测试libsvm时出错

我在用heart_scale文件进行测试的时候，
[heart_scale_label,heart_scale_inst] =libsvmread('heart_scale');
model = svmtrain(heart_scale_label,heart_scale_inst);
这两步都没问题，但是在预测时：
[predict_label,accuracy]=svmpredict(heart_scale_label,heart_scale_inst,model)
后显示

Usage: [predicted_label, accuracy, decision_values/prob_estimates] = svmpredict(testing_label_vector, testing_instance_matrix, model, 'libsvm_options')
       [predicted_label] = svmpredict(testing_label_vector, testing_instance_matrix, model, 'libsvm_options')
Parameters:
  model: SVM model structure from svmtrain.
  libsvm_options:
    -b probability_estimates: whether to predict probability estimates, 0 or 1 (default 0); one-class SVM not supported yet
    -q : quiet mode (no outputs)
Returns:
  predicted_label: SVM prediction output vector.
  accuracy: a vector with accuracy, mean squared error, squared correlation coefficient.
  prob_estimates: If selected, probability estimate vector.

predict_label =

     []


accuracy =

     []

我检查了model是没有问题的，请问这是什么原因呢？谢谢！！

同求解答   :(

楼主是怎么解决的啊

请问 怎么解决呢？

同求，怎么解决的呢？

[predict_label]=svmpredict(heart_scale_label,heart_scale_inst,model);写成这样就可以咯。
看看使用说明Usage: [predicted_label, accuracy, decision_values/prob_estimates] = svmpredict(testing_label_vector, testing_instance_matrix, model, 'libsvm_options')
       [predicted_label] = svmpredict(testing_label_vector, testing_instance_matrix, model, 'libsvm_options')，这貌似是只有这两种使用形式，我改成[predict_label]=svmpredict(heart_scale_label,heart_scale_inst,model);这样就OK了。