Wolfram Language & System 11.0 (2016)|Legacy Documentation

This is documentation for an earlier version of the Wolfram Language.View current documentation (Version 11.2)

CatenateLayer

CatenateLayer[]
represents a net layer taking a list of input tensors and catenating them.

Details and OptionsDetails and Options

  • CatenateLayer[][{tensor1,tensor2,}] explicitly computes the output given a list of tensori.
  • CatenateLayer exposes the following ports for use in NetGraph etc.:
  • "Input"a list of numerical tensors of arbitrary but equal dimensions
    "Output"a numerical tensor
  • CatenateLayer is typically used inside NetChain, NetGraph, etc.
  • CatenateLayer normally infers the dimensions of its input from its context in NetChain etc. To specify the dimensions explicitly as {n1,n2,}, use TotalLayer["Input"->{n1,n2,}].

ExamplesExamplesopen allclose all

Basic Examples  (2)Basic Examples  (2)

Create a CatenateLayer:

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

Apply this layer to a list of vectors:

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

Construct a NetGraph with a CatenateLayer:

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

Apply the net graph to some data:

In[2]:=
Click for copyable input
Out[2]=
Introduced in 2016
(11.0)