.], [2.], [3.], [4.], [5.]], dtype=np.float32)
input_data = np.array([[1.], [2.], [3.]], np.float32)
layer = Normalization()
<tf.Tensor: shape=(3, 1), dtype=float32, numpy=
array([[-1.4142135 ],
       [ 0.        ]], dtype=float32)>

axis Integer or tuple of integers, the axis or axes that should be "kept". These axes are not be summed over when calculating the normalization statistics. By default the last axis, the features axis is kept and any space or time axes are summed. Each element in the the axes that are kept is normalized independently. If axis is set to 'None', the layer will perform scalar normalization (diving the input by a single scalar value). The batch axis, 0, is always summed over (axis=0 is not allowed).



View source

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

data The data to train on. It can be passed either as a 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'.