HeNormal

class HeNormal(seed: Long) : VarianceScaling
Content copied to clipboard

He normal initializer.

Draws samples from a truncated normal distribution centered on 0 with stddev = sqrt(2 / fan_in) where fan_in is the number of input units in the weight tensor.

See also

Constructors

HeNormal
Link copied to clipboard
fun HeNormal(seed: Long = 12L)
Content copied to clipboard
Creates HeNormal initializer.

Functions

apply
Link copied to clipboard
fun apply(fanIn: Int, fanOut: Int, tf: Ops, input: Operand<Float>, name: String): Assign<Float>
Content copied to clipboard
Adds an Assign Op to the graph to initialize a tensorflow variable as specified by the initializer.
initialize
Link copied to clipboard
open override fun initialize(fanIn: Int, fanOut: Int, tf: Ops, shape: Operand<Int>, name: String): Operand<Float>
Content copied to clipboard
Returns a Tensor object initialized as specified by the initializer.
toString
Link copied to clipboard
open override fun toString(): String
Content copied to clipboard

Properties

distribution
Link copied to clipboard
val distribution: Distribution
Content copied to clipboard
Random distribution to use.
mode
Link copied to clipboard
val mode: Mode
Content copied to clipboard
One of "fan_in", "fan_out", "fan_avg".
scale
Link copied to clipboard
val scale: Double = 1.0
Content copied to clipboard
Scaling factor (should be positive).
seed
Link copied to clipboard
val seed: Long = 12L
Content copied to clipboard
Used to create random seeds.