onnx deployment fail

[tianyashu2020]

I tried to use armnn to deploy my onnx model,but failed. Could anyone help me?

[tianyashu2020]

terminate called after throwing an instance of 'armnn::ParseException'
what(): Unsupported operation Transpose for node '/Transpose' at function LoadGraph [/home/shuqinjun/arm_nn/armnn/build-tool/scripts/source/armnn/src/armnnOnnxParser/OnnxParser.cpp:966]
Aborted (core dumped)

[catcor01]

Hello @tianyashu2020,

It seems you are using build-tool. Are you running the model through ExecuteNetwork? You might be able provide details how you are running the model including target backend, ArmNN SHA/branch and details about the Transpose operator that is failing in your model. Additionally, if the model is publicly available, please post a link to it here and I can attempt to reproduce it.

[tianyashu2020]

Hello @tianyashu2020,

It seems you are using build-tool. Are you running the model through ExecuteNetwork? You might be able provide details how you are running the model including target backend, ArmNN SHA/branch and details about the Transpose operator that is failing in your model. Additionally, if the model is publicly available, please post a link to it here and I can attempt to reproduce it.

hello，this is my code，I compiled the armnn so lib in my X64 platform,using ubuntu 22.04 operating system,
I just want to test my model in "armnn::Compute::CpuRef" mannaer.

the attached file is my onnx model.

tru_net_phase_32k_no_dereverb_sim.zip

[catcor01]

Hello,

Thank you for your reply. Unfortunately, I am restricted in downloading user supplied models and can only interact with models that are publicly available under an appropriate license. Would the model be available somewhere? Else, if you could supply me with the operator info such as datatype etc. I can find more into why it is not supported on our side.

[catcor01]

Hello @tianyashu2020,

I have investigated this issue more and discovered that Transpose support has not been added to the ONNX parser. I have brought this up with the team and the work to add this support is on our radar but has not been prioritized in the near future. I can make 2 suggestions to get things running on your side:

• Convert the onnx model to tflite and run through our tflite parser or delegate.
• If you want to try to add support for Tanspose to the ONNX parser we do welcome contributions. For more information on contributing to ArmNN please see the Contributing page on the MLPlatform.org website, or see the Contributor Guide.

Kind Regards,
Cathal.

[catcor01]

Hello again,

I just wanted to suggest you can use ONNX runtime with ACL as an option to accelerate your model also. See here: https://onnxruntime.ai/docs/execution-providers/community-maintained/ACL-ExecutionProvider.html.

Kind Regards,
Cathal.

[tianyashu2020]

@catcor01 problem fixed，the reason is the transpose with groups parameter in my model is not supported, I fixed the transpose operator，it worked
very thanks for you reply