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

EAIDK-610-G01板子运行yolov5l出现Segmenttation fault (core dumped) #675

Open
CPFelix opened this issue May 18, 2021 · 3 comments
Open

Comments

@CPFelix
Copy link

CPFelix commented May 18, 2021

下载Yolov5(v5.0)的yolov5l预训练模型,并用emport.py导出为onnx,然后用在线转换工具转换为tmfile文件,但是在运行时候出现Segmenttation fault (core dumped)错误。
另外这个板子上是不是目前不支持yolov5s?

@kalcohol
Copy link
Collaborator

EAIDK 默认的版本是比较老的版本,可以考虑拉取最新的代码编译后跑跑 example 下的 yolov5s 的例程。

@CPFelix
Copy link
Author

CPFelix commented May 19, 2021

@kalcohol 忘记说了,我是下载的最新版Tengine在板子上重新编译的,然后目前定位到是yolov5s模型后处理定位第二层输出特征图(40*40)获取score时出现类似越界的问题:
float score = feat[a * feat_w * feat_h * 85 + h * feat_w * 85 + w * 85 + s + 5];

@StarStyleSky
Copy link
Collaborator

原始的yolov5s使用了slice来构建focas结构,tengine的example code在处理时,对模型进行了优化,使用cpu重构了foacs部分(优化的部分参考tool下的工具)。

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