Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

paulbridger.com

Post reply on HN
Print view View original

21–30 of 58 posts

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#21

Post by eggy »

eggy wrote: post #20
gcanyon wrote: post #8

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?

I see Rust is almost equal to C if not better in the graph, however, I think equally-skilled programmers in either language would show the Rust programmer spending more 'energy' programming and iterating than the C programmer, but then make the argument that the C program will use more 'energy' downstream if bugs slip in. In any case, an eye-opening metric on what I, and I am sure many, take for granted. Cool.

EDIT: I think Zig would come up pretty good here too:

https://twitter.com/andy_kelley/status/1317586767260774400

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#22

Post by darepublic »

cm2187 wrote: post #4

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.

Roulette spin predictor

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#23

Post by joshvm »

magicalhippo wrote: post #15
cm2187 wrote: post #4

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.

While I'm not into object detection such as this, I can easily imagine this being part of a system where you want the rest of the system to have time to act on the information. As such the point isn't that you can detect objects >N fps, but rather that the object detection shouldn't take more than X% of the time per cycle so that the overall cycle time can run at a given rate.

If your pipeline depends on running inference on a single frame at a time, for example some kind of control loop, then you need to be a bit careful about how you measure speed; you have to use the effective time per batch (ie batch size 1), not the amortised frames per second using as big a batch as will fit. You can still interleave processing though.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#24

Post by stabbles »

cm2187 wrote: post #4

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.

Another aspect is you might get better accuracy with larger input dimensions, but the number of pixels scales quadratically with width/height.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#25

Post by ineedasername »

raverbashing wrote: post #7
bufferoverflow wrote: post #6

Earlier quoted context omitted.

Self-driving. Ideally you want something around 1000fps and low latency, so it has time to react. I'm sure military and sports applications are obvious too.

Doubt Humans reaction times are much slower than that. In fact for some things it can take a whole second https://www.visualexpert.com/Resources/reactiontime.html Maybe racing sports have shorter reaction times, but I'd be frankly surprised if it was something 10fps for your average drive should be more than enough

No, that's only if you want the human to be able to make the reaction. If the application was self-driving, you'd prefer the car to react faster than a human. For a military application like projectile detection to avoid or destroy the object, you'd want something even faster.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#26

Post by moron4hire »

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.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#27

Post by izhak »

cm2187 wrote: post #4

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.

Hypersonic missiles

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#28

Post by briggers »

moron4hire wrote: post #26

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.

BTW, this is pumping the same video file through the network - not just a single file. I don't measure latency, but this is not a deep pipeline so it's easy to calculate.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#29

Post by briggers »

guywhocodes wrote: post #18
cm2187 wrote: post #4

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.

For me it's only exciting because it lowers the barrier of how much I can do with a much smaller system than double 2080ti's.

Yeah. A 2080Ti doesn't fit in your pocket or in your AR glasses but the same techniques and tools scale down.

Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

#30

Post by motoboi »

janimo wrote: post #14

How portable are these techniques to other architectures? Could >100 FPS be realistically achieved today using only CPUs or mobile phones?

Converting to ONNX gives you advantage in Intel CPU too, if you convert from ONNX to OpenVINO.
Post reply on HN