Module: tf.keras.constraints

Constraints: functions that impose constraints on weight values.

Classes

class Constraint: Base class for weight constraints.

class MaxNorm: MaxNorm weight constraint.

class MinMaxNorm: MinMaxNorm weight constraint.

class NonNeg: Constrains the weights to be non-negative.

class RadialConstraint: Constrains Conv2D kernel weights to be the same for each radius.

class UnitNorm: Constrains the weights incident to each hidden unit to have unit norm.

class max_norm: MaxNorm weight constraint.

class min_max_norm: MinMaxNorm weight constraint.

class non_neg: Constrains the weights to be non-negative.

class radial_constraint: Constrains Conv2D kernel weights to be the same for each radius.

class unit_norm: Constrains the weights incident to each hidden unit to have unit norm.

Functions

deserialize(...)

get(...): Retrieves a Keras constraint function.

serialize(...)