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

单样本推理时长统计 #11

Open
gavinking87 opened this issue Feb 18, 2021 · 3 comments
Open

单样本推理时长统计 #11

gavinking87 opened this issue Feb 18, 2021 · 3 comments

Comments

@gavinking87
Copy link

image
你好，我统计bert以及不同speed下，准确率、cpu推理和Gpu推理的耗时。现在有一点疑惑，只有当speed为0.8时，总耗时才能小于原来的bert耗时。 请问下我是哪里出错了吗。
统计bert耗时是执行script_eval.sh脚本。参数配置如下：
image
@gavinking87
Copy link
Author

是fastbert 每一层多出来的子分类器的操作导致耗时过长吗？但是原论文中 这一部分的flops相比较transformer 少很多，应该是不会太耗时间的。请楼主百忙中抽看下，谢谢！

@BitVoyage
Copy link
Owner

请问bert是在什么代码下测试的

@gavinking87
Copy link
Author

run_scripts/script_eval.sh

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
@BitVoyage @gavinking87