Train on different type of custom data

[sasanasadiabadi]

Is it possible to train the LBF or AAM on a dataset (say some landmark localization in biomedical images) with different number of landmarks (say 40)? I'm getting the following error in my case.

Wrong n_landmarks, currently only 29 and 68 landmark points are supported training random forest

Also with the case of 68 landmarks, the trained model is not doing well prediction on custom objects.