Closed bwkchee closed 6 years ago
A bit more is required, for interfacing with yolo. Can you please check the latest commit of test.cpp, and provide your inputs ? The updated file adds support for CV image.
https://github.com/prabindh/darknet/blob/master/arapaho/test.cpp
Arapaho now fully supports a test cycle - opening an image with OpenCV, running a detection with the C++ API, and dumping the object boundaries. Please check and update, if found ok, please close the issue. Thanks.
Announcement: Tag https://github.com/prabindh/darknet/tree/v4.01 is now released, with further compile fixes for Mac and windows, and Arapaho readme. For windows builds please use https://github.com/prabindh/darknet-cpp-windows
Would it be easier to use a cv mat in ArapahoV2.Detect since opencv is required? Is this the proper conversion for a cv::mat?
Mat image = imread(input, CV_LOAD_IMAGE_COLOR); w = image.rows h = image.cols; bgr = image.reshape(1,1);