tiny-cnn是一個基于CNN的開源庫，它的License是BSD 3-Clause。作者也一直在維護更新，對進一步掌握CNN很有幫助，因此下面介紹下tiny-cnn在windows7 64bit vs2013的編譯及使用。

1.??????從https://github.com/nyanp/tiny-cnn下載源碼：

$ git clone https://github.com/nyanp/tiny-cnn.git? 版本號為77d80a8，更新日期2016.01.22

2.??????源文件中已經包含了vs2013工程，vc/tiny-cnn.sln，默認是win32的，examples/main.cpp需要OpenCV的支持，這里新建一個x64的控制臺工程tiny-cnn；

3.??????仿照源工程，將相應.h文件加入到新控制臺工程中，新加一個test_tiny-cnn.cpp文件；

4.??????將examples/mnist中test.cpp和train.cpp文件中的代碼復制到test_tiny-cnn.cpp文件中；

#include <iostream>
#include <string>
#include <vector>
#include <algorithm>
#include <tiny_cnn/tiny_cnn.h>
#include <opencv2/opencv.hpp>using namespace tiny_cnn;
using namespace tiny_cnn::activation;// rescale output to 0-100
template <typename Activation>
double rescale(double x)
{Activation a;return 100.0 * (x - a.scale().first) / (a.scale().second - a.scale().first);
}void construct_net(network<mse, adagrad>& nn);
void train_lenet(std::string data_dir_path);
// convert tiny_cnn::image to cv::Mat and resize
cv::Mat image2mat(image<>& img);
void convert_image(const std::string& imagefilename, double minv, double maxv, int w, int h, vec_t& data);
void recognize(const std::string& dictionary, const std::string& filename, int target);int main()
{//trainstd::string data_path = "D:/Download/MNIST";train_lenet(data_path);//teststd::string model_path = "D:/Download/MNIST/LeNet-weights";std::string image_path = "D:/Download/MNIST/";int target[10] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 };for (int i = 0; i < 10; i++) {char ch[15];sprintf(ch, "%d", i);std::string str;str = std::string(ch);str += ".png";str = image_path + str;recognize(model_path, str, target[i]);}std::cout << "ok!" << std::endl;return 0;
}void train_lenet(std::string data_dir_path) {// specify loss-function and learning strategynetwork<mse, adagrad> nn;construct_net(nn);std::cout << "load models..." << std::endl;// load MNIST datasetstd::vector<label_t> train_labels, test_labels;std::vector<vec_t> train_images, test_images;parse_mnist_labels(data_dir_path + "/train-labels.idx1-ubyte",&train_labels);parse_mnist_images(data_dir_path + "/train-images.idx3-ubyte",&train_images, -1.0, 1.0, 2, 2);parse_mnist_labels(data_dir_path + "/t10k-labels.idx1-ubyte",&test_labels);parse_mnist_images(data_dir_path + "/t10k-images.idx3-ubyte",&test_images, -1.0, 1.0, 2, 2);std::cout << "start training" << std::endl;progress_display disp(train_images.size());timer t;int minibatch_size = 10;int num_epochs = 30;nn.optimizer().alpha *= std::sqrt(minibatch_size);// create callbackauto on_enumerate_epoch = [&](){std::cout << t.elapsed() << "s elapsed." << std::endl;tiny_cnn::result res = nn.test(test_images, test_labels);std::cout << res.num_success << "/" << res.num_total << std::endl;disp.restart(train_images.size());t.restart();};auto on_enumerate_minibatch = [&](){disp += minibatch_size;};// trainingnn.train(train_images, train_labels, minibatch_size, num_epochs,on_enumerate_minibatch, on_enumerate_epoch);std::cout << "end training." << std::endl;// test and show resultsnn.test(test_images, test_labels).print_detail(std::cout);// save networksstd::ofstream ofs("D:/Download/MNIST/LeNet-weights");ofs << nn;
