Hi,
I'm converting pytorch script to dlc by command snpe-pytorch-to-dlc.
The model has been converted successfully. But it shows this INFO: "Using injective.cpu for reshape based on highest priority (10)".
What does this info mean? Can the dlc be loaded & exectued with GPU runtime?
Thanks!
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.
Dear developer,
We don't understand about the question you mentioned.
What does this info mean? Can the dlc be loaded & exectued with GPU runtime?
What's runtime you hope to execute? And what's SNPE SDK version you test?
BR.
Wei
Dear weihuan,
The INFO: "Using injective.cpu for reshape based on highest priority (10)" is showed when I run 'snpe-pytorch-to-dlc' command.
It likes a warning, after all my Pt model has been convert to dlc successfully.
But on snapdrgon 8Gne1/2, cpu runtime, my dlc is OK. On gpu runtime, my dlc execute longer than CPU, and output is incorrect.
What I really ask is whether the INFO will affect the model convert result.
Thanks for your reply.
BR