Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream

Re:Object Detection at 1840 FPS with TorchScript, TensorRT a... by janimo on Sunday October 18, 2020 @09:02AM (#24817573)

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

[ Parent | on HN ]

Re:Object Detection at 1840 FPS with TorchScript, TensorRT a... by nl on Sunday October 18, 2020 @06:49PM (#24821762)

> Could >100 FPS be realistically achieved today using only CPUs or mobile phones?

Not yet.

Google's MediaPipe object detector (which is one of the most optimised mobile solutions around) can do "26fps on an Adreno 650 mobile GPU"[1].

The Adreno 650 is the GPU in the Snapdragon 865, ie the current high end SOC used by most non-Apple phones. This gives roughly the same performance as an iPhone 11.

[1] https://google.github.io/mediapipe/solutions/objectron.html

[2] https://www.tweaktown.com/news/69097/qualcomm-adreno-650-gpu...

[3] https://www.tomsguide.com/news/snapdragon-865-benchmarks

[ Parent | on HN ]

Re:Object Detection at 1840 FPS with TorchScript, TensorRT a... by janimo on Monday October 19, 2020 @06:18AM (#24824910)

Thanks for the links. I think there also isn't an API for accessing high FPS cameras on Android devices that support slow motion video capture.

[ Parent | on HN ]

Re:Object Detection at 1840 FPS with TorchScript, TensorRT a... by motoboi on Sunday October 18, 2020 @10:49AM (#24818223)

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

[ Parent | on HN ]

Re:Object Detection at 1840 FPS with TorchScript, TensorRT a... by briggers on Sunday October 18, 2020 @09:11AM (#24817624)

Mobile phones definitely since these days most of them have pretty powerful GPUs.

[ Parent | on HN ]