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

Excuse me, how can I realize the training of D2Det model with iSAID data set #33

Open
zhaozhiyi11 opened this issue Dec 10, 2020 · 7 comments

Comments

@zhaozhiyi11
Copy link

Excuse me, how can I realize the training of D2Det model with iSAID data set

@JialeCao001
Copy link
Owner

@zhaozhiyi11 Thanks for interests. I remeber that some parameters should be changed (e.g., the number of proposals), which follow the settings reported in iSAID paper.

@zhaozhiyi11
Copy link
Author

@zhaozhiyi11 Thanks for interests. I remeber that some parameters should be changed (e.g., the number of proposals), which follow the settings reported in iSAID paper.

Thanks for your reply.Have you ever trained D2Det with an iSAID dataset?Can you share some of the models you've trained with the iSAID dataset?proposals are put in which document?

@JialeCao001
Copy link
Owner

@zhaozhiyi11 I am sorry that I donot save the model on iSAID from the foreign server. The parameter settings follow the iSAID paper https://openaccess.thecvf.com/content_CVPRW_2019/papers/DOAI/Zamir_iSAID_A_Large-scale_Dataset_for_Instance_Segmentation_in_Aerial_Images_CVPRW_2019_paper.pdf.

@zhaozhiyi11
Copy link
Author

@zhaozhiyi11 I am sorry that I donot save the model on iSAID from the foreign server. The parameter settings follow the iSAID paper https://openaccess.thecvf.com/content_CVPRW_2019/papers/DOAI/Zamir_iSAID_A_Large-scale_Dataset_for_Instance_Segmentation_in_Aerial_Images_CVPRW_2019_paper.pdf.

谢谢您的回复!这边论文我已经看过了,您说的修改参数是在D2Det的模型的config里修改吗?

@JialeCao001
Copy link
Owner

对了,需要把一些coco的参数按照这个论文第7页里面的说法进行修改。

@zhaozhiyi11
Copy link
Author

对了,需要把一些coco的参数按照这个论文第7页里面的说法进行修改。
您好!我还是没有找到在要修改哪些参数,您能具体说一下吗?麻烦您了!

@JialeCao001
Copy link
Owner

JialeCao001 commented Dec 14, 2020

@zhaozhiyi11 主要可能是下面这些参数:
train_cfg: rcnn.sampler.num = 1024, rcnn.sampler.pos_fraction= 0.5;test_cfg:rcnn.max_per_img=500;
test_pipeline: img_scale=[(1333, 800),(1333, 1200),(1333, 1000),(1333, 600),(1333, 400)].
如果还有啥调参的问题也可以加我微信。

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