Forums - snpe-pytorch-to-dlc problem

2 posts / 0 new
or Register
Last post
snpe-pytorch-to-dlc problem
diwu
Join Date: 15 Nov 21
Posts: 15
Posted: Mon, 2022-03-28 02:20
Top

When I use the snpe-pytorch-to-dlc to converse the 'resnet100' , the following warning appears, and I try to set imagesize to(224, 224), there is no this problem. But my imagesize must be 1280*720 in application. It is what causes the problem?  What should I do to solve the problem?

 
 
"snpe-1.59.0.3230/lib/python/qti/aisw/converters/backend/ir_to_dlc.py:189: RuntimeWarning: info_code=802;
message=Layer parameter value is invalid in GPU.
Layer input : output width = 720, depth = 1280 width * depth (packed) = 230400 exceeds maximum image width 16384 for Adreno A650; component=GPU Runtime; line_no=981; thread_id=139824093290688
 
 
  • Up0
  • Down0
Re: snpe-pytorch-to-dlc problem
weihuan
Join Date: 12 Apr 20
Posts: 270
Posted: Thu, 2022-03-31 01:13
Top

Dear customer,

SNPE only support single dimension input tensor instead of muliple dimension at the end while SNPE compiled with offline mode.

If you want to run with 1280x720, the input dimension shall be set to 1280x720 rather than 224x224.

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.