I am trying to implement one vs rest multiclass classification using LIBSVM.
The function is as below:
function [pred, ac, decv] = ovrpredict(y, x, model)
labelSet = model.labelSet;
labelSetSize = length(labelSet);
models = model.models;
decv= zeros(size(y, 1), labelSetSize);
for i=1:labelSetSize
[l,a,d] = svmpredict(double(y == labelSet(i)), x, models{i});
decv(:, i) = d * (2 * models{i}.Label(1) - 1); % ERROR IN THIS LINE
end
[tmp,pred] = max(decv, [], 2);
pred = labelSet(pred);
ac = sum(y==pred) / size(x, 1);
The error message I get is Attempt to reference field of non-structure array.
Reference to non-existent field 'Label'.
Any suggestions will be really helpful.
It might be a bit late for you now, but this looks less like a LIBSVM thing and more like a MATLAB thing. From what I can see in the script, you don't actually have 'models.Label' set to anything, so it doesn't exist - hence the error.
Dear Adam, Thank you for your answer but this really the LIBSVM and this
function [pred, ac, decv] = ovrpredict(y, x, model)
it is used for multi-classification problems and the input argument model is the struct consists from two fields.
The problem in your script is that at run time the object "models" is not a struct array as it should be according to your code.
https://www.gnu.org/software/octave/doc/interpreter/Structure-Arrays.html#Structure-Arrays
In any case, the method for obtaining probability estimates you're using is not the one recommended by libsvm authors
http://www.csie.ntu.edu.tw/~cjlin/papers/svmprob/svmprob.pdf
- Badges
- Science topic