Does the project use TensorRt for quantization when it is deployed to jetson?

Question

yin-qiyu opened this issue 2 years ago · 2 comments

Hi, have you used TensorRT acceleration when deploying projects with jetson at frame rates over 27FPS?

Answer 1 · 2022-05-04T14:48:31.000Z

Thanks for your attention to our work. In this codebase, we don't use the TensorRT. In our future work, we will provide the TensorRT version.

Answer 2 · 2022-05-06T01:12:35.000Z

So 27FPS in paper is gained by just pytorch format model and running in AGX GPU?