RandomNormal

Initializer that generates tensors with a normal distribution.

Constructors

RandomNormal

fun RandomNormal(mean: Float = 0.0f, stdev: Float = 1.0f, seed: Long = 12L)

Creates a RandomNormal initializer.

apply

fun apply(fanIn: Int, fanOut: Int, tf: Ops, input: Operand<Float>, name: String): InitializerOperation

Adds an Assign Op to the graph to initialize a tensorflow variable as specified by the initializer.

initialize

open override fun initialize(fanIn: Int, fanOut: Int, tf: Ops, shape: Operand<Int>, name: String): Operand<Float>

Returns a Tensor object initialized as specified by the initializer.

toString

open override fun toString(): String

mean

val mean: Float = 0.0f

Mean of the random values to generate.

seed

val seed: Long = 12L

Used to create random seeds.

stdev

val stdev: Float = 1.0f

Standard deviation of the random values to generate.