Quadro RTX 4000 : Outputs always [0,0,1,0...0] no matter which image is given in input

Description

A clear and concise description of the bug or issue.

Environment

TensorRT Version: 8.4.1.5
GPU Type: Quadro RTX 4000
Nvidia Driver Version: 582.02
CUDA Version: 11.6
CUDNN Version: 8.4
Operating System + Version: Windows 10
Python Version (if applicable): 3.6
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered

Hello,

I am trying to port my CNN (densenet201), trained on tensorflow and converted in the ONNX format, on a new GPU after successfully using it on an old GPU (from the Quadro familly too).

However after converting the ONNX model to a .trt file with the following command : trtexec --onnx=model.onnx --saveEngine=densenet201.trt ; and loading into a code I developped following the Samples provided by NVIDIA, i always get the same output (9 output tensor) → [0,0,1,0,0,0,0,0,0].

Is there a specific version of TensorRT I have to download to make it work ?

You can find the code I use in the linked files.

Thank You.

LibTensorRT.cpp (10.5 KB)

Hi,

Could you please try the following.

  • Please verify that ONNX-Runtime produces correct results when compared to TensorRT output.
  • Please try on the latest TensorRT version 8.5.2 (also available as NGC container)

If you still face the issue, please share with us the ONNX model here or via DM.

Thank you.

Thank you for your answer,

I checked again and indeed I had issues in my preprocessing.

We can close this question.
Have a nice day