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

如何将模型导出onnx,部署至地平线J5 #81

Open
xiongda777 opened this issue Jul 26, 2024 · 8 comments
Open

如何将模型导出onnx,部署至地平线J5 #81

xiongda777 opened this issue Jul 26, 2024 · 8 comments

Comments

@xiongda777
Copy link

这部分您是否可以给出一些建议,我导出的onnx在地平线J5 hb_mapper checker 时一直没办法通过,这部分您有什么经验吗?

@linxuewu
Copy link
Collaborator

请问具体报什么错呢?

j5的部署问题,可以也去开发者论坛询问https://developer.horizon.ai/。

@reskipper
Copy link

模型DeformableAggregation是cuda算子的话应该不可以在地平线BPU上跑

@linxuewu
Copy link
Collaborator

linxuewu commented Aug 2, 2024

代码里面提供了torch版本的DeformableAggregation,编译的话把use_deformable_func关了就行了。是可以部署到j5上的。

@xiongda777
Copy link
Author

image
导出onnx时是否应该把temp_instance_feature,temp_anchor,time_interval作为输入,以便下一步的板端推理?

@xiongda777
Copy link
Author

您这边是否 有计划开源模型部署到J5等芯片的教程呢?或者将模型加入到OE开发包的model zoo中?

@24werewolf
Copy link

image 导出onnx时是否应该把temp_instance_feature,temp_anchor,time_interval作为输入,以便下一步的板端推理?
请问你那边转出来onnx 了吗?

@JYS997760473
Copy link

这部分您是否可以给出一些建议,我导出的onnx在地平线J5 hb_mapper checker 时一直没办法通过,这部分您有什么经验吗?

请问如何导出的onnx呢,我这边一直在报错

@ThomasVonWu
Copy link

@24werewolf
This repository may be useful for your deployment:https://github.com/ThomasVonWu/SparseEnd2End

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

6 participants