Darknet: Don't want the image/window to display

[Flock1]

Hi,

I am trying to edit the code so that it doesn't the output image with bounding boxes. The cod should just continue after displaying the confidence of different labels. How should I do that?

[frvalentini]

What command are you using?

[Flock1]

I am using ./darknet detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights data/dog.jpg to run YOLO on the image. And it displays the image with bounded boxes. I want to avoid the image display.

[frvalentini]

Okay then
in examples/detector.c you should comment lines 611 to 619.

#ifdef OPENCV
            cvNamedWindow("predictions", CV_WINDOW_NORMAL); 
            if(fullscreen){
                cvSetWindowProperty("predictions", CV_WND_PROP_FULLSCREEN, CV_WINDOW_FULLSCREEN);
            }
            show_image(im, "predictions");
            cvWaitKey(0);
            cvDestroyAllWindows();
#endif

[Flock1]

Worked!!! Thanks a lot

[guptavasu1213]

I am trying to run the following command, but I don't want to see the video output. What lines of code should I modify?

./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights <videoPath>