We use jetson xavier as out ADAS controller. We noticed that the GPU load is almost always at 100% high when AI module is activated. What potential problems this may cause? Any advice is appreactated.
Do you use TensorRT for inference?
If yes, it is normal. Since TensorRT tends to use all the available GPU resources to achieve the best performance.
You can control this by adjusting the frequency of feeding input to TensorRT.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.