Module: tf.keras.constraints

Constraints: functions that impose constraints on weight values.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.constraints

Classes

class Constraint

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(...)

serialize(...)