vitis::ai::YOLOv2 - 1.2 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2020-07-21
Version
1.2 English
Base class for detecting objects in the input image(cv::Mat). Input is an image(cv::Mat). Output is position of the objects in the input image. Sample code:
 auto img = cv::imread("sample_yolov2.jpg");
 auto model = vitis::ai::YOLOv2::create("yolov2_voc");
 auto result = model->run(img);
 for (const auto &bbox : result.bboxes) {
   int label = bbox.label;
   float xmin = bbox.x * img.cols + 1;
   float ymin = bbox.y * img.rows + 1;
   float xmax = xmin + bbox.width * img.cols;
   float ymax = ymin + bbox.height * img.rows;
   if (xmax > img.cols)
     xmax = img.cols;
   if (ymax > img.rows)
     ymax = img.rows;
   float confidence = bbox.score;

   cout << "RESULT: " << label << "\t" << xmin << "\t" << ymin << "\t" << xmax
       << "\t" << ymax << "\t" << confidence << "\n";
   rectangle(img, Point(xmin, ymin), Point(xmax, ymax), Scalar(0, 255, 0), 1,
            1, 0);
}

Quick Function Reference

The following table lists all the functions defined in the vitis::ai::YOLOv2 class:

Table 1. Quick Function Reference
Type Name Arguments
std::unique_ptr< YOLOv2 > create
  • const std::string & model_name
  • bool need_preprocess
YOLOv2Result run
  • const cv::Mat & image
std::vector< YOLOv2Result > run
  • images
int getInputWidth
  • void
int getInputHeight
  • void
size_t get_input_batch
  • void