tf.keras.initializers.Identity

View source on GitHub

Initializer that generates the identity matrix.

Inherits From: Initializer

tf.keras.initializers.Identity(
    gain=1.0
)

Initializers allow you to pre-specify an initialization strategy, encoded in the Initializer object, without knowing the shape and dtype of the variable being initialized.

Only usable for generating 2D matrices.

Examples:

def make_variable(k, initializer):
  return tf.Variable(initializer(shape=[k, k], dtype=tf.float32))
make_variable(2, tf.initializers.Identity())
<tf.Variable ... shape=(2, 2) dtype=float32, numpy=
array([[1., 0.],
       [0., 1.]], dtype=float32)>
make_variable(3, tf.initializers.Identity(gain=0.5))
<tf.Variable ... shape=(3, 3) dtype=float32, numpy=
array([[0.5, 0. , 0. ],
       [0. , 0.5, 0. ],
       [0. , 0. , 0.5]], dtype=float32)>

gain Multiplicative factor to apply to the identity matrix.

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)

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

Returns
An Initializer instance.

get_config

View source

get_config()

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

Returns
A JSON-serializable Python dict.

__call__

View source

__call__(
    shape, dtype=tf.dtypes.float32
)

Returns a tensor object initialized as specified by the initializer.

Args
shape Shape of the tensor.
dtype Optional dtype of the tensor. Only floating point types are supported.

Raises
ValueError If the dtype is not floating point
ValueError If the requested shape does not have exactly two axes.