New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Train YOLO v3 on subset of COCO #2920

Open

PROGRAMMINGENGINEER-NIKI opened this issue Apr 13, 2019 · 1 comment

PROGRAMMINGENGINEER-NIKI commented Apr 13, 2019 •

edited

Hi, Alexey I have 3 questions. I appreciate if you could clarify them.

I wanted to train YOLOv3 for a subset of classes namely, cat, dog, person.
Could you please explain the steps that I need to take in order to train for a subset of COCO using transfer learning?
Is there any way to detect only these classes without training? If yes could you explain how?
training yolov3 for a subset of images lets say, 4 class, will lead to better performance or not?

Thank you in advance!

Owner

AlexeyAB commented Apr 13, 2019

@PROGRAMMINGENGINEER-NIKI Hi,

Just add -dont_show before each line except cat, dog, person here: https://github.com/AlexeyAB/darknet/blob/master/data/coco.names

and run
./darknet detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights -thresh 0.25

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment