YOLO: Real-Time Object Detection

To use this model, first download the weights:

Then run the detector with the tiny config file and weights:

Running YOLO on test data isn’t very interesting if you can’t see the result. Darknet wants a file for each image with a line for each ground truth object in the image that looks like:

Where , , , and are relative to the image’s width and height. Run the command:

If you want to use multiple gpus run:

If you want to stop and restart training from a checkpoint:

If you are using YOLO version 2 you can still find the site here: you use YOLOv3 in your work please cite our paper!

Source: pjreddie.com