tf.keras.layers.experimental.preprocessing.Discretization.DiscretizingCombiner

Combiner for the Discretization preprocessing layer.

tf.keras.layers.experimental.preprocessing.Discretization.DiscretizingCombiner(
    epsilon, num_bins
)

This class encapsulates the computations for finding the quantile boundaries of a set of data in a stable and numerically correct way. Its associated accumulator is a namedtuple('summaries'), representing summarizations of the data used to generate boundaries.

epsilon Error tolerance.
num_bins The desired number of buckets.

Methods

compute

View source

compute(
    values, accumulator=None
)

Compute a step in this computation, returning a new accumulator.

deserialize

View source

deserialize(
    encoded_accumulator
)

Deserialize an accumulator received from 'serialize()'.

extract

View source

extract(
    accumulator
)

Convert an accumulator into a dict of output values.

merge

View source

merge(
    accumulators
)

Merge several accumulators to a single accumulator.

restore

View source

restore(
    output
)

Create an accumulator based on 'output'.

serialize

View source

serialize(
    accumulator
)

Serialize an accumulator for a remote call.