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.

Sign up for GitHub

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

Jump to bottom

weights_path #1

Open
ruoyuryc opened this issue Feb 21, 2020 · 5 comments
Open

weights_path #1

ruoyuryc opened this issue Feb 21, 2020 · 5 comments

Comments

@ruoyuryc
Copy link

Could you share the pretrained weight of this model?
Thanks
@VectXmy
Copy link
Owner

VectXmy commented Feb 21, 2020

Maybe you should go to the official repository to get pre-trained weights. I haven't trained on widerface yet.

@ruoyuryc
Copy link
Author

所以你是從頭用VOC dataset訓練嗎？
想請問你是改了哪裡使LFFD可以做multi-class detection？
謝謝!

@VectXmy
Copy link
Owner

VectXmy commented Feb 22, 2020

是从头训练，类别只与最后输出的通道数有关，其他细节自行看代码，除了backbone，其余都是按照我自己理解实现，没有参照官方mxnet的代码，你可以把它当成anchorfree版的SSD

@ruoyuryc
Copy link
Author

這樣效果如何？速度或準確性怎麼樣？

@VectXmy
Copy link
Owner

VectXmy commented Feb 23, 2020

网络很小速度当然还好，我没在wider face上训练没法评价是否有原文的效果，个人觉得一般，毕竟wider face的数据量很大

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@VectXmy @ruoyuryc