chunseoklee

> Is there any reason to support cpu backend as well? For now, not yet. IMHO, you can go assuming that "trix backend only" at the first step.

@ragmani Q. `has_parallel_batches` of [1,0,0,0 ] means that 4 is batch dimention in input shape [4,224,224,3] ?

Little thought about `Q. how to determine multi-batch input w.r.t. nnfw api ?` and https://github.com/Samsung/ONE/pull/9583. I'd like to recognize user's intention for batch execution w/o additional feature like https://github.com/Samsung/ONE/pull/9583. Thus,...

> @chunseoklee , @hseok-oh , new schema has now SignatureDef field in the format (currently not migrated from tflite but will work on this soon). Do you think we need...

> OK. I think it would be better to take some time and understand SignatureDef. I agree. I will take a look at sugnaturedef from TFL's viewpoint. At a glance,...

FYI: with https://github.com/chunseoklee/ONE-1/tree/pr8805 (commit: 64980cb3b), gbs build done anyway.

>Will we change build option to use c++17 ? 1. tizen's toolchain is gcc-9 2. But, tizen have not suggest to use c++17 officially(AFIAK. let me know if wrong). I...

Via offline discussion with tizen's toolchain guy, in his personal opinion, there will be no problem with c++17. But it is not official comment :)

Let's discuss this later when at least TIZEN officially suggests to use c++17 feature.

update - line coverage 80% -> TEM 4.0 (line cov 80%, func cov 80%, pass ratw 100%) - sam score 4.0 -> sam 4.0 ( + DC 4.0 )