Maybe scales are rarely a power of two (I assume you mean values such as 0100b, 0.0010b). They are basically with long fractionals.
Tianqi Chen <notificati...@github.com>于2019年7月7日 周日上午11:08写道： > OK, given that most of the qnn ops are already in integer domain, we might > be just fine. Minimization of requantize is still useful. And in the case > when the scale is a power of two, use shift and normalize might be better > than float scale and round > > — > You are receiving this because you were mentioned. > Reply to this email directly, view it on GitHub > <https://github.com/dmlc/tvm/issues/2351?email_source=notifications&email_token=ABFVHDKDLR7B7VSQ7PAIRCLP6FMYHA5CNFSM4GMOMOS2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODZLDX7Q#issuecomment-508967934>, > or mute the thread > <https://github.com/notifications/unsubscribe-auth/ABFVHDKEMYZ7HLOFF6FB7G3P6FMYHANCNFSM4GMOMOSQ> > . > -- Best Regards Zhenhua -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2351#issuecomment-508968352
