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

为啥gpu和cpu测试的结果不一致？ #18

Open

luodahei opened this issue Jul 5, 2022 · 1 comment

luodahei commented Jul 5, 2022

No description provided.

Panda-Young commented Nov 19, 2024 •

edited

Loading

fp16 low-precision optimization is enabled by default on Android, and the output is consistent after it is disabled.
You can set it as follows:

ncnn::Net net;
net.opt.use_fp16_packed = false;
net.opt.use_fp16_storage = false;
net.opt.use_fp16_arithmetic = false;

https://github.com/Tencent/ncnn/wiki/FAQ-ncnn-produce-wrong-result

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment