tf.keras.constraints.MaxNorm

TensorFlow 2 version

View source on GitHub

MaxNorm weight constraint.

Inherits From: Constraint

View aliases

Main aliases

tf.keras.constraints.max_norm

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.constraints.MaxNorm, tf.compat.v1.keras.constraints.max_norm, `tf.compat.v2.keras.constraints.MaxNorm`, `tf.compat.v2.keras.constraints.max_norm`

tf.keras.constraints.MaxNorm(
    max_value=2, axis=0
)

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

Arguments
`m`	the maximum norm 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="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)`.

Arguments

m the maximum norm 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="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).

Methods

`get_config`

View source

get_config()

`call`

View source

__call__(
    w
)

Call self as a function.