error "Error using nnet.inter​nal.cnn.la​yer.util.i​nferParame​ters>iInfe​rSize (line 86) The output of layer 13 is incompatible with the input expected by layer 14."

where is the error in this code ..i only use googlenet as deep tuning without change any thing in it's Layers except the last 3 layers . i changed the size of my images to be similar of googlenet (224 224) so what wrong

net=googlenet;

TransfereLayers= net.Layers(2:end-3);

%% my layers Layers =[...

imageInputLayer([224 224 3],'Name','input')

TransfereLayers

fullyConnectedLayer(2,'Name',fc)

softmaxLayer

classificationLayer('Name','coutput')];

%% define the weights and biase

Layers(142).Weights = randn([2 1024]) * 0.001;

Layers(142).Bias = randn([2 1])*0.001 + 1;

%% options opts=trainingOptions('sgdm','Initiallearnrate',0.0001,'maxEpoch',maxEpochs ,..... 'Minibatchsize',miniBatchSize ,... 'Plots','training-progress',.... 'LearnRateSchedule', 'piecewise', ... 'LearnRateDropFactor', 0.1, ... 'LearnRateDropPeriod', 1, ... 'ValidationData',valDigitData,'ValidationFrequency',50 );

[mynet, traininfo] = trainNetwork(trainingimages,Layers,opts);

[Nicholas Howe]

I'm encountering a similar problem when trying to use googlenet. Likewise, inceptionv3 gives a similar error between layers 24 and 25. What's going on?

[Salma Hassan]

i didn't find what is wrong ? if you know please post the answer...thanks

[conngame]

You guys ever figure this problem out?

Answer 1

[Joakim Lindblad]

It's because GoogLeNet is a DAG which matlab handles differently than a layered network.

Checkout https://se.mathworks.com/help/nnet/ref/dagnetwork.html and https://se.mathworks.com/help/nnet/ref/googlenet.html

You can try with

trainNetwork(trainingimages,layerGraph(Layers),opts);

but I'm not sure that will be enough in this case.

[Johannes Bergstrom]

For an example showing how to do transfer learning with DAG networks, see Transfer Learning Using GoogLeNet.