Jang Jiseob

~Building onert on x86_64 now works.~ Most of the errors have already been resolved by #9265. ```bash $ cd {one dir} $ docker run -it --rm -v `pwd`:`pwd` -w `pwd`...

Same situation with arm and aarch64. Only `ruy` throws the error. I hope this error is solved by #9500. - arm ```bash $ sudo apt-get install qemu qemu-user-static binfmt-support debootstrap...

I summarized my thoughts on this work. If you have questions or discussions about it, please contact me or leave a comment. ## TODO - [ ] Add tests -...

> - How can the intention of users to change batch size be distinguished? By adding a specific api? By adding a parameter of nnfw_set_input_tensorinfo? `onert` also distinguishes which input...

> Q. has_parallel_batches of [1,0,0,0 ] means that 4 is batch dimension in input shape [4,224,224,3] ? Yes, `has_parallel_batches` of [1,0,0,0 ] means that 1st dimension is batch. This member...

Thinking about it again, just below is enough. ```c++ typedef struct nnfw_tensorinfo { /** The data type */ NNFW_TYPE dtype; /** The number of dimensions (rank) */ int32_t rank; /**...

I have a plan to change the member `_lowergraph` of `exec::ExecutorBase` to a reference or pointer for this task. I think it would be better to use `shared_ptr` to allow...

> IMO, lowered graph should create one executor because lowered graph includes compile result. Could you explain why we need this change? I have a plan to clone one batch...

> I don't know your big picture, but maybe you want to execute at once multiple executors. But I have concern `lowered graph` access and executors sharing `lowered graph` are...

> And delete LoweredGraph's copy constructor OK I will.