• Remove pthread,opencv dependency.
• You need only 1 files for YOLO deep-learning.

You need backup/, bin/, train/, obj.cfg, obj.data, obj.names, test.txt, train.txt. All files are included in my repository. You can execute YOLOv2/train.bat for training.

YOLOv2_SE_Detection_Example/download_pretrained_model_and_dll.bat

Example source is in my repository. You need only 1 header file and 2 dll files.

Recall : 0.481481
Precision : 0.722222
Average detection time : 0.0363674
FPS : 27.4971

The class YOLOv2 that in YOLOv2SE.h has 3 method.

void Create(std::string weights,std::string cfg,std::string names);

This method load trained model(weights), network configuration(cfg) and class naming file(names)

• Parameter
  • weights : trained model path(e.g. "obj.weights")
  • cfg : network configuration file(e.g. "obj.cfg")
  • names : class naming file(e.g. "obj.names")

std::vector<BoxSE> Detect(cv::Mat img, float threshold);
std::vector<BoxSE> Detect(std::string file, float threshold);
std::vector<BoxSE> Detect(IplImage* img, float threshold);

This method is detecting objects of file,cv::Mat or IplImage.

• Parameter
  • file : image file path
  • img : 3-channel image.
  • threshold : It removes predictive boxes if there score is less than threshold.

void Release();

Release loaded network.

Original YOLOv2 has so many dependencies. I removed that.

A YOLOv2_Train_SE.exe is automatically choosing multi-gpu training. and select backup weights.

• Visual Studio 2015
• CUDA 8.0