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

thundernet 部署 #32

Open
Guzaiwang opened this issue Mar 11, 2020 · 7 comments
Open

thundernet 部署 #32

Guzaiwang opened this issue Mar 11, 2020 · 7 comments

Comments

@Guzaiwang
Copy link

你好,请问你有试过,将thundernet部署到x86平台嘛? 有试过将thundernet转onnx之后的模型部署嘛

@1343464520
Copy link

请问你部署成功了吗?

@JimKimHome
Copy link

thundernet转onnx后转mnn行不通,因为不支持slice操作,想知道论文中作者是怎么部署的,有谁知道么?

@buaaxiejun
Copy link

thundernet转onnx后转mnn行不通,因为不支持slice操作,想知道论文中作者是怎么部署的,有谁知道么?

你好,解决了么?

@JimKimHome
Copy link

没解决,我改用shufflenet-ssd来做轻量级检测了......

@buaaxiejun
Copy link

没解决,我改用shufflenet-ssd来做轻量级检测了......

多大?效果如何?

@JimKimHome
Copy link

没解决,我改用shufflenet-ssd来做轻量级检测了......

多大?效果如何?

模型转成mnn之后是3.67M,推断速度在OPENGL加速的情况下才可以满足我的要求,大概是10ms,效果要看不同的检测任务了,我是只做车辆检测,效果还不错,map是0.5左右,但是还要继续优化才行,因为想要尽量避免漏检

@buaaxiejun
Copy link

没解决,我改用shufflenet-ssd来做轻量级检测了......

多大?效果如何?

模型转成mnn之后是3.67M,推断速度在OPENGL加速的情况下才可以满足我的要求,大概是10ms,效果要看不同的检测任务了,我是只做车辆检测,效果还不错,map是0.5左右,但是还要继续优化才行,因为想要尽量避免漏检

您好,这个模型有开源么?

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