LayerNormalization

class LayerNormalization<T : DType, V>(normalizedShape: IntArray, eps: Double = 1.0E-5, elementwiseAffine: Boolean = true, val name: String = "LayerNormalization", initGamma: Tensor<T, V>? = null, initBeta: Tensor<T, V>? = null) : Module<T, V> , ModuleParameters<T, V> (source)

LayerNormalization layer - Used in attention mechanisms. Normalizes the input across the last dimension(s).

Parameters

normalizedShape

The shape of the normalization (typically the last dimension(s))

eps

Small value added to the denominator for numerical stability

elementwiseAffine

Whether to learn elementwise affine parameters (gamma and beta)

name

Name of the module

initGamma

Initial gamma (scale) parameter

initBeta

Initial beta (shift) parameter

Constructors

Link copied to clipboard
constructor(normalizedShape: IntArray, eps: Double = 1.0E-5, elementwiseAffine: Boolean = true, name: String = "LayerNormalization", initGamma: Tensor<T, V>? = null, initBeta: Tensor<T, V>? = null)

Properties

Link copied to clipboard
open override val modules: List<Module<T, V>>
Link copied to clipboard
open override val name: String
Link copied to clipboard
open override val params: List<ModuleParameter<T, V>>

Parameters owned by this node (weights, biases, etc.).

Functions

Link copied to clipboard
open override fun forward(input: Tensor<T, V>, ctx: ExecutionContext): Tensor<T, V>