Can not know how to use minibatchqueue for a deep learning network that takes input as 4-D numbers and output 3 numbers through fully-connected layer.

4 visualizzazioni (ultimi 30 giorni)
There is a MATLAB example that uses minibatchqueue for input date as 4-D (image) and output as categorical. What I need is to update this example to accept output to be three numberical values (through a 3-fully connected layer).
The MATLAB example is:
[XTrain,YTrain] = digitTrain4DArrayData;
dsX = arrayDatastore(XTrain,IterationDimension=4);
dsY = arrayDatastore(YTrain);
dsTrain = combine(dsX,dsY);
classes = categories(YTrain);
numClasses = numel(classes);
net = dlnetwork;
layers = [
imageInputLayer([28 28 1],Mean=mean(XTrain,4))
convolution2dLayer(5,20)
reluLayer
convolution2dLayer(3,20,Padding=1)
reluLayer
convolution2dLayer(3,20,Padding=1)
reluLayer
fullyConnectedLayer(numClasses)
softmaxLayer];
net = addLayers(net,layers);
net = initialize(net);
miniBatchSize = 128;
mbq = minibatchqueue(dsTrain,...
MiniBatchSize=miniBatchSize,...
PartialMiniBatch="discard",...
MiniBatchFcn=@preprocessMiniBatch,...
MiniBatchFormat=["SSCB",""]);
function [X,Y] = preprocessMiniBatch(XCell,YCell)
% Extract image data from the cell array and concatenate over fourth
% dimension to add a third singleton dimension, as the channel
% dimension.
X = cat(4,XCell{:});
% Extract label data from cell and concatenate.
Y = cat(2,YCell{:});
% One-hot encode labels.
Y = onehotencode(Y,1);
end
Again, what I need is to know how to modify the code to accept three regression values at fully connected output layer.
Actually, I tried alot and alot without success. I think the main trick is the update that should be done inside this function: preprocessMiniBatch (defined above).
Thanks
  5 Commenti
Nader Rihan
Nader Rihan il 23 Lug 2024
Modificato: Nader Rihan il 23 Lug 2024
Hi Umar,
I have solved the issue. As I mentioned, the only issue with your solution is regressionLayer. If you remove it, all will be fine. I obtained this idea from this simulation:
where classification task is converted to regression one.
Have a nice day and thanks alot for your time.
Umar
Umar il 23 Lug 2024
I apologize Nader, attending meeting with software consultants for a large scale project. Glad to know your problem is resolved.

Accedi per commentare.

Risposte (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by