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

共享SR和非共享TP #4

Closed
zhaoguoqing12 opened this issue Jul 31, 2021 · 2 comments
Closed

共享SR和非共享TP #4

zhaoguoqing12 opened this issue Jul 31, 2021 · 2 comments

Comments

@zhaoguoqing12
Copy link

zhaoguoqing12 commented Jul 31, 2021

论文中多阶段训练 提出使用共享SR和非共享TP,但是代码中写的是 非共享SR和共享TP
image
image
根据你提出的训练命令
python3 -u main.py --arch="tsrn_tl_cascade" --batch_size=48 --STN --mask --use_distill --gradient --sr_share --stu_iter=3 --vis_dir='vis_TPGSR-TSRN'
--sr_share 默认为False,训练时是True

@vardenppp
Copy link

这里应该:上面是如果不sr_share,初始化多个sr模块,下面是初始化多个tpg模块。
但最后实际应用的时候,是根据是否share进行选择的,你可以搜一下“pick”,代码里写的是如果share,pick=0,否则pick=i。

@zhaoguoqing12
Copy link
Author

@vardenppp 感谢,我看到了。所以训练不加 sr_share 并且 加上 tpg_share,才是共享SR和非共享TP。

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

2 participants