tfl.pwl_calibration_layer.NaiveBoundsConstraints

Naively clips all elements of tensor to be within bounds.

tfl.pwl_calibration_layer.NaiveBoundsConstraints(
    lower_bound=None, upper_bound=None
)

This constraint is used only for the weight tensor for missing output value.

Args
`lower_bound`	Lower bound to clip variable values to.
`upper_bound`	Upper bound to clip variable values to.

Methods

@classmethod
from_config(
    config
)

Instantiates a weight constraint from a configuration dictionary.

constraint = UnitNorm()
config = constraint.get_config()
constraint = UnitNorm.from_config(config)

Args
`config`	A Python dictionary, the output of `get_config`.

Returns
A `tf.keras.constraints.Constraint` instance.

get_config()

Standard Keras config for serialization.

__call__(
    w
)

Applies constraints to w.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2024-08-02 UTC.