search

google / gemmlowp

Low-precision matrix multiplication
Apache License 2.0
1.78k stars 451 forks source link

is D in your fomation (2) calculated by this? #204

Open mittkongg opened 3 years ago

mittkongg commented 3 years ago

max = scale (255 - zero_point); min = scale (0 - zero_point);

and this zero_point and scale both are real number , so is not calculated like what i do ?