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

CPU Benchmarking #8

Open
srireddy821 opened this issue Dec 27, 2016 · 6 comments
Open

CPU Benchmarking #8

srireddy821 opened this issue Dec 27, 2016 · 6 comments

Comments

@srireddy821
Copy link

Hi DaFu,

Thanks a lot for sharing your code. Did you get a chance to benchmark your code on CPU?

Thanks,
Sri

@zhanglaplace
Copy link

你好,这个代码我在cpu下运行好像也出现问题了

@DaFuCoding
Copy link
Owner

@zhanglaplace 代码第14行,//#define CPU_ONLY 把注释取消再试一试。

@DaFuCoding
Copy link
Owner

DaFuCoding commented Jun 13, 2017

@srireddy821
GPU: GTX 1080 CPU:i7-4.2G Single core run this code.
minFaceSize = 24
threshold = [0.6, 0.7, 0.7]
Image Size :
960x540: avg cpu: 264ms avg gpu: 128ms
640x480: avg cpu: 109ms avg gpu: 49ms
320x240: avg cpu: 21ms avg gpu: 9ms
For reference only. Because this time contains multiple factors. Such as: face number, threshold and proposals' pnet.

@srireddy821
Copy link
Author

@DaFuCoding Thanks a lot for the response. Somehow I lost your reply.

@sunjunlishi
Copy link

sunjunlishi commented Jan 18, 2019

ClassifyFace_MulImage 感觉 GPU 执行 错误,难道 必须用你的 layer ?
ClassifyFace GPU 就没有问题。还是我的驱动的问题。有人遇到过 这样的 问题 ??

@sunjunlishi
Copy link

it is ok。我的代码有问题,已经解决。

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

4 participants