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

图片Normalize可省略提升性能 #38

Open
linxiaochunsd opened this issue Oct 28, 2021 · 1 comment
Open

图片Normalize可省略提升性能 #38

linxiaochunsd opened this issue Oct 28, 2021 · 1 comment

Comments

@linxiaochunsd
Copy link

在推理阶段, 图片预处理Normalize占用了大量CPU资源, tensorrt跑推理速度只有使用timing_inference_latency预计的0.5倍.
在网络内有BN的情况下, 可以省略预处理的Normalize. 即在训练时和推理时同时去掉Normalize. 肉眼看性能明显提升, 准召差别不大

@YonghaoHe
Copy link
Owner

@linxiaochunsd 如果是部署的话,可以把normalize写到onnx里面去,这样就可以让GPU来做这个操作。

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