News for hackers. Stuff that matters.

boscon

Re:Responding to the Controversy about YOLOv5 on Sunday June 14, 2020 @07:23PM (#23522316)
Judging by the many tests, their yolov5 is worse than yolov4, so they should call it yolov3.5
Re:YOLOv5: State-of-the-art object detection at 140 FPS on Wednesday June 10, 2020 @03:13PM (#23480895)
Latency is measured for batch=32 and divided by 32? This means that 1 batch will be processed in 500 milliseconds. I have never seen a more fake comparison.
Re:YOLOv4: Optimal Speed and Accuracy of Object Detection on Tuesday April 28, 2020 @06:22PM (#23012858)
This is a strictly scientific definition. When something lies on the Pareto optimality accuracy/speed curve, then it is optimal in terms of accuracy and speed. "Pareto optimality" is a formally defined concept used to describe when an allocation is optimal.