Could not find any implementation for node

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

Description

I get the following error when trying to run trtexec with my onnx model.

[E] Error[10]: [optimizer.cpp::computeCosts::3728] Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[/ReduceMax.../ScatterND_6]}.)

This error only occurs on this version of TRT, but unfortunately due to client constraints I cannot upgrade my jetpack version.

Environment

TensorRT Version: 8.5.2.2+cuda11.8.0.065+520.61.05+cublas11.11.3.6
GPU Type: RTX2080TI and jetson orin (jetpack 5.1)
Nvidia Driver Version: 555.42.06
CUDA Version: cuda11.8
CUDNN Version: 8.7.0.84
Operating System + Version: jetpack / ubuntu 22.04
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag): nvcr.io/nvidia/tensorrt:23.01-py3

Relevant Files

Here is a log file with the --verbose flag trtexec_r.log - Google Drive

Steps To Reproduce

trtexec --onnx=./data/od/odox-xs-ha7-n3hw.onnx --shapes=input:1x3x512x960

2

Hi @mattangus02 ,
Can you please try with the updated TRT,
If the issue persist, please share the model and repro scripts with us

Thanks

3

As Matt explained, we are not able to upgrade TensorRT as this model is destined for a device which has already been through substantial compliance testing on Jetpack 5.1 and they are not able to update to Jetpack 6.1 (which is the only version which provides TensorRT 10). We can confirm that the model does execute currently with TensorRT 10, however. Can you please advise on how we might make this model work with Jetpack 5.1 (i.e. Tensor RT 8)

4

@AakankshaS I have shared the model with you in a private message.

Thanks!

Richard

5

@AakankshaS Could you provide an update please? We have a client waiting for our release.

Thanks,

Richad.