0

After training an image detection model, how do I load the parameters of the bounding boxes for a specific operation?

Model: Darkflow Yolov2 Classes:7

For instance, if I set the threshold as 0.5, how do I utilize the resultant bounding boxes in a video to calculate the overlap. I am rather new to python and would appreciate it if someone could point me in the right direction.

I am unclear how to extract the individual class detection box and their relevant x and y data. Thank you!

Brandon Speedster Loo
  • 11
  • 5
  • I am rather new to darkflow and Yolo, so please share some code snippet. How do you use it? What do you get? What did you already try? – AlexisBRENON Dec 30 '19 at 15:44
  • YOLO is an image detection model that is implemented in a C++ based framework called Darknet on the Linux platform. Darkflow is using Tensorflow and can be installed on Windows. I am currently training the darkflow Yolov2 model which involves the feeding of a large quantity of images which are manually labeled with bounding boxes that dictates the class of the object within the box. The images are then iterated through many passes in which the model learns. The output will be a real time detection which draws boxes on objects within a video and identify their classes. – Brandon Speedster Loo Dec 30 '19 at 15:58
  • I haven't done any coding yet as I'm trying to understand how to extract the coordinates of the detected boxes from the video, to be utilized as the input, as I can't seem to find any info on it online. Thank you! – Brandon Speedster Loo Dec 30 '19 at 16:02
  • I know YOLO and darknet, but did not use it for a while. Do not hesitate to edit your question instead of puting long comments. Exctracting bounding boxes from the resulting images in the video would be difficult... If I remember well, yolo also prints the boxes information in the terminal, doesn't it? – AlexisBRENON Dec 30 '19 at 16:30

0 Answers0