concatenationLayer

Concatenation layer

Description

A concatenation layer takes inputs and concatenates them along a specified dimension. The inputs must have the same size in all dimensions except the concatenation dimension.

Specify the number of inputs to the layer when you create it. The inputs have the names 'in1','in2',...,'inN', where N is the number of inputs. Use the input names when connecting or disconnecting the layer by using connectLayers or disconnectLayers.

Creation

Syntax

layer = concatenationLayer(dim,numInputs)

layer = concatenationLayer(dim,numInputs,'Name',name)

Description

layer = concatenationLayer(dim,numInputs) creates a concatenation layer that concatenates numInputs inputs along the specified dimension, dim. This function also sets the Dim and NumInputs properties.

layer = concatenationLayer(dim,numInputs,'Name',name) also sets the Name property.

Properties

Concatenation

Dim — Concatenation dimension

positive integer

Concatenation dimension, specified as a positive integer. The layer supports concatenating over the channel and spatial dimensions only.

Example: 4

Layer

Name — Layer name

"" (default) | character vector | string scalar

Layer name, specified as a character vector or string scalar. For Layer array input, the trainnet and dlnetwork functions automatically assign names to layers with the name "".

The ConcatenationLayer object stores this property as a character vector.

Data Types: char | string

NumInputs — Number of inputs

positive integer

Number of inputs to the layer, specified as a positive integer greater than or equal to 2.

The inputs have the names 'in1','in2',...,'inN', where N is NumInputs. For example, if NumInputs is 3, then the inputs have the names 'in1','in2', and 'in3'. Use the input names when connecting or disconnecting the layer using the connectLayers or disconnectLayers functions.

InputNames — Input Names

{'in1','in2',…,'inN'} (default)

Input names, specified as {'in1','in2',...,'inN'}, where N is the number of inputs of the layer.

Data Types: cell

NumOutputs — Number of outputs

1 (default)

This property is read-only.

Number of outputs from the layer, returned as 1. This layer has a single output only.

Data Types: double

OutputNames — Output names

{'out'} (default)

This property is read-only.

Output names, returned as {'out'}. This layer has a single output only.

Data Types: cell

Examples

Create and Connect Concatenation Layer

Create a concatenation layer that concatenates two inputs along the fourth dimension (channels). Name the concatenation layer 'concat'.

concat = concatenationLayer(4,2,'Name','concat')

concat = 
  ConcatenationLayer with properties:

          Name: 'concat'
           Dim: 4
     NumInputs: 2
    InputNames: {'in1'  'in2'}

Create two ReLU layers and connect them to the concatenation layer. The concatenation layer concatenates the outputs from the ReLU layers.

relu_1 = reluLayer('Name','relu_1');
relu_2 = reluLayer('Name','relu_2');

net = dlnetwork;
net = addLayers(net, relu_1);
net = addLayers(net, relu_2);
net = addLayers(net, concat);

net = connectLayers(net, 'relu_1', 'concat/in1');
net = connectLayers(net, 'relu_2', 'concat/in2');
plot(net)

Algorithms

Layer Input and Output Formats

Layers in a layer array or layer graph pass data to subsequent layers as formatted dlarray objects. The format of a dlarray object is a string of characters in which each character describes the corresponding dimension of the data. The formats consist of one or more of these characters:

• "S" — Spatial

• "C" — Channel

• "B" — Batch

• "T" — Time

• "U" — Unspecified

For example, you can describe 2-D image data that is represented as a 4-D array, where the first two dimensions correspond to the spatial dimensions of the images, the third dimension corresponds to the channels of the images, and the fourth dimension corresponds to the batch dimension, as having the format "SSCB" (spatial, spatial, channel, batch).

You can interact with these dlarray objects in automatic differentiation workflows, such as those for developing a custom layer, using a functionLayer object, or using the forward and predict functions with dlnetwork objects.

This table shows the supported input formats of ConcatenationLayer objects and the corresponding output format. If the software passes the output of the layer to a custom layer that does not inherit from the nnet.layer.Formattable class, or a FunctionLayer object with the Formattable property set to 0 (false), then the layer receives an unformatted dlarray object with dimensions ordered according to the formats in this table. The formats listed here are only a subset. The layer may support additional formats such as formats with additional "S" (spatial) or "U" (unspecified) dimensions.

The layer supports concatenation over "S" (spatial) and "C" (channel) dimensions only. The output format matches the input format. Each input must have data of the same format.

Input Format	Output Format
"CB" (channel, batch)	"CB" (channel, batch)
"SCB" (spatial, channel, batch)	"SCB" (spatial, channel, batch)
"SSCB" (spatial, spatial, channel, batch)	"SSCB" (spatial, spatial, channel, batch)
"SSSCB" (spatial, spatial, spatial, channel, batch)	"SSSCB" (spatial, spatial, spatial, channel, batch)
"CBT" (channel, batch, time)	"CBT" (channel, batch, time)
"SCBT" (spatial, channel, batch, time)	"SCBT" (spatial, channel, batch, time)
"SSCBT" (spatial, spatial, channel, batch, time)	"SSCBT" (spatial, spatial, channel, batch, time)
"SSSCBT" (spatial, spatial, spatial, channel, batch, time)	"SSSCBT" (spatial, spatial, spatial, channel, batch, time)
"CU" (channel, unspecified)	"CU" (channel, unspecified)
"SC" (spatial, channel)	"SC" (spatial, channel)
"SSC" (spatial, spatial, channel)	"SSC" (spatial, spatial, channel)
"SSSC" (spatial, spatial, spatial, channel)	"SSSC" (spatial, spatial, spatial, channel)

In dlnetwork objects, ConcatenationLayer objects also support these input and output format combinations.

Input Format	Output Format
"CT" (channel, time)	"CT" (channel, time)
"SCT" (spatial, channel, time)	"SCT" (spatial, channel, time)
"SSCT" (spatial, spatial, channel, time)	"SSCT" (spatial, spatial, channel, time)
"SSSCT" (spatial, spatial, spatial, channel, time)	"SSSCT" (spatial, spatial, spatial, channel, time)

Complex Numbers

ConcatenationLayer objects support complex-valued input and outputs. (since R2024a) The layer applies the same underlying operation to complex-valued input as it does to real-valued input and outputs complex-valued data where applicable.

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

Usage notes and limitations:

For code generation, you must pass a dlarray object with a channel (C) dimension as the input to this layer. For example, code generation supports data format such as "SSC" or "SSCBT".

GPU Code Generation

Generate CUDA® code for NVIDIA® GPUs using GPU Coder™.

Refer to the usage notes and limitations in the C/C++ Code Generation section. The same limitations apply to GPU code generation.

Version History

Introduced in R2019a

R2024a: Support for complex-valued inputs and outputs

ConcatenationLayer objects support complex-valued input and outputs. The layer applies the same underlying operation to complex-valued input as it does to real-valued input and outputs complex-valued data where applicable.