Does the project use TensorRt for quantization when it is deployed to jetson?
yin-qiyu opened this issue · 2 comments
yin-qiyu commented
Hi, have you used TensorRT acceleration when deploying projects with jetson at frame rates over 27FPS?
vision4robotics commented
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.
laisimiao commented
So 27FPS in paper is gained by just pytorch format model and running in AGX GPU?