from Hacker News

Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

by briggers on 10/18/20, 11:54 AM with 55 comments

  • by mozak1111 on 10/18/20, 3:06 PM

    I see this and I immediately think of "trash sorting" at ultra high speed. If one can combine this with a bunch of accurate (laser precision) air guns, to shoot and move individual pieces of trash you can sort through a truck load of trash in a matter of seconds, perhaps in the air while they are being dumped! compare this approach with how we are currently doing it [0] - Somebody should get Elon Musk on this project right away!

    [0] - https://www.youtube.com/watch?v=QbKA9uNgzYQ

  • by cm2187 on 10/18/20, 12:15 PM

    Out of curiosity, what are the possible use cases for object detection at >100 fps? I assume it would have to be objects that move very fast, i.e. nothing ordinary that I can think of.

    [edit] actually stupid question. I assume it's more about throughput than fps, i.e. be able to process lots of streams on the same machine, for instance for doing mass analysis of CCTV streams.

  • by janimo on 10/18/20, 1:02 PM

    How portable are these techniques to other architectures? Could >100 FPS be realistically achieved today using only CPUs or mobile phones?
  • by gcanyon on 10/18/20, 12:41 PM

    A weird question, but since there's another article on HN right now about programming language energy efficiency https://news.ycombinator.com/item?id=24816733 any idea whether going from 9fps to 1840fps consumes the same power, 200x the power, or somewhere in between?
  • by Grimm1 on 10/18/20, 5:06 PM

    Good work getting TensorRT running we had a real pain in the butt recently when working with it and just opted to go with ONNXRuntime, their graph optimizer and their TensorRT backend -- may not be as fast as straight TensorRT from comparisons I've seen but it got us to a competitive inference and latency so we're happy with it.
  • by moron4hire on 10/18/20, 2:22 PM

    Any word on latency? I didn't see anything in the article. I guess, since this is a synthetic test just pumping a single image file through repeatedly instead of an actual video stream, then it wouldn't realistically be measurable. But if latency is particularly low, this would be a boon for AR systems.
  • by stabbles on 10/18/20, 12:05 PM

    > There is evidence (measured using gil_load) that we were throttled by a fundamental Python limitation with multiple threads fighting over the Global Interpreter Lock (GIL).

    Can anyone comment on how often this is a problem and if this problem is truly fundamental to Python? Could it be solved in a Python 3.x release?

  • by indeyets on 10/18/20, 6:37 PM

    Name clash again… I thought about https://deepstream.io/