|TensorFlow 2 version||View source on GitHub|
MinMaxNorm weight constraint.
See Migration guide for more details.
tf.keras.constraints.MinMaxNorm( min_value=0.0, max_value=1.0, rate=1.0, axis=0 )
Constrains the weights incident to each hidden unit to have the norm between a lower bound and an upper bound.
||the minimum norm for the incoming weights.|
||the maximum norm for the incoming weights.|
rate for enforcing the constraint: weights will be
rescaled to yield
integer, axis along which to calculate weight norms.
For instance, in a
__call__( w )
Call self as a function.