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

关于识别效率 #21

Open
liujinjiao opened this issue Jul 26, 2024 · 9 comments
Open

关于识别效率 #21

liujinjiao opened this issue Jul 26, 2024 · 9 comments

Comments

@liujinjiao
Copy link

想知道什么性能才能达到1s左右的识别速度,在i510400,24g内存识别效率在3s左右,在我的2核2g的服务器上在5s左右,很感谢作者,比paddle效率高很多

@jingsongliujing
Copy link
Owner

性能取决于服务器配置和图片大小等因素,后续可能会出c++版本的,效率可能会更高

@jingsongliujing
Copy link
Owner

感谢您的认可和支持,您的反馈和支持是我维护下去最大的动力

@liujinjiao
Copy link
Author

感谢,我修改了一下图片大小和预加载已经很不错了

@nissansz
Copy link

nissansz commented Sep 1, 2024

感谢,我修改了一下图片大小和预加载已经很不错了

哪种预加载最快?大小按什么标准设置比较好?

@liujinjiao
Copy link
Author

我是用的django在启动时预加载好模型,图片看复杂度,反正越小识别越快,当然也更差,自己调节吧

@nissansz
Copy link

nissansz commented Sep 9, 2024 via email

@liujinjiao
Copy link
Author

这个没尝试过,可以自己修改试一下

@jingsongliujing
Copy link
Owner

自己训练v2模型的准确率也能达到v4效果? 哪个训练配置文件准确率最好,最快?

------------------ 原始邮件 ------------------ 发件人: liu_sir @.> 发送时间: 2024-09-09 09:18:33 收件人:jingsongliujing/OnnxOCR @.> 抄送:nissanjp @.>,Comment @.> 主题: Re: [jingsongliujing/OnnxOCR] 关于识别效率 (Issue #21) 我是用的django在启动时预加载好模型,图片看复杂度,反正越小识别越快,当然也更差,自己调节吧 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>
理论上可以,但是v2的rcnn架构肯定没有v4的svtr效果好

@jingsongliujing
Copy link
Owner

建议用v4

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

3 participants