Hi abdu,
As per my understanding, you would like to use the ‘concatenationLayer()’ function to concatenate the output of two convolution layer.
Please refer to the code below to see how to concatenate the output of two ‘convolution2dLayer()’ layer. The same can be performed on other type of convolution layers like ‘convolution1dLayer()’, ‘convolution3dLayer()’ too.
im=imageInputLayer([100 100 3],Normalization="none");
layers1=[...
im
convolution2dLayer([5 5],10,Name="conv1")
concatenationLayer(1,2,Name='concatLayer')
];
layers2=[...
im
convolution2dLayer([5 5],10,Name="conv2")
];
lgraph = layerGraph;
lgraph = addLayers(lgraph,layers1);
lgraph = addLayers(lgraph,layers2);
lgraph = connectLayers(lgraph,'conv2','concatLayer/in2');
plot(lgraph)
%analyzeNetwork(dlnetwork(lgraph))
You can read about the functions used in the above code here:
- convolution2dLayer 2-D convolutional layer - MATLAB - MathWorks India
- concatenationLayer Concatenation layer - MATLAB - MathWorks India
- layerGraph Graph of network layers for deep learning - MATLAB - MathWorks India
- connectLayers Connect layers in layer graph or network - MATLAB connectLayers - MathWorks India
- analyzeNetwork Analyze deep learning network architecture - MATLAB analyzeNetwork - MathWorks India
- imageInputLayer Image input layer - MATLAB - MathWorks India
I hope this resolves the issue you are facing.
