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

关于Segment使用C++推理开启Mkldnn加速无法处理动态Shape的问题 #3861

Open
Hold-on-li opened this issue Dec 12, 2024 · 2 comments
Open

关于Segment使用C++推理开启Mkldnn加速无法处理动态Shape的问题 #3861

Hold-on-li opened this issue Dec 12, 2024 · 2 comments
Assignees
@zhang-prog

Comments

@Hold-on-li
Copy link

问题描述 Please describe your issue

您好，请问一下，我在用C++加载PaddleSeg训练的模型进行推理时，基于开启Mkldnn加速的条件下，输入图像的Shape变化较大时推理会出错，例如：第一次加载的Shape是10001000第二次是500500 这种情况有办法规避吗？求解
@Hold-on-li Hold-on-li changed the title 关于Segment使用C++推理开启Mkldnn加速无法无法处理动态Shape的问题 关于Segment使用C++推理开启Mkldnn加速无法处理动态Shape的问题 Dec 12, 2024
@zhang-prog
Copy link
Collaborator

麻烦贴一下用的什么模型，具体报错信息，还有你的代码吧。

@Hold-on-li
Copy link
Author

麻烦贴一下用的什么模型，具体报错信息，还有你的代码吧。
image
模型用的是这个配置文件训练的模型
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@zhang-prog zhang-prog

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@zhang-prog @Hold-on-li