While converting ONNX model to TRT with enabling DLA 0 and allow GPU fallback to true, is there any way to identify that how many layers are running on DLA and how many on GPU ?
For model conversion and inference, I am using Nvidia Jetson AGX Orin.
Hi @ashimabisla03 ,
I believe Jetson forum should be the correct platform to raise this query.
Thanks.
I can move this over for you.
Duplicated with Layers Inspection on TRT model - Jetson & Embedded Systems / Jetson AGX Orin - NVIDIA Developer Forums
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.