Open GattupalliMonica opened 1 year ago
you have to find the four corner point with x,y and label_name and class no. As you can see in sample image and txt file
you can also check that issue https://github.com/hukaixuan19970627/yolov5_obb/issues/320
You can use this tool https://github.com/RayOct18/labelImg.
I have integrated the code from cgvict into the current version of LabelImg, which allows for directly saving txt in the YOLOv5 OBB format needed for training.
After following the installation instructions in the README file, open the LabelImg program and click the button below "Save" until "RotatedYOLO" appears, and then you can start annotating!
How can we annotate the images to train in YOLOv5_obb. I means should we need to create rectangular bounding box and then convert them to yolov5_obb format?