ThreadingLayer

represents a net layer that takes two input tensors and applies a binary function f to corresponding tensor elements.

Details and Options

ThreadingLayer is typically used inside NetGraph.
ThreadingLayer has a single input port that must be a pair of tensors of identical dimensions.
In ThreadingLayer[f], the function f can be any one of the following: Plus, Subtract, Times, Divide, Power, Min, Max, Clip.
In general, f can be any object that when applied to two arguments gives any combination of Plus, Subtract, etc. together with Ramp, LogisticSigmoid, Tanh, ArcTan, ArcTanh, Sin, Sinh, ArcSin, ArcSinh, Cos, Cosh, ArcCos, ArcCosh, Log, Exp, Sqrt, Abs, Gamma, LogGamma and numbers.
ThreadingLayer[…][{a,b}] explicitly computes the output from applying the layer.
ThreadingLayer exposes the following ports for use in NetGraph etc.:
"Input" a pair of tensors of identical dimensions

"Output" a tensor with the same dimensions as the inputs
When they cannot be inferred from other layers in a larger net, the option "Input"{shape₁,shape₂} can be used to fix the dimensions of the two inputs to ThreadingLayer. Currently, shape₁ and shape₂ must be identical, although broadcasting functionality may be added in future. Each shape can be one of the following:
{d} ord a vector of dimensions d

{d₁,d₂,…} a tensor of dimensions d₁×d₂×…