TotalLayer

TotalLayer[]

represents a net layer taking a list of input tensors and performing elementwise addition on them.

Details and Options

  • TotalLayer has a single input port that must be a list of tensors.
  • Within a NetGraph, a TotalLayer can be connected using a single edge of the form {src1,src2,…}totlayer, where totlayer is the name or index of the TotalLayer, or as a multiple separate edges given in the corresponding order, as src1->totlayer,…,src2totlayer,….
  • TotalLayer[…][{tensor1,tensor2,…}] explicitly computes the output given a list of tensori.
  • TotalLayer is typically used inside NetGraph.
  • TotalLayer exposes the following ports for use in NetGraph etc.:
  • "Input"a list of tensors of arbitrary but equal dimensions
    "Output"a tensor of the same dimension as the inputs
  • When it cannot be inferred from other layers in a larger net, the option "Input"{shape1,shape2,…} can be used to fix the dimensions of the input tensors to TotalLayer. Each shape can be one of the following:
  • "Real"a single real number
    {d1,d2,…}a tensor of dimensions d1×d2×…

Examples

open allclose all

Basic Examples  (3)

Create a TotalLayer:

In[1]:=
Click for copyable input
Out[1]=

Create a TotalLayer with input dimension specified:

In[1]:=
Click for copyable input
Out[1]=

Apply the layer to a list of two vectors:

In[2]:=
Click for copyable input
Out[2]=

Construct a NetGraph with a TotalLayer that has two inputs:

In[1]:=
Click for copyable input
Out[1]=

Apply the layer to two vectors:

In[2]:=
Click for copyable input
Out[2]=

Scope  (2)

Properties & Relations  (2)

Possible Issues  (1)

See Also

AggregationLayer  SummationLayer  ConstantPlusLayer  CatenateLayer  NetChain  NetGraph  NetTrain

Introduced in 2016
(11.0)