I have images (1440,2560,3) images and I would like train YOLOR at 640 image size, because I trained YOLOv5 in this way. Now, I am little concerned about which files to use. yolor_p6.pt and yolor_w6.pt were trained at 1280 image size, so I dont know if it is good idea to use them. There is also a yolor_csp_x model which in .cfg file has width, height = 512 and test size was 640, so maybe it would be good choice?
Or maybe just use yolor_p6 or yolor_w6 model with cmd python3 train.py --image-size 640 640 ?
Hi,
I have images (1440,2560,3) images and I would like train YOLOR at 640 image size, because I trained YOLOv5 in this way. Now, I am little concerned about which files to use. yolor_p6.pt and yolor_w6.pt were trained at 1280 image size, so I dont know if it is good idea to use them. There is also a yolor_csp_x model which in .cfg file has width, height = 512 and test size was 640, so maybe it would be good choice?
Or maybe just use yolor_p6 or yolor_w6 model with cmd
python3 train.py --image-size 640 640?