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!
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