tf.keras.initializers.Orthogonal

View source on GitHub

Initializer that generates an orthogonal matrix.

Inherits From: Initializer

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)

gain multiplicative factor to apply to the orthogonal matrix
seed A Python integer. An initializer created with a given seed will always produce the same random tensor for a given shape and dtype.

References:

Saxe et al., 2014 (pdf)

Methods

from_config

View source

Instantiates an initializer from a configuration dictionary.

Example:

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

Args
config A Python dictionary. It will typically be the output of get_config.

Returns
An Initializer instance.

get_config

View source

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

Returns
A JSON-serializable Python dict.

__call__

View source

Returns a tensor object initialized to an orthogonal matrix.

Args
shape Shape of the tensor.
dtype Optional dtype of the tensor. Only floating point types are supported. If not specified, tf.keras.backend.floatx() is used, which default to float32 unless you configured it otherwise (via tf.keras.backend.set_floatx(float_dtype))