Coder Social home page Coder Social logo

onnx deployment fail about armnn HOT 7 CLOSED

tianyashu2020 avatar tianyashu2020 commented on August 21, 2024
onnx deployment fail

from armnn.

Comments (7)

tianyashu2020 avatar tianyashu2020 commented on August 21, 2024

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)

from armnn.

catcor01 avatar catcor01 commented on August 21, 2024

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.

from armnn.

tianyashu2020 avatar tianyashu2020 commented on August 21, 2024

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

image
image

from armnn.

catcor01 avatar catcor01 commented on August 21, 2024

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.

from armnn.

catcor01 avatar catcor01 commented on August 21, 2024

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.

from armnn.

catcor01 avatar catcor01 commented on August 21, 2024

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.

from armnn.

tianyashu2020 avatar tianyashu2020 commented on August 21, 2024

@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

from armnn.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.