Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
1–10 of 58 posts
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#2> 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?
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#3> 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?
The subject has been debated to death. Google it.
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#4Out 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.
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#5Out 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.
Very practical question :)
Exactly as you say, multi-stream throughput. Also for faster than realtime offline processing of video.
Check the caveats section at the end of the post - DeepStream is probably not well suited to high throughput single-stream inference.
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#6Out 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.
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.
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#7Out 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.
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
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#8A 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?
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#9Earlier 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
Answering my own question. Possibly industrial applications like detecting objects on a fast conveyor belt. A recycling facility for instance.
Re: Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream
#10Out 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.
Smart missiles and weapons i guess