I tried to build trtexec in .../TensorRT/samples. I followed this git link for building the sample but it didn’t work. It looks like it’s not a valid command with the message : bash: trtexec: command not found
Environment
TensorRT Version: 7.1.0: GPU Type: Xavier: Nvidia Driver Version: N/A: CUDA Version: 10.2: CUDNN Version: n/a: Operating System + Version: Ubuntu 18.04: Python Version (if applicable): TensorFlow Version (if applicable): PyTorch Version (if applicable): Baremetal or Container (if container which image + tag):
I think the building steps are similar and and intuitive with make commad. But I am not sure why I got the error after make the trtexec and I cannot use the trtexec command.
Hi,
I have the exact same problem that the command is not recognized. I am also using a xavier and i also tried it on tx2. The build using make in /usr/src/tensorrt/samples/trtexec/ looks to be succesful and I can see the files in /usr/src/tensorrt/bin but when I try to use trtexec command i get : -bash: trtexec: command not found
I have read somewhere that maybe I should add it to the path but I do not know how that works. Any idea how I can solve this ?
Thank you in advance
Hi,
Request you to share the ONNX model and the script if not shared already so that we can assist you better.
Alongside you can try few things:
validating your model with the below snippet
check_model.py
import sys
import onnx
filename = yourONNXmodel
model = onnx.load(filename)
onnx.checker.check_model(model).
2) Try running your model with trtexec command. https://github.com/NVIDIA/TensorRT/tree/master/samples/opensource/trtexec
In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!
I actually solved by problem by simply copying the trtexec from “/usr/src/tensorrt/bin/trtexec/” to “/usr/local/bin/” I think there might have been a problem with linking the file.