VisDrone / VisDrone-Dataset

The dataset for drone based detection and tracking is released, including both image/video, and annotations.
1.22k stars 157 forks source link

crop image to 416 x 416 and change annotation accordingly #1

Open MuhammadAsadJaved opened 5 years ago

MuhammadAsadJaved commented 5 years ago

I want to train YOLO V3 for object detection on VisDrone dataset , for the YOLO V3 training I want to resize all the images to 416 x 416 and also change Annotations accordingly .

Is there any method or suggestions to do it ?