How can I debugging Tensor RT?

Jetson Xavier
Jetpack 4.3. DP
Ubuntu 18.04
gpu_arch: 7.2
cuda: 10.0.326


I am using Tensor RT in C++.

When I execute a trt engine, segmentation fault in function ‘execute’.

Using system profiler, I can find that delay occurs in ‘shuffle layer’ but I don’t know what’s happened.

It shows only segmentation fault without any information.

Segmentation fault (core dumped)

How can I debug in tensorRT function?


For debugging the issue, you can set the ILogger to INFO mode and use supported profiling tools to help investigate bottlenecks.

You can also use “trtexec” command line tool for benchmarking & generating serialized engines from models.

If possible, could you please share the sample script and model along with reproduction setups?


1 Like