-
Notifications
You must be signed in to change notification settings - Fork 40
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
关于去掉预测框,仅用四个角点坐标来检测的问题? #11
Comments
我感觉你这个问题更加适合使用旋转的目标检测算法 |
其实我现在的数据格式是保留了原始的xywh还有置信度,然后自己新增了5个关键点的坐标,以及9个装甲板类别,4个颜色,最后output应该是5+10+9+4=28 |
为什么呢,我只是检测装甲板啊 |
给个数据示例看看 |
x y w h obj 5点 类别9 颜色4 |
大佬,不然加个微信交流,我把我之前录制的检测视频给你发一下,github上太大传不了 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
大佬你好,就是我是一名大二学生,然后是在中北大学的robomaster战队里负责用神经网络识别装甲板实现自动瞄准,不过就是之前我用yolo系列训练出来的模型最后实际测试时得到的bbox和装甲板的轮廓并不能很好的拟合,导致后续使用pnp进行姿态解算时会有较大误差,所以我想将传统yolo的数据集格式改为用四个角点的归一化坐标,然后我看到了您这个项目,不过我看您的数据集格式里还是包含了传统yolo的归一化后的中心点坐标和w,h,就是我想把这部分去掉去训练的话,是需要改动dataloader以及loss这些吗,希望大佬能解惑
The text was updated successfully, but these errors were encountered: