tfmri.initializers.VarianceScaling

class VarianceScaling(scale=1.0, mode='fan_in', distribution='truncated_normal', seed=None)

Bases: keras.initializers.initializers_v2.VarianceScaling

Initializer capable of adapting its scale to the shape of weights tensors.

Note

This initializer can be used as a drop-in replacement for tf.keras.initializers.VarianceScaling. However, this one also supports initialization of complex-valued weights. Simply pass dtype='complex64' or dtype='complex128' to its __call__ method.

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

With distribution="truncated_normal" or "untruncated_normal", samples are drawn from a truncated/untruncated normal distribution with a mean of zero and a standard deviation (after truncation, if used) stddev = sqrt(scale / n), where n is:

• number of input units in the weight tensor, if mode="fan_in"

• number of output units, if mode="fan_out"

• average of the numbers of input and output units, if mode="fan_avg"

With distribution="uniform", samples are drawn from a uniform distribution within [-limit, limit], where limit = sqrt(3 * scale / n).

Examples:

>>> # Standalone usage:
>>> initializer = tf.keras.initializers.VarianceScaling(
... scale=0.1, mode='fan_in', distribution='uniform')
>>> values = initializer(shape=(2, 2))

>>> # Usage in a Keras layer:
>>> initializer = tf.keras.initializers.VarianceScaling(
... scale=0.1, mode='fan_in', distribution='uniform')
>>> layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)

Args:

scale: Scaling factor (positive float). mode: One of “fan_in”, “fan_out”, “fan_avg”. distribution: Random distribution to use. One of “truncated_normal”,

“untruncated_normal” and “uniform”.

seed: A Python integer. Used to make the behavior of the initializer

deterministic. Note that a seeded initializer will produce the same random values across multiple calls.