tf.keras.initializers.Orthogonal

View source on GitHub

Initializer that generates an orthogonal matrix.

Inherits From: Initializer

tf.keras.initializers.Orthogonal(
    gain=1.0, seed=None
)

Also available via the shortcut function tf.keras.initializers.orthogonal.

If the shape of the tensor to initialize is two-dimensional, it is initialized with an orthogonal matrix obtained from the QR decomposition of a matrix of random numbers drawn from a normal distribution. If the matrix has fewer rows than columns then the output will have orthogonal rows. Otherwise, the output will have orthogonal columns.

If the shape of the tensor to initialize is more than two-dimensional, a matrix of shape (shape[0] * ... * shape[n - 2], shape[n - 1]) is initialized, where n is the length of the shape vector. The matrix is subsequently reshaped to give a tensor of the desired shape.

Examples:

# Standalone usage:
initializer = tf.keras.initializers.Orthogonal()
values = initializer(shape=(2, 2))

# Usage in a Keras layer:
initializer = tf.keras.initializers.Orthogonal()
layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)

References:

Saxe et al., 2014 (pdf)

Methods

from_config

View source

@classmethod
from_config(
    config
)

Instantiates an initializer from a configuration dictionary.

Example:

initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)

get_config

View source

get_config()

Returns the configuration of the initializer as a JSON-serializable dict.

__call__

View source

__call__(
    shape, dtype=None, **kwargs
)

Returns a tensor object initialized to an orthogonal matrix.