Onnx to tensorrt inference fail

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

Description

The engine I generated on the gtx1080ti graphics card, the reasoning was normal, but I switched to the engine generated on the rtx3060, and the reasoning results were wrong.

Environment

TensorRT Version: 8.0.1.6
GPU Type: rtx3060
Nvidia Driver Version: 471.68
CUDA Version: 11.3
CUDNN Version: 8.2.1
Operating System + Version: windows10
Python Version (if applicable): no
TensorFlow Version (if applicable): no
PyTorch Version (if applicable): 1.4
Baremetal or Container (if container which image + tag):

Relevant Files

sorry，onnx file is too large to upload successfully

Steps To Reproduce

gtx1080ti configs: cuda10.2，cudnn8.1 , tensorrt 8.0.1.6 ,it works.

cmd:
trtexec.exe --explicitBatch --onnx=test.onnx --saveEngine=test.eng --verbose=true

Hope to give some suggestions

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!