Could not parse ONNX model (2)

[JoleCRO]

Hello!

Could not parse ONNX model from file

Description Hello! When trying to convert ONNX file into TensorRT engine file on my Jetson Nano I get following error: ERROR: builtin_op_importers.cpp:3422 In function importResize: [8] Assertion failed: scales.is_weights() && "Resize scales must be an initializer!" |yolov5|error|[Builder] buildEngine() failure: could not parse ONNX model from file Detailed log of conversion is attached. As can be seen in log, initial Pytorch model was generated using Yolo5 and converted to ONNX through: ht…

Unfortunately this - not yet solved - post somehow went out of Your „radar“ but is of great importance for us.

In short:
When trying to convert ONNX file into TensorRT engine file on Jetson Nano an error occured and you suggested that I try with newest TRT ver. 8.6.1 but:

Q1) Does for this 8.6.1 still apply the rule that the engine must be built on same machine type where inference will be run (Nano in this case) ?

Q2) If above answer is yes: TRT 8.6.1 is incompatible with Nano AFAIK, how to run in there then, in Docker perhaps?

Q3) If above answer is yes: could You please suggest Docker image for TRT 8.6.1 ? And must Nano be the host or host is other machine and Nano L4T is the container?

Thanks!

Environment

TensorRT Version: 8.0.1
GPU Type: Jetson Nano devkit (Maxwell)
Nvidia Driver Version:
CUDA Version: 10.2.300
CUDNN Version: 8.2.1
Operating System + Version: Ubuntu 18.04 (Jetpack 4.6.0)
PyTorch Version (if applicable): 1.12.1

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