Forums - Multi-model operation

3 posts / 0 new
or Register
Last post
Multi-model operation
MarkWu
Join Date: 8 May 22
Posts: 37
Posted: Wed, 2023-02-22 22:14
Top

Hi,

I have four models, which are temporarily called model1, model2, model3, and model4.

Model1 uses gpu-runtime, and others use dsp-runtime.

It takes 10ms for model3 to excute alone, but they are run together and excute in the order of model1 ->model2 ->model3.

model3 will take 10s to excute. I want to ask why and how to solve this problem?

Model 3 cannot run on the gpu because the size of a layer is too large.

SNPE build failed error_code=206; error_message=Insert failed. Runtime already present; error_component=Dl System; line_no=55; thread_id=539762566400

What is the reason for this error

  • Up0
  • Down0
Re: Multi-model operation
weihuan
Join Date: 12 Apr 20
Posts: 270
Posted: Sat, 2023-02-25 21:21
Top

Dear developer,

What's SNPE verison you have used?

You can run those models sperately to check what's the detailed errors for all models.

BR.

Wei

  • Up0
  • Down0
Re: Multi-model operation
MarkWu
Join Date: 8 May 22
Posts: 37
Posted: Sun, 2023-02-26 17:20
Top

SNPE verison : snpe-2.5.0.4052

  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.