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

老哥测试过C++版本和python版本trt耗时差距么? #1

Open
sjr512 opened this issue Aug 30, 2021 · 4 comments
Open

老哥测试过C++版本和python版本trt耗时差距么? #1

sjr512 opened this issue Aug 30, 2021 · 4 comments

Comments

@sjr512
Copy link

sjr512 commented Aug 30, 2021

我现在用的是DB+CRNN的流程做OCR 全是python版本的
python版本crnn trt的模型我试着测了一下耗时 发现还比ONNX慢 不清楚是不是C++和python的关系
python版本db trt我测试比onnx快了大概3倍 但是还是得200多ms(之前做过yolo检测 转trt大概20ms C++版本)
有点疑惑是python和C++会差那么多么(我也都是动态输入)

另外老哥能否提供一下你训好的模型 我想测试看看
另外我QQ 303502399 老哥愿意交流欢迎加我呀:)

@liwer0715
Copy link
Owner

liwer0715 commented Aug 30, 2021 via email

@sjr512
Copy link
Author

sjr512 commented Aug 30, 2021

GPU肯定是起来了的 我测试10次 取后9次平均时间的 是纯推理时间 模型如果DB和CRNN都有就更好 不行的话就CRNN的吧 谢谢老哥

@liwer0715
Copy link
Owner

CRNN我没有,都是实际项目的模型,你可以自己训练,只测速度就不需要模型收敛,随便训练个模型就行,这是我的训练代码https://github.com/LW-CVer/crnn_pytorch

@sjr512
Copy link
Author

sjr512 commented Aug 30, 2021

好的 多谢

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