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

推理自己的rknn模型时npu占用率很低 #20

Open
Levin-x opened this issue Nov 20, 2023 · 1 comment
Open

推理自己的rknn模型时npu占用率很低 #20

Levin-x opened this issue Nov 20, 2023 · 1 comment

Comments

@Levin-x
Copy link

Levin-x commented Nov 20, 2023

大佬您好,我用您的代码推理我的模型,推理的时候查看npu的占用率仅有百分之一,尝试定频,却没有改进,这是什么问题呢?用官方模型yolov5-640-640.rknn的话帧率可以达到30帧,三个npu的占用率都是17%左右。

@leafqycc
Copy link
Owner

这是在转换模型过程中没有进行量化吗?30帧是使用官方模型yolov5s的连接相机的吗?转换的自己的模型是yolov5s?
可能的原因:
在量化过程中控制台的输出是float层居多吗?如果是这样代表模型没有得到较好的量化,大量的计算任务都由CPU运算

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