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

替换自己模型,识别有误差 #102

Open
meikorol opened this issue Oct 23, 2022 · 5 comments
Open

替换自己模型,识别有误差 #102

meikorol opened this issue Oct 23, 2022 · 5 comments

Comments

@meikorol
Copy link

电脑上用yolov5s-6.1版本训练识别结果是正确的,转ncnn并替换,在app上的识别却有误

@cmdbug
Copy link
Owner

cmdbug commented Oct 23, 2022

使用 yolov5customlayer 的代码,并修改 .h 里面的输出名称

@meikorol
Copy link
Author

感谢!已经成果部署,但为什么选择视频识别,输出来的视频好卡,FPS只有2帧,然后还显示FPS is not accurate

@cmdbug
Copy link
Owner

cmdbug commented Oct 24, 2022

视频本来就是测试用的,读取视频本身就慢,想读取快的话需要改读取方式,然后视频本身尺寸是不很大。

@meikorol
Copy link
Author

好的了解了,请问下设置nms和threshold为什么是分开设置呢,不都是作为阈值吗

@cmdbug
Copy link
Owner

cmdbug commented Oct 26, 2022

threshold是网络输出的阈值,过低的直接去掉。nms的是多个框重合度过大,按照一定规则去掉重合度多的框,留下一小部分,具体查资料去。

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