Open chuck0518 opened 3 years ago
hey,man,thanks for the work,it's cool. When i convert the model to 8bit by ncnn tool,the accuracy has dropped a lot,can you give me some suggetions?
int8 ncnn is not well optimized,int8 does not bring inference speed advantages
got it,thank you
hey,man,thanks for the work,it's cool. When i convert the model to 8bit by ncnn tool,the accuracy has dropped a lot,can you give me some suggetions?