Why do i receive Uncoonected input?

netWidth = 16;
layers = [
    imageInputLayer([224 224 3],'Name','input')
    
    convolution2dLayer(3,netWidth,'Padding','same','Name','convInp')
    
    batchNormalizationLayer('Name','BNInp')
    
    reluLayer('Name','reluInp')
   
    convolutionalUnit(netWidth,1,'S1U1')
    additionLayer(2,'Name','add11')
    reluLayer('Name','relu11')
    convolutionalUnit(netWidth,1,'S1U2')
    additionLayer(2,'Name','add12')
    reluLayer('Name','relu12')
    
    convolutionalUnit(2*netWidth,2,'S2U1')
    additionLayer(2,'Name','add21')
    reluLayer('Name','relu21')
    convolutionalUnit(2*netWidth,1,'S2U2')
    additionLayer(2,'Name','add22')
    reluLayer('Name','relu22')
    
    convolutionalUnit(4*netWidth,2,'S3U1')
    additionLayer(2,'Name','add31')
    reluLayer('Name','relu31')
    convolutionalUnit(4*netWidth,1,'S3U2')
    additionLayer(2,'Name','add32')
    reluLayer('Name','relu32')
    
    averagePooling2dLayer(8,'Name','globalPool')
    
    fullyConnectedLayer(2,'Name','fcFinal')
    
    softmaxLayer('Name','softmax')
    
    classificationLayer('Name','classoutput')
    ];

lgraph = layerGraph(layers);

lgraph = connectLayers(lgraph,'reluInp','add11/in2');

lgraph = connectLayers(lgraph,'relu11','add12/in2');

skip1 = [
    convolution2dLayer(1,2*netWidth,'Stride',2,'Name','skipConv1')
    batchNormalizationLayer('Name','skipBN1')];

lgraph = addLayers(lgraph,skip1);

lgraph = connectLayers(lgraph,'relu12','skipConv1');

lgraph = connectLayers(lgraph,'skipBN1','add21/in2');

lgraph = connectLayers(lgraph,'relu21','add22/in2');

skip2 = [
    convolution2dLayer(1,4*netWidth,'Stride',2,'Name','skipConv2')
    
    batchNormalizationLayer('Name','skipBN2')];

lgraph = addLayers(lgraph,skip2);

lgraph = connectLayers(lgraph,'relu22','skipConv2');

lgraph = connectLayers(lgraph,'skipBN2','add31/in2');

lgraph = connectLayers(lgraph,'relu31','add32/in2');

options = trainingOptions('sgdm', 'MiniBatchSize',128,'MaxEpochs',10,'InitialLearnRate',1e-4,'ExecutionEnvironment','parallel');

%[trainedNet1,traininfo] = trainNetwork(trainData,lgraph,options);
class = trainedNet1;

convnet= trainNetwork(trainData,layers,options);

Hello Community, please I have a problem with this code, when i run it they said:

Error in NOUVEAU (line 107)

convnet= trainNetwork(trainData,layers,options);

Caused by:

Layer 'add11': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Layer 'add12': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Layer 'add21': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Layer 'add22': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Layer 'add31': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Layer 'add32': Unconnected input. Each layer input must be connected to the output of another layer.

Detected unconnected inputs:

input 'in2'

Answer 1

[Gayathri]

Hi @Hind Haboubi,

The "unconnected inputs" error is occuring as in layers there are some unconnected errors. Please modify the line of code from

convnet= trainNetwork(trainData,layers,options);

to

convnet= trainNetwork(trainData,lgraph,options);

All the connections are made in "lgraph". So now the error will be resolved.

For more information about "layerGraph", please run the following command in the command window.

doc layerGraph

Hope this helps!