libSVM3.17的安装

本文只是搬运与记录

安装的帖子参考

一、http://www.matlabsky.com/thread-10966-1-1.html

二、http://blog.youkuaiyun.com/abcjennifer/article/details/7370177

下载

http://download.youkuaiyun.com/detail/wzh_xwjh/5648969

安装后的使用

load报错

数据的载入在参考贴子二中有解释

3.17的版本

svmpredict的返回参数格式有变化

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.