-
Notifications
You must be signed in to change notification settings - Fork 7.9k
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
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
【模型压缩推全计划】为六大套件新增模型压缩功能 #10657
Comments
队伍名:风清扬 |
队伍名:风清扬 |
队伍名:飞桨小队 |
队伍名:德布罗意波 |
队伍名:Dec20b |
队伍名:晓飞队 |
队伍名:Zheng-Bicheng |
队伍名:Zheng-Bicheng |
This issue was moved to a discussion.
You can continue the conversation there. Go to discussion →
背景
目前各套件的模型压缩能力参差不齐,而模型压缩作为部署之前的一步,可以在不损害或者少量损害模型精度的情况下,对模型的能耗,速度、大小都有显著的改善。因此为了对各套件的模型压缩进行推全,我们提出了基于PaddleSlim的ACT为各大套件新增模型压缩功能的计划。
解决步骤:
查看Paddleslim的ACT文档,学习ACT,熟悉基于不同任务进行ACT中量化压缩的主要步骤。
为某一任务接入ACT中的量化训练压缩功能:在适配paddle2.5,paddleslim2.5和套件develop版本的前提下,仿照pp-Liteseg接入ACT的PR,在各大套件的部署文件夹下(例如分割为PaddleSeg/deploy/slim/act) 接入ACT。下面以分割为例说明需要包括的新增文件内容:
参考paddleslim的ACT使用文档,对量化训练模型进行导出,并验证不同模型在量化蒸馏训练前后的精度和速度对比,验证通过后,撰写量化训练使用文档,增加相关Readme在 PaddleSeg/deploy/slim/act/readme.md。
提交PR到对应模型的仓库中。
注:不同套件的部署目录如下,将上述分割的目录进行相应替换即可:
模型列表
同一个任务仅有配置文件差异,一个任务需要完成对应的模型配置,领取通用目标检测任务的开发者将认领四个检测模型。
The text was updated successfully, but these errors were encountered: