Class UnitNorm
Inherits From: Constraint
Aliases:
- Class
tf.keras.constraints.UnitNorm
- Class
tf.keras.constraints.unit_norm
Defined in tensorflow/python/keras/constraints.py
.
Constrains the weights incident to each hidden unit to have unit norm.
Arguments:
axis
: integer, axis along which to calculate weight norms. For instance, in aDense
layer the weight matrix has shape(input_dim, output_dim)
, setaxis
to0
to constrain each weight vector of length(input_dim,)
. In aConv2D
layer withdata_format="channels_last"
, the weight tensor has shape(rows, cols, input_depth, output_depth)
, setaxis
to[0, 1, 2]
to constrain the weights of each filter tensor of size(rows, cols, input_depth)
.
__init__
__init__(axis=0)
Initialize self. See help(type(self)) for accurate signature.
Methods
tf.keras.constraints.UnitNorm.__call__
__call__(w)
Call self as a function.
tf.keras.constraints.UnitNorm.get_config
get_config()