tfc.layers.IdentityInitializer

Initialize to the identity kernel with the given shape.

View aliases

Main aliases

tfc.IdentityInitializer

tfc.layers.IdentityInitializer(
    gain=1
)

This creates an n-D kernel suitable for SignalConv* with the requested support that produces an output identical to its input (except possibly at the signal boundaries).

Note: The identity initializer in tf.keras.initializers is only suitable for matrices, not for n-D convolution kernels (i.e., no spatial support).

Methods

from_config

@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, the output of get_config().

Returns
An Initializer instance.

get_config

View source

get_config()

Returns the initializer's configuration as a JSON-serializable dict.

Returns
A JSON-serializable Python dict.

__call__

View source

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

Returns a tensor object initialized as specified by the initializer.

Args
shape	Shape of the tensor.
dtype	Optional dtype of the tensor.
**kwargs	Additional keyword arguments.