I noticed snpe-throughput-net-run has no parameter like --set_output_tensors, does it generate all outputs nodes? I have this confusion because I find that this parameter in snpe-net-run can cause a huge gap in inference time. I want to know if the inference time of snpe-throughput-net-run is equivalent to snpe-net-run without --set_output_tensors.
I also want to ask where can I find the log output when set --debug about snpe-throughput-net-run? I set the --storage_dir but i only noticed a small .pb file, and i don't know how to read it.
How to solve the problems? Thanks for the help!!
Dear customer,
The core scheme for snpe-throughput-net-run is same as snpe-net-run, but has bits of logs output. You can't generat the output logs even you add option of --debug. Please move to snpe-net-run if you hopes to know more debugging info.
Regarding the mode accuracy issue, you also can try the tool of snpe-net-run and debug your issue model.
BR.
Wei