OpenCV 3.0无法加载神经网络 [英] OpenCV 3.0 Can't load neural network

问题描述

我需要在我的OpenCV（3.0版）项目中使用神经网络。我创建和训练神经网络，它的工作原理，但如果我想加载神经网络从YML文件，它不能预测。

这是一个代码我创建，训练和保存我的神经网络：

  FileStorage fs（nn.yml，FileStorage :: WRITE）; 
 
 int input_neurons = 7; 
 int hidden_​​neurons = 100; 
 int output_neurons = 5; 
 
 Ptr< TrainData> train_data = TrainData :: loadFromCSV（data.csv，10，7，12）; 
 
 Ptr  neural_network-> setTrainMethod（ANN_MLP :: BACKPROP）; 
 neural_network-> setBackpropMomentumScale（0.1）; 
 neural_network-> setBackpropWeightScale（0.05）; 
 neural_network-> setTermCriteria（TermCriteria（TermCriteria :: MAX_ITER，（int）10000，1e-6））; 
 
 Mat layers = Mat（3，1，CV_32SC1）; 
 layers.row（0）= Scalar（input_neurons）; 
 layers.row（1）= Scalar（hidden_​​neurons）; 
 layers.row（2）= Scalar（output_neurons）; 
 
 neuro_network-> setLayerSizes（layers）; 
 neural_network-> setActivationFunction（ANN_MLP :: SIGMOID_SYM，1,1）; 
 
 neural_network-> train（train_data）; 
 
 if（neural_network-> isTrained（））{
 neural_network-> write（fs）; 
 cout<< 没关系！ << endl; 
} 
  

但是下一次，如果我想从YML文件加载它：

  Ptr< ANN_MLP> neural_network = Algorithm :: load< ANN_MLP>（nn.yml，neural_network）; 
  

我得到输出：

-1。＃IND，-1。＃IND，-1。＃IND，-1。＃IND，-1。＃IND]

< IND，1.0263158,1.0263158,1.0263158,1.0263158]

[1.0263158,1.0263158,1.0263158,1.0263158,1.0263158]

> [ - 1.＃IND，-1。＃IND，-1。＃IND，-1。＃IND，-1。＃IND]

  Ptr& lt; ANN_MLP> neural_network = Algorithm :: load< ANN_MLP>（nn.yml）; 
  

此行导致我收到错误：

在cvGetFileNodeByName，文件C中，OpenCV错误：未指定的错误（节点既不是映射也不是空的collecti
）C：\builds\master_PackSlave-win64-vc12-shared\op
encv\modules\core\src\persistence.cpp，第739行

我做错了什么？

您可以使用保存和 load 或写和读

所以你需要做：

  //保存
 neural_network-> save（nn.yml）; 
 
 // Load 
 Ptr< ANN_MLP> nn = Algorithm :: load< ANN_MLP>（nn.yml）; 
  

或：

 code> // Write 
 neural_network-> write（fs）; 
 
 //读取
 FileStorage ffs（nn.yml，FileStorage :: READ）; 
 Ptr< ANN_MLP> nn = Algorithm :: read< ANN_MLP>（ffs.root（））; 
  

I need to use a neural network in my OpenCV (version 3.0) project. I've created and trained neural network and it works, but if I want to load neural network from YML file, it doesn't predict.

This is a code where I creat, train and save my neural network:

FileStorage fs("nn.yml", FileStorage::WRITE);

int input_neurons = 7;
int hidden_neurons = 100;
int output_neurons = 5;

Ptr<TrainData> train_data = TrainData::loadFromCSV("data.csv", 10, 7, 12);

Ptr<ANN_MLP> neural_network = ANN_MLP::create();
neural_network->setTrainMethod(ANN_MLP::BACKPROP);
neural_network->setBackpropMomentumScale(0.1);
neural_network->setBackpropWeightScale(0.05);
neural_network->setTermCriteria(TermCriteria(TermCriteria::MAX_ITER, (int)10000, 1e-6));

Mat layers = Mat(3, 1, CV_32SC1);
layers.row(0) = Scalar(input_neurons);
layers.row(1) = Scalar(hidden_neurons);
layers.row(2) = Scalar(output_neurons);

neural_network->setLayerSizes(layers);
neural_network->setActivationFunction(ANN_MLP::SIGMOID_SYM, 1, 1); 

neural_network->train(train_data);

if (neural_network->isTrained()) { 
    neural_network->write(fs);
    cout << "It's OK!" << endl; 
}

But next time, if I want to load it from YML file:

Ptr<ANN_MLP> neural_network = Algorithm::load<ANN_MLP>("nn.yml", "neural_network");

I get the output:

[-1.#IND, -1.#IND, -1.#IND, -1.#IND, -1.#IND]

[-1.#IND, 1.0263158, 1.0263158, 1.0263158, 1.0263158]

[1.0263158, 1.0263158, 1.0263158, 1.0263158, 1.0263158]

[-1.#IND, -1.#IND, -1.#IND, -1.#IND, -1.#IND]

Ptr<ANN_MLP> neural_network = Algorithm::load<ANN_MLP>("nn.yml");

This line cause that I get an error:

OpenCV Error: Unspecified error (The node is neither a map nor an empty collecti on) in cvGetFileNodeByName, file C:\builds\master_PackSlave-win64-vc12-shared\op encv\modules\core\src\persistence.cpp, line 739

What am I doing wrong? Where is the problem?

解决方案

You can use save and load, or write and read, but you shouldn't mix them.

So you either need to do:

// Save
neural_network->save("nn.yml");

// Load
Ptr<ANN_MLP> nn = Algorithm::load<ANN_MLP>("nn.yml");

or:

// Write
neural_network->write(fs);

// Read
FileStorage ffs("nn.yml", FileStorage::READ);
Ptr<ANN_MLP> nn = Algorithm::read<ANN_MLP>(ffs.root());

这篇关于OpenCV 3.0无法加载神经网络的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！