}void construct_net(network<mse, adagrad>& nn) {// connection table [Y.Lecun, 1998 Table.1]
#define O true
#define X falsestatic const bool tbl[] = {O, X, X, X, O, O, O, X, X, O, O, O, O, X, O, O,O, O, X, X, X, O, O, O, X, X, O, O, O, O, X, O,O, O, O, X, X, X, O, O, O, X, X, O, X, O, O, O,X, O, O, O, X, X, O, O, O, O, X, X, O, X, O, O,X, X, O, O, O, X, X, O, O, O, O, X, O, O, X, O,X, X, X, O, O, O, X, X, O, O, O, O, X, O, O, O};
#undef O
#undef X// construct netsnn << convolutional_layer<tan_h>(32, 32, 5, 1, 6)  // C1, 1@32x32-in, 6@28x28-out<< average_pooling_layer<tan_h>(28, 28, 6, 2)   // S2, 6@28x28-in, 6@14x14-out<< convolutional_layer<tan_h>(14, 14, 5, 6, 16,connection_table(tbl, 6, 16))              // C3, 6@14x14-in, 16@10x10-in<< average_pooling_layer<tan_h>(10, 10, 16, 2)  // S4, 16@10x10-in, 16@5x5-out<< convolutional_layer<tan_h>(5, 5, 5, 16, 120) // C5, 16@5x5-in, 120@1x1-out<< fully_connected_layer<tan_h>(120, 10);       // F6, 120-in, 10-out
}void recognize(const std::string& dictionary, const std::string& filename, int target) {network<mse, adagrad> nn;construct_net(nn);// load netsstd::ifstream ifs(dictionary.c_str());ifs >> nn;// convert imagefile to vec_tvec_t data;convert_image(filename, -1.0, 1.0, 32, 32, data);// recognizeauto res = nn.predict(data);std::vector<std::pair<double, int> > scores;// sort & print top-3for (int i = 0; i < 10; i++)scores.emplace_back(rescale<tan_h>(res[i]), i);std::sort(scores.begin(), scores.end(), std::greater<std::pair<double, int>>());for (int i = 0; i < 3; i++)std::cout << scores[i].second << "," << scores[i].first << std::endl;std::cout << "the actual digit is: " << scores[0].second << ", correct digit is: "<<target<<std::endl;// visualize outputs of each layer//for (size_t i = 0; i < nn.depth(); i++) {//	auto out_img = nn[i]->output_to_image();//	cv::imshow("layer:" + std::to_string(i), image2mat(out_img));//}visualize filter shape of first convolutional layer//auto weight = nn.at<convolutional_layer<tan_h>>(0).weight_to_image();//cv::imshow("weights:", image2mat(weight));//cv::waitKey(0);
}// convert tiny_cnn::image to cv::Mat and resize
cv::Mat image2mat(image<>& img) {cv::Mat ori(img.height(), img.width(), CV_8U, &img.at(0, 0));cv::Mat resized;cv::resize(ori, resized, cv::Size(), 3, 3, cv::INTER_AREA);return resized;
}void convert_image(const std::string& imagefilename,double minv,double maxv,int w,int h,vec_t& data) {auto img = cv::imread(imagefilename, cv::IMREAD_GRAYSCALE);if (img.data == nullptr) return; // cannot open, or it's not an imagecv::Mat_<uint8_t> resized;cv::resize(img, resized, cv::Size(w, h));// mnist dataset is "white on black", so negate requiredstd::transform(resized.begin(), resized.end(), std::back_inserter(data),[=](uint8_t c) { return (255 - c) * (maxv - minv) / 255.0 + minv; });
}

5.??????編譯時會提示幾個錯誤，解決方法是：

(1)、error C4996，解決方法：將宏_SCL_SECURE_NO_WARNINGS添加到屬性的預處理器定義中；

(2)、調用for_函數時，error C2668，對重載函數的調用不明教，解決方法：將for_中的第三個參數強制轉化為size_t類型；

6.??????運行程序，train時，運行結果如下圖所示：

7.??????對生成的model進行測試，通過畫圖工具，每個數字生成一張圖像，共10幅，如下圖：

通過導入train時生成的model，對這10張圖像進行識別，識別結果如下圖，其中6和9被誤識為5和1：

GitHub：https://github.com/fengbingchun/NN