Missing TensorRT library

I’m working on implementing a TensorRT project. The cmake file contains:

find_library(NVONNXPARSERRUNTIME NAMES nvonnxparser_runtime)

I can find all the other libraries in the file (eg nvonnxparser, nvinfer). I can’t find how to fix this one, any help would be appreciated.

Thanks!

Hi,

Could you please let me know the TRT version you are using in this case?
I think all the required package should be part of the TRT_RELEASE itself.

Otherwise, those files can be found in the ONNX parser repo for branches v5.0, 5.1 and 6.0: https://github.com/onnx/onnx-tensorrt/tree/5.1

Thanks

So for this one I was using TensorRT 7
Was resolved when I switched to 5, but this also required CUDA 10.1

Thanks

I have the same problem here - Any idea how to fix it with trt7 on a Jetson NX? ie without downgrading trt + cuda?

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:

  1. 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!