tf.contrib.nn.alpha_dropout

View source on GitHub

Computes alpha dropout.

tf.contrib.nn.alpha_dropout(
    x, keep_prob, noise_shape=None, seed=None, name=None
)

Alpha Dropout is a dropout that maintains the self-normalizing property. For an input with zero mean and unit standard deviation, the output of Alpha Dropout maintains the original mean and standard deviation of the input.

See Self-Normalizing Neural Networks

x A tensor.
keep_prob A scalar Tensor with the same type as x. The probability that each element is kept.
noise_shape A 1-D Tensor of type int32, representing the shape for randomly generated keep/drop flags.
seed A Python integer. Used to create random seeds. See tf.compat.v1.set_random_seed for behavior.
name A name for this operation (optional).

A Tensor of the same shape of x.

ValueError If keep_prob is not in (0, 1].