How to use Bag of features with inceptionv3?

i have imdsTrain and imdsValidation

Then i want to bring this

bag = bagOfFeatures(trainingSet);

to use with this code

net = inceptionv3;

lgraph = layerGraph(net);

figure('Units','normalized','Position',[0.1 0.1 0.8 0.8]);

plot(lgraph)

net.Layers(1)

inputSize = net.Layers(1).InputSize;

lgraph = removeLayers(lgraph, {'predictions','predictions_softmax','ClassificationLayer_predictions'});

numClasses = numel(categories(imdsTrain.Labels));

newLayers = [

fullyConnectedLayer(numClasses,'Name','fc','WeightLearnRateFactor',10,'BiasLearnRateFactor',10)

softmaxLayer('Name','softmax')

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

lgraph = addLayers(lgraph,newLayers);

lgraph = connectLayers(lgraph,'avg_pool','fc');

pixelRange = [-30 30];

imageAugmenter = imageDataAugmenter( ...

'RandXReflection',true, ...

'RandXTranslation',pixelRange, ...

'RandYTranslation',pixelRange);

augimdsTrain = augmentedImageDatastore(inputSize(1:2),imdsTrain, ...

'DataAugmentation',imageAugmenter);

augimdsValidation = augmentedImageDatastore(inputSize(1:2),imdsValidation);

options = trainingOptions('sgdm', ...

'MiniBatchSize',10, ...

'MaxEpochs',4, ...

'InitialLearnRate',1e-4, ...

'ValidationData',augimdsValidation, ...

'ValidationFrequency',3, ...

'ValidationPatience',Inf, ...

'Verbose',false ,...

'Plots','training-progress');

net = trainNetwork(augimdsTrain,lgraph,options);

i want to know how to use Bag of features as features with inceptionv3

Answer 1

[Udit06]

You can refer to the following research paper for the same:

https://arxiv.org/pdf/2105.04895

Lorente, Ò., Riera, I., & Rana, A. (2021). Image classification with classic and deep learning techniques. arXiv preprint arXiv:2105.04895.