Search code examples
deep-learningobject-detectionyolobounding-box

How to show few correct bounding boxes instead of all detectiones in YOLOv3

This is my first YOLOv3 project to detect objects with 2 classes. In the resuls I am seeing plenty of detections. Is it possible to show only those boxes which has more than 70% (for example) accuracy or lets say top 3 boxes for each class? Would somebody please help?

my test is executed as follows: !./darknet detector test data/obj.data cfg/yolov3_custom.cfg ~/yolov3_custom_last.weights /content/5.png

Solution

  • You must set 0.7 threshold value, if you want see only boxes which has more than 70% confidence score.

    like this !./darknet detector test data/obj.data cfg/yolov3_custom.cfg ~/yolov3_custom_last.weights /content/5.png -thresh 0.7