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

cpu 识别时间问题 #17

Open
Achhhe opened this issue Aug 5, 2018 · 4 comments
Open

cpu 识别时间问题 #17

Achhhe opened this issue Aug 5, 2018 · 4 comments

Comments

@Achhhe
Copy link

Achhhe commented Aug 5, 2018

您好,参考您的demo,训练好的模型经过slim后为4.1M,在电脑cpu测试实时视频,识别时间大约为37ms/帧,比论文中手机端测试速度还慢,我想请问,这个结果正常么?
提前谢谢了

@moli232777144
Copy link
Owner

PC端用的什么前置计算框架?ncnn在pc端没有加速优化,只能基础调试。论文的移动端速度是没问题的

@Achhhe
Copy link
Author

Achhhe commented Aug 6, 2018

抱歉啊,我是新手,请问前置计算框架是什么意思,我就是参考您的demo,用mxnet训练好的模型,然后参考test.py测试的实时视频640×480,没有用gpu,大约37ms,请问你有用cpu测试过么

@Achhhe
Copy link
Author

Achhhe commented Aug 6, 2018

抱歉,又打搅您了
您有尝试过论文中BN合并到conv层么,经过合并以后模型大小可以从4m降为0.99m么

@moli232777144
Copy link
Owner

您应该是理解有所偏差,4M是模型大小,论文里的0.99M是参数量,合并bn层模型大小缩小很少,那层参数不多。

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

2 participants