question on why 4 fragments in parallel runs slower than 4 fragments in series

[guochengqian]

Dear @nmaac ,

May I ask a question w.r.t ShuffleNet v2?
Why 4 fragments in parallel run slower than 4 fragments in series?
The 4 fragments in parallel does not compute in parallel fashion? Is that due to implementation issue? Does that mean inception module actually does now increase speed but decrease it?

Thank you!

[nmaac]

Hi @guochengqian ,
We use Table 4 to show that more-fragmented structures (both in parallel and in series) run slower than less-fragmented structures.
The speed differences between structures in parallel and in series, which is beyond the focus of that paper, are negligible comparing with the differences among 1/2/4-fragmented structures.

[guochengqian]

Okay. Thank you.