TensorFlow 2.0 RC is available Learn more

tf.keras.constraints.UnitNorm

TensorFlow 2.0 version View source on GitHub

Class UnitNorm

Constrains the weights incident to each hidden unit to have unit norm.

Inherits From: Constraint

Aliases:

  • Class tf.compat.v1.keras.constraints.UnitNorm
  • Class tf.compat.v1.keras.constraints.unit_norm
  • Class tf.compat.v2.keras.constraints.UnitNorm
  • Class tf.compat.v2.keras.constraints.unit_norm
  • Class tf.keras.constraints.unit_norm

Arguments:

  • 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="channels_last", the weight tensor has shape (rows, cols, input_depth, output_depth), set axis to [0, 1, 2] to constrain the weights of each filter tensor of size (rows, cols, input_depth).

__init__

View source

__init__(axis=0)

Methods

__call__

View source

__call__(w)

get_config

View source

get_config()