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

【PaddlePaddle Hackathon】32、基于Paddle-Lite在ios gpu上跑通SSD_MobileNetV3_large模型 #7030

Closed
TCChenlong opened this issue Sep 23, 2021 · 0 comments

Comments

@TCChenlong
Copy link

(此 ISSUE 为 PaddlePaddle Hackathon 活动的任务 ISSUE,更多详见PaddlePaddle Hackathon

【任务说明】

  • 任务标题:基于Paddle-Lite在ios gpu上跑通SSD_MobileNetV3_large模型

  • 技术标签:Paddle-Lite,C++,IOS,CMake、Metal

  • 任务难度:中等

  • 详细描述:基于Paddle-Lite OP添加文档添加新OP gpu实现,如multiclas_nms,优化模型性能,在ios gpu上跑通模型, 保证精度对齐。

【提交内容】

  • 支持某一款苹果手机GPU上跑通该模型且精度对齐

  • 新增op实现代码

  • op单测代码

【技术要求】

  • 熟悉主流推理框架,有gpu或metal方向的性能优化经验

  • 通过提PR方式将相关代码合入Paddle-Lite

@TCChenlong TCChenlong changed the title 【PaddlePaddle Hackathon】32、基于Paddle-Lite在ios gpu上跑通[SSD_MobileNetV3_large](https://ecloud.baidu.com/?t=ad755a28feba85840796f2c7adc0f7b7)模型 【PaddlePaddle Hackathon】32、基于Paddle-Lite在ios gpu上跑通SSD_MobileNetV3_large模型 Sep 23, 2021
@PaddlePaddle PaddlePaddle deleted a comment from paddle-bot-old bot Sep 23, 2021
@qili93 qili93 closed this as completed Feb 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants