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

ncnn多线程下工作性能下降 #13

Open
dengly opened this issue Jan 28, 2019 · 2 comments
Open

ncnn多线程下工作性能下降 #13

dengly opened this issue Jan 28, 2019 · 2 comments

Comments

@dengly
Copy link

dengly commented Jan 28, 2019 •
edited
Loading

经测试发现，ncnn 通过设置 set_num_threads 设置多个线程时，设置到8个线程性能还不如2个线程的性能。而且在java层面上，创建多个线程同时做人脸检测时，性能也不如单个线程做人脸检测。
@dengly dengly changed the title ncnn ncnn多线程下工作性能下降 Jan 28, 2019
@dengly
Copy link
Author

dengly commented Jan 29, 2019

修改jni 的代码后，发现在java层面上，多个线程同时做人脸检测有了提高，但是 ncnn 设置 set_num_threads 过多依然有问题。

@AnyLifeZLB
Copy link

修改jni 的代码后，发现在java层面上，多个线程同时做人脸检测有了提高，但是 ncnn 设置 set_num_threads 过多依然有问题。

一张照片要189 毫秒，100 张要18.9 秒？？！ 1:N 识别几乎不可行

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
@dengly @AnyLifeZLB