Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

速度比mxnet慢许多 #457

Closed
anguoyang opened this issue Jun 28, 2018 · 9 comments
Closed

速度比mxnet慢许多 #457

anguoyang opened this issue Jun 28, 2018 · 9 comments

Comments

@anguoyang
Copy link

您好,我把mxnet的模型转换到ncnn以后,识别的结果是一致的。但速度比mxnet反而满了许多。
我试过mtcnn(caffe)转成ncnn以后做人脸检测,速度很快,效果也不错,但识别(mxnet)转成ncnn以后,识别速度比mxnet慢很多。

@anguoyang
Copy link
Author

请问可能是什么原因?

@nihui
Copy link
Member

nihui commented Jun 28, 2018

ncnn对手机平台做了优化,对pc没有优化,pc上速度慢

@anguoyang
Copy link
Author

多谢

@sunjunlishi
Copy link

@anguoyang 你是怎么调用的,我调用转换后的模型,结果一直一样

@anguoyang
Copy link
Author

@sunjunlishi 好久了,记不太清楚怎么调用的。结果是一模一样的,速度不一样而已。

@sunjunlishi
Copy link

那个年龄性别的最新版本已经可以了

@anguoyang
Copy link
Author

@sunjunlishi 哪个模型?

@sunjunlishi
Copy link

@zhanglaplace
Copy link

@sunjunlishi 请教下这个ncnn得模型转化后的提取的输出节点是什么

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants