vitis::ai::MultiTask - 3.5 English - UG1354

Input an image (cv::Mat).

Output is a struct of MultiTaskResult includes segmentation results, detection results and vehicle towards;

Sample code:

auto det = vitis::ai::MultiTask::create("multi_task");
auto image = cv::imread("sample_multitask.jpg");
auto result = det->run_8UC3(image);
cv::imwrite("sample_multitask_result.jpg",result.segmentation);

Display of the model results:

Quick Function Reference

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