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
Missing ssd.py / train_pseudo137.py / train_pseudo151.py? #1
Comments
Hello, thanks for your attention. |
From what I understand, this repo contains at least two implementations of CrossTeaching. Can I refer just to detectron2 impl? Is it complete? |
Yes, you can. The proposed cross-teaching is actually a training paradigm. So whatever the platform you choose to implement on, the core idea is always the same. |
This is good news. Thanks! Yeah. I understand about the paradigm, was just wondering if the detectron2 impl is complete and fully represents description in the paper. |
Never mind. |
Do you sample half of the batch from the supervised subset as does unbiasedteacher codebase? |
As far as I know, hyper-parameters (such as batch size, learning rate, and augmentations) are usually set differently among recent semi-supervised object detection papers. In fact, these settings are vital to the model performance. In my experiments, I choose to follow the hyper-parameters provided by the official detectron2 platform for fair comparison. |
Sampling in unbiasedteacher codebase is done at https://github.com/machengcheng2016/CrossTeaching-SSOD/blob/534b7f993e58d0c19f26871a073647267f70e311/detectron2/VOC07-sup-VOC12-unsup-self-teaching-0.7/ubteacher/data/common.py#L125 It samples half of the batch from supervised subset, and half of the batch from unsupervised subset. Then both halfs are subject to weak and strong augs... |
detectron2 directory has five different subfolders / impls. what are the difference? just configs? |
My question was whether crosstraining does the sampling the same way as the original ubteacher. Now I see that it does the same sampling as the original ubteacher. So no more open question about sampling |
Oh I know where the problem is. Please check the script |
These are only used in the COCO experiments. The differences between 5 configs only lie in the random seed. You can json.load the |
I see! Would be great to have some recipes for the COCO experiments too.. |
Hi! Various
train_*
files includefrom ssd import build_ssd
, butssd.py
is missing in this repo.Is it a typo? Should it be instead
from csd import build_ssd_con
? Or are some files fromssd.pytorch
missing in this repo?What is the difference between
csd.py
andisd.py
?Also,
train_pseudo137.py
andtrain_pseudo151.py
mentioned at https://github.com/machengcheng2016/CrossTeaching-SSOD#33-reproduce-table3 are missing from the repo...Thanks!
The text was updated successfully, but these errors were encountered: