使用OpenCV在ANN中使用笨重的CvMat *

时间:2014-11-07 05:36:10

标签: c++ opencv opencv-mat

我尝试使用OpenCV在C ++中训练神经网络。

我无法将cv :: Mat *(或Mat *,如果使用了命名空间cv)转换为CvMat *,我将不胜感激。


让我详细说明:

我有两个cv :: Mat *类型的数据结构。第一个是特征向量集,第二个是预期输出集。

   cv::Mat *feat = new cv::Mat(3000, 100, CV_32F, featureData);
   cv::Mat *op = new cv::Mat(3000, 2, CV_32F, expectedOutput);

(这些是特征向量长度= 100且输出状态= 2的3000个数据点)

这两个矩阵填充了正确尺寸的数据,并且在控制台上打印样本数据时似乎工作正常。

神经网络已初始化为:

   int layers_array[] = {100,200,2};    //hidden layer nodes = 200

   CvMat* layer = cvCreateMatHeader(1, 3, CV_32SC1); 
   cvInitMatHeader(layer, 1,3,CV_32SC1, layers_array);

   CvANN_MLP nnetwork;
   nnetwork.create(layer, CvANN_MLP::SIGMOID_SYM, SIGMOID_ALPHA, SIGMOID_BETA);

现在,ANN的列车方法是以下模板:

   virtual int train( const CvMat* inputs, const CvMat* outputs,
                       const CvMat* sampleWeights, const CvMat* sampleIdx=0,
                       CvANN_MLP_TrainParams params = CvANN_MLP_TrainParams(),
                       int flags=0 );

我尝试使用以下代码在cv :: Mat *和CvMat *之间进行转换:

   CvMat featMat,opMat;

   (&featMat)->cols = feat->cols;
   (&featMat)->rows = feat->rows;
   (&featMat)->type = CV_32F;
   (&featMat)->data.fl = (float *)feat->data;


   (&opMat)->cols = op->cols;
   (&opMat)->rows = op->rows;
   (&opMat)->type = CV_32F;
   (&opMat)->data.fl = (float *)op->data;

   //setting up the ANN training parameters

   int iterations = network.train(&featMat, &opMat, NULL, NULL, trainingParams);

当我运行此代码时,我在控制台中收到以下错误消息:

**OpenCV Error: Bad argument (input training data should be a floating-point matrix withthe number of rows equal to the number of training samples and the number
of columns equal to the size of 0-th (input) layer) in CvANN_MLP::prepare_to_train, file ..\..\OpenCV-2.3.0-win-src\OpenCV-2.3.0\modules\ml\src\ann_mlp.cpp, 
line 694**

我理解错误消息。但是,就我所知,我相信我还没有弄清楚输入/输出层中的节点数量。

你能帮我理解出了什么问题吗?

1 个答案:

答案 0 :(得分:2)

请尽量避免指向cv :: Mat以及CvMat *。

幸运的是,overload to CvANN_MLP::train以cv :: Mat为args,所以请改用:

   cv::Mat feat = cv::Mat(3000, 100, CV_32F, featureData);
   cv::Mat op = cv::Mat(3000, 2, CV_32F, expectedOutput);

   int layers_array[] = {100,200,2};    //hidden layer nodes = 200
   cv::Mat layers = cv::Mat (3, 1, CV_32SC1, layers_array );

   CvANN_MLP nnetwork;
   nnetwork.create(layers, CvANN_MLP::SIGMOID_SYM, SIGMOID_ALPHA, SIGMOID_BETA);

   int iterations = nnetwork.train(feat, op, cv::Mat(), cv::Mat(), CvANN_MLP_TrainParams());