训练SVM坏参数错误

Question

我按照How to train an SVM with opencv based on a set of images?中的代码执行了以下异常

OpenCV错误：cvCheckTrainData中的错误参数（列车数据必须是浮点矩阵），文件...... \ src \ opencv \ modules \ ml \ src \ inner_functions.cpp，第857行 线程“main”中的异常CvException [org.opencv.core.CvException：...... \ src \ opencv \ modules \ ml \ src \ inner_functions.cpp：857：错误：（ - 5）列车数据必须浮动函数cvCheckTrainData中的点矩阵 ]

我按照评论中提到的步骤进行操作。但仍然徒劳无功。

System.loadLibrary(Core.NATIVE_LIBRARY_NAME);

        Mat classes = new Mat();
        Mat trainingData = new Mat();
        Mat trainingImages = new Mat();
        Mat trainingLabels = new Mat();
        CvSVM clasificador;
        String path="C:\\java workspace\\ora\\images\\Color_Happy_jpg";
        for (File file : new File(path).listFiles()) {
            Mat img=new Mat();   
            Mat con = Highgui.imread(path+"\\"+file.getName());
            con.convertTo(img, CvType.CV_32F,1.0/255.0);

                img.reshape(1, 1);


                trainingImages.push_back(img);
               trainingLabels.push_back(Mat.ones(new Size(1, 1), CvType.CV_32F));
            }
        System.out.println("divide");
        path="C:\\java workspace\\ora\\images\\Color_Sad_jpg";
            for (File file : new File(path).listFiles()) {
                Mat img=new Mat();
                 Mat m=new Mat(new Size(640,480),CvType.CV_32FC3);
                Mat con = Highgui.imread(file.getAbsolutePath());

                con.convertTo(img, CvType.CV_32F,1.0/255.0);
                img.reshape(1, 1);
                trainingImages.push_back(img);
                System.out.println((CvType.typeToString(img.type())));
                trainingLabels.push_back(Mat.zeros(new Size(1, 1), CvType.CV_32F));
              }

            trainingLabels.copyTo(classes);
            CvSVMParams params = new CvSVMParams();
            params.set_kernel_type(CvSVM.LINEAR);

            System.out.println(CvType.typeToString(trainingImages.type()));
                        CvSVM svm=new CvSVM();
            System.out.println(svm.get_support_vector_count());
            boolean b=svm.train(trainingImages, classes);

            System.out.print(b);

 }

}