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

大batch_size和多目标检测的双层for循环导致ATSS算法执行时间长,GPU利用率低,如何提升性能与效率? #102

Open
chenrui17 opened this issue Aug 11, 2022 · 3 comments

Comments

@chenrui17
Copy link

如题,batch _size = 15, 检测目标类别=6,则atss算法会连续调用90次,通过profile,该部分GPU利用率低,耗时占比训练 30%左右,如何考虑优化,从而提升性能 与GPU利用率呢?

@suekarry
Copy link

如题,batch _size = 15, 检测目标类别=6,则atss算法会连续调用90次,通过profile,该部分GPU利用率低,耗时占比训练 30%左右,如何考虑优化,从而提升性能 与GPU利用率呢?

您好,我想问一下,您知道论文里的伪代码在哪个文件里?我找了好久没有找到符合的

@Tangled12
Copy link

应该是在 atss_core/modeling/rpn/atss/loss.py
里面的prepare_target是准备计算loss的target,也就是匹配anchor和target

@suekarry
Copy link

suekarry commented Aug 3, 2023

应该是在 atss_core/modeling/rpn/atss/loss.py 里面的prepare_target是准备计算loss的target,也就是匹配anchor和target

是的!谢谢你~

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

3 participants