Comment Comment by deepnotderp I'm pretty sure this isn't using the Tensor cores on the GPU.If you see here (https://github.com/ultralytics/yolov5/blob/master/README.md), the speed of inference on a V100 for YOLOv5s should be 2 ms per image, or 500 imgs/s, not the 44.6 img/s being reported here.This is important as it is more than an order of magnitude off. parent deepnotderp 5 years ago
If you see here (https://github.com/ultralytics/yolov5/blob/master/README.md), the speed of inference on a V100 for YOLOv5s should be 2 ms per image, or 500 imgs/s, not the 44.6 img/s being reported here.
This is important as it is more than an order of magnitude off.