OpenCV中神经网络介绍与使用
一：神经网络介绍
人工神经网络(ANN) 简称神经网络(NN)，最早它的产生跟并行计算有关系，主要是学习生物神经元互联触发实现学习、完成对输入数据的分类与识别。最基本的单元是神经元，有一个输入值，一个输出值，神经元本身根据激活函数来说决定输出值，最简单例子就是感知器
上述在开始的时候通过随机初始化生成权重，然后通过对数据X的训练迭代更新权重直到收敛，过程表示如下：
上述就是最简单的单个感知器工作原理。而在实际情况下，神经网络会有多个感知器，多个层级，我们把输入数据X的层称为输入层，最终输出结果的层称为输出层，中间各个层级统统称为隐藏层。一个典型的多层感知器(MLP)网络如下：
这个时候我们选择的激活函数就不能选择简单的二分类函数，OpenCV中支持的激活函数有三个：
上述网络中的权重值是未知的，只有通过训练我们才可以得到这些权重值，生成可用网络模型，OpenCV中支持的两种训练算法分别是：
- 反向传播算法
- RPROP算法
二：OpenCV中创建神经网络
首先创建多层感知器的层数：
代码语言：javascript复制Mat_<int> layerSizes(1, 3);
layerSizes(0, 0) = data.cols;
layerSizes(0, 1) = 20;
layerSizes(0, 2) = responses.cols;上面几行代码是创建一个三层的感知器，输入层跟数据维度有关系，隐藏层有20个神经元、最后是输出层，一般是类别表示。
代码语言：javascript复制Ptr<ANN_MLP> network = ANN_MLP::create();
network->setLayerSizes(layerSizes);
network->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0.1, 0.1);
network->setTrainMethod(ANN_MLP::BACKPROP, 0.1, 0.1);上述代码是创建神经网络，设置层数、激活函数、训练方法等参数。
代码语言：javascript复制Ptr<TrainData> trainData = TrainData::create(data, ROW_SAMPLE, responses);
network->train(trainData);上述代码是创建训练数据，执行网络训练
三：代码演示
OpenCV3.4中的sample的代码演示如下：
代码语言：javascript复制#include<opencv2/ml/ml.hpp>
usingnamespace std;
usingnamespace cv;
usingnamespace cv::ml;
int main()
{
//create random training data
Mat_<float> data(100, 100);
randn(data, Mat::zeros(1, 1, data.type()), Mat::ones(1, 1, data.type()));
//half of the samples for each class
Mat_<float> responses(data.rows, 2);
for(int i = 0; i<data.rows; i)
{
if(i < data.rows / 2)
{
responses(i, 0) = 1;
responses(i, 1) = 0;
}
else
{
responses(i, 0) = 0;
responses(i, 1) = 1;
}
}
/*
//example code for just a single response (regression)
Mat_<float> responses(data.rows, 1);
for (int i=0; i<responses.rows; i)
responses(i, 0) = i < responses.rows / 2 ? 0 : 1;
*/
//create the neural network
Mat_<int> layerSizes(1, 3);
layerSizes(0, 0) = data.cols;
layerSizes(0, 1) = 20;
layerSizes(0, 2) = responses.cols;
Ptr<ANN_MLP> network = ANN_MLP::create();
network->setLayerSizes(layerSizes);
network->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0.1, 0.1);
network->setTrainMethod(ANN_MLP::BACKPROP, 0.1, 0.1);
Ptr<TrainData> trainData = TrainData::create(data, ROW_SAMPLE, responses);
network->train(trainData);
if(network->isTrained())
{
printf("Predict one-vector:n");
Mat result;
network->predict(Mat::ones(1, data.cols, data.type()), result);
cout << result << endl;
printf("Predict training data:n");
for(int i = 0; i<data.rows; i)
{
network->predict(data.row(i), result);
cout << result << endl;
}
}
return0;
}四：基于神经网络的实现mnist数据集训练
代码语言：javascript复制
Mat train_images = readImages(0);
normalize(train_images, train_images, -1.0, 1.0, NORM_MINMAX, -1);
Mat train_labels = readLabels(0);
printf("n read mnist train dataset successfully...n");
Mat response = Mat::zeros(Size(10, train_labels.rows), CV_32FC1);
for(int i = 0; i < train_labels.rows; i ) {
int digit = train_labels.at<int>(i, 0);
response.at<float>(i, digit) = 1;
}
//create the neural network
Mat_<int> layerSizes(1, 3);
layerSizes(0, 0) = train_images.cols;
layerSizes(0, 1) = 100;
layerSizes(0, 2) = 10;
Ptr<ANN_MLP> network = ANN_MLP::create();
network->setLayerSizes(layerSizes);
network->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0.1, 0.1);
network->setTrainMethod(ANN_MLP::BACKPROP, 0.1, 0.1);
network->setTermCriteria(TermCriteria(TermCriteria::MAX_ITER, 1000, 1e-6));
Ptr<TrainData> trainData = TrainData::create(train_images, ROW_SAMPLE, response);
printf("start network trainning...n");
network->train(trainData);
if(network->isTrained())
{
printf("ready to save network model data...n");
network->save("D:/vcprojects/images/mnist/ann_knowledge.yml");
}
test_ann_minist();
waitKey(0);
return0;
