Description ONNX file was generated from PyTorch Retinanet and then folded using polygraphy. Then when running /usr/src/tensorrt/bin/trtexec --onnx=folded.onnx --saveEngine=model.engine, this is the error: ... [07/11/2023-17:14:31] [I] [TRT] [GpuLayer] MYELIN: {ForeignNode[onnx::Equal_3245.../model…

It does work with trtexec tool. I was able to get if working with that inference code by modifying the model so its output was not dynamically shaped

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: Quick Start Guide — NVIDIA TensorRT validating your model with the below snippet check_model.py import sys impo…

Hi, We recommend that you please try the latest TensorRT version 8.6.1. Please share with us your complete verbose logs if you still face the issue. You can also try TensorRT | NVIDIA NGC container for easy setup. Thank you.

Is it possible to use TensorRT 8.6.1 on Jetson Xavier with Jetpack 5.1? I thought I saw some indications that this is not possible

Hi, [image] brad.steiner1: Is it possible to use TensorRT 8.6.1 on Jetson Xavier with Jetpack 5.1? I thought I saw some indications that this is not possible We are moving this post to the Jetson Xavier forum to get better help on the above query. Thank you.

Hi, TensorRT 8.6 is not available for Jetson yet. Let’s check if the error comes from ONNX or TensorRT first. Have you run the ONNX file with other frameworks like ONNXRuntime? If not, please do so. Thanks.

I removed NMS from the Pytorch model and that seems to have resolved this error. The engine is now fully building. However, I am getting a seg fault when trying to run the example inference code found here: https://github.com/NVIDIA/TensorRT/blob/main/quickstart/SemanticSegmentation/tutorial-runtime…

Hi, Could you try if the engine file can work with trtexec tool first? Below is another inference example for your reference: https://elinux.org/Jetson/L4T/TRT_Customized_Example#OpenCV_with_PLAN_model Thanks.

ONNX to TensoRT conversion failing with error: "each train expected to have at most one ShapeHostToDeviceNode"

Robotics & Edge Computing Jetson Systems Jetson Xavier NX

spolisetty July 13, 2023, 7:17pm 6

Hi,

We are moving this post to the Jetson Xavier forum to get better help on the above query.

Thank you.

Topic		Replies	Views
Convert onnx to trt error on jetson xavier nv TensorRT tensorrt	2	781	January 13, 2022
Resize error Jetson Xavier NX tensorrt , tensorflow	5	1356	September 12, 2021
Error when converting an ONNX model using trtexec on Jetson Orin Nano Developper kit TensorRT tensorrt , cuda , pytorch , cudnn , onnx , jetson	5	173	June 30, 2025
Trtexec Internal Error (Symbolic relation a.z >= 0 is always false. ) Jetson Xavier NX tensorrt	4	691	December 20, 2022
Error Code 2: Internal Error (ForeignNode does not support data-dependent shape for now.) TensorRT tensorrt , cuda , tensorflow	1	609	November 22, 2023
ONNX -> TRT Error Code 1 and 2: Cask (isConsistent) and Internal Error (Assertion enginePtr != nullptr failed.) Jetson AGX Xavier tensorrt	6	1510	July 26, 2022
TRT engine created on Tesla T4, Quadro P1000 but engine creation fails on Jetson AGX Xavier Jetson AGX Xavier tensorrt , cuda , jetson-inference , python	17	2945	October 18, 2021
IShuffleLayer applied to shape tensor must have 0 or 1 reshape dimensions: dimensions were [-1,2]) TensorRT	7	6604	May 30, 2022
Erorr with onnx to trt Jetson Xavier NX tensorrt	8	1352	March 30, 2022
Centernet model TensortRT file type conversion TensorRT tensorrt , tensorflow , onnx	1	839	November 2, 2022

ONNX to TensoRT conversion failing with error: "each train expected to have at most one ShapeHostToDeviceNode"

Related topics