Error using nnet.cnn.L​ayerGraph>​iThrowErro​rIfStartLa​yerIsOutpu​tLayer Unable to connect to the layer 'Classific​ationLayer​_fc1000'. This layer is an output layer and has no outp

Hi everyone,

I am trying to learn deep learning but I am getting the error. here is the code.

gTruth(1:4,:)

rng(0);

shuffledIndices = randperm(height(gTruth));

idx = floor(0.6 * length(shuffledIndices) );

trainingData = gTruth(shuffledIndices(1:idx),:);

testData = gTruth(shuffledIndices(idx+1:end),:);

imdsTrain = imageDatastore(trainingData{:,'imageFilename'});

bldsTrain = boxLabelDatastore(trainingData(:,2:end));

imdsTest = imageDatastore(testData{:,'imageFilename'});

bldsTest = boxLabelDatastore(testData(:,2:end));

trainingData = combine(imdsTrain,bldsTrain);

testData = combine(imdsTest, bldsTest);

data = read(trainingData);

I = data{1};

bbox = data{2};

annotatedImage = insertShape(I,'rectangle',bbox);

annotatedImage = imresize(annotatedImage,2);

figure

imshow(annotatedImage)

net = resnet50();

lgraph = layerGraph(net);

inputSize = [2872 920 3];

classNames = {'orangecone','bluecone', 'yellowcone'};

ssdLayerGraph = removeLayers(lgraph,'activation_40_relu');

weightsInitializerValue = 'glorot';

biasInitializerValue = 'zeros';

% Append Extra layers on top of a base network.

extraLayers = [];

% Add conv6_1 and corresponding reLU

filterSize = 1;

numFilters = 256;

numChannels = 1024;

conv6_1 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Name = 'conv6_1', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu6_1 = reluLayer(Name = 'relu6_1');

extraLayers = [extraLayers; conv6_1; relu6_1];

% Add conv6_2 and corresponding reLU

filterSize = 3;

numFilters = 512;

numChannels = 256;

conv6_2 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Padding = "same", ...

Stride = [2, 2], ...

Name = 'conv6_2', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu6_2 = reluLayer(Name = 'relu6_2');

extraLayers = [extraLayers; conv6_2; relu6_2];

% Add conv7_1 and corresponding reLU

filterSize = 1;

numFilters = 128;

numChannels = 512;

conv7_1 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Name = 'conv7_1', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu7_1 = reluLayer(Name = 'relu7_1');

extraLayers = [extraLayers; conv7_1; relu7_1];

% Add conv7_2 and corresponding reLU

filterSize = 3;

numFilters = 256;

numChannels = 128;

conv7_2 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Padding = "same", ...

Stride = [2, 2], ...

Name = 'conv7_2', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu7_2 = reluLayer(Name = 'relu7_2');

extraLayers = [extraLayers; conv7_2; relu7_2];

% Add conv8_1 and corresponding reLU

filterSize = 1;

numFilters = 128;

numChannels = 256;

conv8_1 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Name = 'conv8_1', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu8_1 = reluLayer(Name = 'relu8_1');

extraLayers = [extraLayers; conv8_1; relu8_1];

% Add conv8_2 and corresponding reLU

filterSize = 3;

numFilters = 256;

numChannels = 128;

conv8_2 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Name = 'conv8_2', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu8_2 = reluLayer(Name ='relu8_2');

extraLayers = [extraLayers; conv8_2; relu8_2];

% Add conv9_1 and corresponding reLU

filterSize = 1;

numFilters = 128;

numChannels = 256;

conv9_1 = convolution2dLayer(filterSize, numFilters, NumChannels = numChannels, ...

Padding = "same", ...

Name = 'conv9_1', ...

WeightsInitializer = weightsInitializerValue, ...

BiasInitializer = biasInitializerValue);

relu9_1 = reluLayer('Name', 'relu9_1');

extraLayers = [extraLayers; conv9_1; relu9_1];

if ~isempty(extraLayers)

lastLayerName = ssdLayerGraph.Layers(end).Name;

ssdLayerGraph = addLayers(ssdLayerGraph, extraLayers);

ssdLayerGraph = connectLayers(ssdLayerGraph, lastLayerName, extraLayers(1).Name);

end

error :

Error using nnet.cnn.LayerGraph>iThrowErrorIfStartLayerIsOutputLayer

Unable to connect to the layer 'ClassificationLayer_fc1000'. This layer is an output layer and has no

outputs to other layers.

Error in nnet.cnn.LayerGraph>iGetSourceInformation (line 629)

iThrowErrorIfStartLayerIsOutputLayer( layers(startLayerIndex) );

Error in nnet.cnn.LayerGraph/connectLayers (line 295)

[startLayerName,startLayerIndex,~, layerOutputIndex] = iGetSourceInformation(s, layers);

>>

[Rahul]

I have analyzed the code shared by you. Please make the changes in the code as shown below. You will see the layered graph.

if ~isempty(extraLayers)
    lastLayerName = ssdLayerGraph.Layers(end).Name;
    ssdLayerGraph = addLayers(ssdLayerGraph, extraLayers);
    %ssdLayerGraph = connectLayers(ssdLayerGraph, lastLayerName, extraLayers(1).Name);
end
analyzeNetwork(ssdLayerGraph)

In this, you will find issues in the attached image.

Please confirm the connections, its inputs and outputs. Based on that, you can connect your layers as per that information. Please refer to the documentation page of "addLayers", "connectLayers" for your reference.

Answer 1

[Rahul]

I have analyzed the code shared by you. Please make the changes in the code as shown below. You will see the layered graph.

if ~isempty(extraLayers)
    lastLayerName = ssdLayerGraph.Layers(end).Name;
    ssdLayerGraph = addLayers(ssdLayerGraph, extraLayers);
    %ssdLayerGraph = connectLayers(ssdLayerGraph, lastLayerName, extraLayers(1).Name);
end
analyzeNetwork(ssdLayerGraph)

Please confirm the connections, its inputs and outputs. Based on that, you can connect your layers as per that information. Please refer to the documentation page of "addLayers", "connectLayers" for your reference.