Hacker News Reader

Those numbers are quite impressive.

YOLOv4 -> YOLOv5

Inference time: 20ms -> 7ms (on P100)

Frames per second: 50 -> 140

Size: 244mb -> 27 mb

f(x)=c, zero size, infinite fps. You should also take some accuracy metric into account ;)

> "Similarly accurate"

MS COCO looks to be improved even overall.

OT: the stats above should be part of the PyTorch marketing material, indeed impressive