Package org.jetbrains.kotlinx.dl.api.core.layer.merge

Types

AbstractMerge

abstract class AbstractMerge(layerTypeName: String, name: String) : Layer

Layer that adds a list of inputs.

Add

Layer that adds a list of inputs.

Average

Layer that averages a list of inputs element-wise.

Concatenate

Layer that concatenates a list of inputs.

Dot

class Dot(axis: IntArray, normalize: Boolean, name: String) : AbstractMerge

Layer that computes a dot product between samples in two tensors.

Maximum

Layer that computes the maximum (element-wise) a list of inputs.

Minimum

Layer that computes the minimum (element-wise) a list of inputs.

Multiply

Layer that multiplies (element-wise) a list of inputs.

Subtract

Layer that subtracts inputs, following from the previous.

batchDot

fun batchDot(scope: Scope?, x: Operand<Float>, y: Operand<Float>, axis: IntArray): Operand<Float>

Batchwise dot product.

l2Normalize

fun l2Normalize(scope: Scope?, x: Operand<Float>, axis: IntArray?): Operand<Float>

Normalizes a tensor wrt the L2 norm alongside the specified axis.