Why is the Score Transform lost when using "saveCompactModel"?

I simply modified the MATLAB fisheriris example at:

https://www.mathworks.com/help/stats/savecompactmodel.html

to add "fitSVMPosterior". As you can see in this example the score transform is lost after "loadCompactModel". Is there a reason it does not save the score transform for deployment?

Code example:

load fisheriris
inds = ~strcmp(species,'setosa');
X = meas(inds,:);
Y = species(inds);
Mdl = fitcsvm(X,Y);

MdlScore=fitSVMPosterior(Mdl);
saveCompactModel(MdlScore,'SVMIris');

And then when I do this,

loadCompactModel('SVMIris')

I get the following warning message:

Warning: Unable to restore ScoreTransform property. Call

fitSVMPosterior to fit posterior probabilities.

> In classreg.learning.classif.CompactClassificationSVM.fromStruct (line 296)

In classreg.coderutils.structToModel (line 50)

In loadCompactModel (line 30)

Answer 1

[MathWorks Support Team]

One of the limitations of using "saveCompactModel" to save an SVM model with capabilities to predict posterior probabilities is that "loadCompactModel" cannot restore the 'ScoreTransform' property to the MATLAB Workspace.

However, while preforming code generation, "loadCompactModel" is able to load the model along with the 'ScoreTransform' property at compile time within an entry function, and hence should function properly.

For more information on such limitations on various model objects while using "loadCompactModel", please refer to the documentation link below:

https://www.mathworks.com/help/stats/loadcompactmodel.html#bvcl05n-1-CompactMdl