关于repconv的实现 - Githubissues

tinyvision / DAMO-YOLO

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

Apache License 2.0

3.78k stars 476 forks source link

关于repconv的实现 #59

Closed jie311 closed 1 year ago

jie311 commented 1 year ago

Before Asking

[X] I have read the README carefully. 我已经仔细阅读了README上的操作指引。
[ ] I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。
[X] I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

[X] I have searched the DAMO-YOLO issues and found no similar questions.

Question

在damoyolo的实现中，self.rbr_identity = None，即没有使用identity分支，想请教一下去掉identity分支是基于什么样的考虑

Additional

No response

cwhgn commented 1 year ago

我们实验发现去掉identity分支可以达到一个更好的效果。原因可能是，原来的repvgg是不包含shortcut结构的，所以需要identity分支。我们的TinyNAS和Efficient RepGFPN中是包含shortcut的，因此identity分支就不是必须的了。