Using tensorrt .plan engine for object detection

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

hello i just finished converting my tensorflow model from .pb file to .onnx and then to .plan how do i use this .plan engine to use in object detection, im using the nvidia jetson nano. thankyou

2

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!

5

Hi,
Sorry for the late reply

here is my model

eyemodel.onnx (8.3 MB)
eyemodel.plan (8.8 MB)

im using this guide for the convertion https://developer.nvidia.com/blog/speeding-up-deep-learning-inference-using-tensorflow-onnx-and-tensorrt/
i got stuck after the convertion started to got confused on the Running inference from the TensorRT engine part

im about to try and check the model with your code.
the github link to run the trtexec is not found

thanks again

6

Hi i am also facing the same issue i can able to do the conversion untill .plans or .engine file after that i need to use the .engine file for inference for object detection pls share me code for inferencing that .engine or plans to get the object detection
i am struggling hard to get the code or resource

7

Hi,

Please refer to the following Developer guide to run inference.

Also, you can refer to samples here for examples on how to run inference.

Thank you.