Padding layer error Error Code 2: Internal Error (Assertion rank == 0 || rank == 1 failed. )

[jackgao0323]

Description

I’m using the trtexec to parsing the onnx model and got the error as title. What’s the ‘rank’ mean and how could I fixed this error?

The trtexec command I used is:

trtexec.exe --onnx=C:\Users\jackg\Downloads\project\model\Depth\test_modified.onnx --saveEngine=C:\Users\jackg\Downloads\project\model\Depth\engine\test_fp16.trt --minShapes=‘input’:1x6x480x640 --optShapes=‘input’:1x6x480x640 --maxShapes=‘input’:1x6x480x640 --verbose --shapes=‘input’:1x6x480x640 --fp16

Here is the error image.

Environment

TensorRT Version: 8.4.1.5
NVIDIA GPU: 3080
NVIDIA Driver Version: 516.40
CUDA Version: 11.1
CUDNN Version: 8
Operating System: windows 10
Python Version (if applicable):
Tensorflow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if so, version):

Relevant Files

Here is the onnx model. I convert it from tensorflow by using tf2onnx.
test_modified.zip (5.8 MB)

Steps To Reproduce

[NVES]

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 Deep Learning TensorRT Documentation

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.

TensorRT/samples/trtexec at master · NVIDIA/TensorRT

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

[jackgao0323]

Hi @NVES,
I’ve “already” share the ONNX model and trtexec command. Have you seen my post clearly?

[spolisetty]

Hi,

Looks like you already created a Git issue, please refer to the response in the git issue.

Padding layer error Error Code 2: Internal Error (Assertion rank == 0 || rank == 1 failed. )

Thank you.