tf.keras.constraints.MaxNorm

MaxNorm weight constraint.

Inherits From: Constraint

Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value.

Also available via the shortcut function tf.keras.constraints.max_norm.

max_value the maximum norm value for the incoming weights.
axis integer, axis along which to calculate weight norms. For instance, in a Dense layer the weight matrix has shape (input_dim, output_dim), set axis to 0 to constrain each weight vector of length (input_dim,). In a Conv2D layer with data_format