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

Integrate MobileSAM into the pipeline for lightweight and faster inference #3346

Closed
2 tasks done
qiaoyu1002 opened this issue Jun 30, 2023 · 3 comments
Closed
2 tasks done
Assignees

Comments

@qiaoyu1002
Copy link

问题确认 Search before asking

需求描述 Feature Description

  1. 任务目标(请描述你正在做的项目是什么,如模型、论文、项目是什么?); 2. 需求场景(请描述你的项目中为什么需要用此功能); 3. 功能描述(请简单描述或设计这个功能)

  2. 我们完成了faster segment anything 模型的优化,目前github的项目star已经有1.5K星 Reference: https://github.com/ChaoningZhang/MobileSAM

  3. 需求场景:我们的项目与原始 SAM 的性能相当,并且除了图像编码上的更改之外,与原始 SAM 保持完全相同的管道,因此,很容易集成到任何项目中。MobileSAM 比原始 SAM 小约 60 倍,快约 50 倍,比并发 FastSAM 小约 7 倍,快约 5 倍。 整个pipeline的对比总结如下:

image

image

是否愿意提交PR Are you willing to submit a PR?

  • Yes I'd like to help by submitting a PR!
@Asthestarsfalll
Copy link
Contributor

你好,我尝试完成了一个PR,推理结果稍后上传

@shiyutang
Copy link
Collaborator

以上回答已经充分解答了问题,如果有新的问题欢迎随时提交issue,或者在此条issue下继续回复~ 我们开启了飞桨套件的ISSUE攻关活动,欢迎感兴趣的开发者参加:PaddlePaddle/PaddleOCR#10223

上述PR暂时未通过,需要等PR通过后这条issue才解决@ToddBear

@shiyutang
Copy link
Collaborator

该PR目前已经已经验证通过,即将被合入,因此关闭此条Issue~

以上回答已经充分解答了问题,如果有新的问题欢迎随时提交issue,或者在此条issue下继续回复~ 我们开启了飞桨套件的ISSUE攻关活动,欢迎感兴趣的开发者参加:PaddlePaddle/PaddleOCR#10223

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