YOLOv5 v6.0 is here – new Nano model at 1666 FPS

Posted by j-sizz on Wednesday October 13, 2021 @12:14PM
from the blog.roboflow.com dept.

https://blog.roboflow.com/yolov5-v6-0-is-here/

( 3 comments | 14 points | on HN )

Re:YOLOv5 v6.0 is here – new Nano model at 1666 FPS by Imnimo on Wednesday October 13, 2021 @01:52PM (#28855258)

I don't really grasp why inference speed of tiny YOLO models is still reported by using giant GPUs. I guess it helps to see the improvement from the previous iteration, but under what circumstances would I realistically want to run this on a P100 at 1600 fps? I feel like I'd rather know how fast it runs on, say, a Jetson or even a Raspberry Pi CPU.

[ Parent | on HN ]

Re:YOLOv5 v6.0 is here – new Nano model at 1666 FPS by thebruce87m on Wednesday October 13, 2021 @05:46PM (#28858100)

Something like an inference server on a cloud instance?

[ Parent | on HN ]

Re:YOLOv5 v6.0 is here – new Nano model at 1666 FPS by glenn-jocher on Thursday October 14, 2021 @03:56AM (#28861604)

Awesome :)

[ Parent | on HN ]