Forums - Customized onnx2dlc model batchsize

2 posts / 0 new
Last post
Customized onnx2dlc model batchsize
deepwork
Join Date: 9 Sep 21
Posts: 3
Posted: Tue, 2021-11-23 10:40

Hello qualcomm forum, currently  I am working on a project using qualcomm chip SA8155P to run my customized model.. 

I've successfully converted model to .dlc file and it is giving the right result. 

HOWEVER, I want to make it avaliable to run for batchsize bigger than 2 (eg. 2, 256, 256, 3).

I've tried some ways such as making ONNX model that gets (2, 256, 256, 3) as an input but, it didn't worked well.

 

 

So can anyone help me find solution? 

 

Thanks,

Joseph

  • Up0
  • Down0
weihuan
Join Date: 12 Apr 20
Posts: 270
Posted: Tue, 2021-11-23 17:53

Dear developer,

Thanks for your efforts in our products. Could you please help to give us more messages to narrow down this issue?

1. What's SNPE version you have used?

2. What's detail's issue you want to us resolve? You mentioned model don't work well. Is issue from SNPE conversion or implements with wrong results compared with golden data?

BR.

Wei

  • 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.