Create Ses image out of engine output

Description

i am getting a tensor in the size of 51264018 for 18 classes. I am trying to get the info into a picture base of a color map.

Environment : linux

TensorRT Version : 8.2.3:
GPU Type : A6000:
Nvidia Driver Version : 460:
CUDA Version: 11.2:
**CUDNN Version : 9.1.85 **:
ubuntu 18.04:
Python 3.6:

Relevant Files

uploads:

  • onnx model
  • onnx2tensorrt
    -test.trt (trt file i have been using)
    -show trt image
  • 2 images of the source and after Ses by the model
    NVIDIA - Google Drive

Steps To Reproduce

  1. run show trt image and change params location as needed

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.

In case you are still facing issue, request you to share the trtexec “”–verbose"" log for further debugging
Thanks!