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

输入大小 #50

Open
junze6 opened this issue Apr 10, 2022 · 6 comments
Open

输入大小 #50

junze6 opened this issue Apr 10, 2022 · 6 comments

Comments

@junze6
Copy link

junze6 commented Apr 10, 2022

输入大小只能是224x320吗,如果输入是224x224该怎么改main.c文件

@zhen8838
Copy link
Owner

输入大小是和模型相关的,首先修改模型,然后再把main.c里面的10改成7.

@junze6
Copy link
Author

junze6 commented Apr 11, 2022

我尝试使用pytorch框架下yolov3-tiny训练剪枝完转成kmodel,输入224x224,结果检测不出来东西,10改7,20改14,还有一些其他参数改了都没用,会是模型的问题吗

@zhen8838
Copy link
Owner

不用剪枝, k210不支持稀疏加速, 这个可能是量化误差问题,但是不至于一点也检测不出来. 你可以参考我写的yolox的例子 , 先检查ncc infer的结果和原始模型推理结果是否一致. 例子里面有个cpu文件夹, 可以方便来做pc端的验证.

@junze6
Copy link
Author

junze6 commented Apr 16, 2022

非常感谢您的回答,代码里只有单独的precision,recall指标,请问我想计算map应该怎么做。

@zhen8838
Copy link
Owner

zhen8838 commented Apr 16, 2022 via email

@junze6
Copy link
Author

junze6 commented Apr 22, 2022

好的,感谢您的回复,我利用pycocotools,现在已经可以计算每个epoch的map了

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