Main Content

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

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.

example

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

Properties

expand all

Concatenation

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

Example: 4

Layer

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

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.

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

Data Types: cell

This property is read-only.

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

Data Types: double

This property is read-only.

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

Data Types: cell

Examples

collapse all

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)

Figure contains an axes object. The axes object contains an object of type graphplot.

Algorithms

expand all

Extended Capabilities

Version History

Introduced in R2019a

expand all