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

Roadmap of Open-CD #12

Open
likyoo opened this issue Mar 15, 2023 · 5 comments
Open

Roadmap of Open-CD #12

likyoo opened this issue Mar 15, 2023 · 5 comments

Comments

@likyoo
Copy link
Owner

likyoo commented Mar 15, 2023

If you have any suggested methods or features, please leave a comment below.

@likyoo likyoo pinned this issue Mar 15, 2023
@likyoo
Copy link
Owner Author

likyoo commented Mar 15, 2023

@croros
Copy link

croros commented Sep 25, 2024

Suggestion: add xview2 as a supported dataset.

Thanks

@likyoo
Copy link
Owner Author

likyoo commented Sep 25, 2024

Suggestion: add xview2 as a supported dataset.

Thanks

xview2 (xBD) seems to be a building segmentation dataset.

@ldzhhua
Copy link

ldzhhua commented Sep 26, 2024

如何建立高分辨率的自己的数据集?有自己的A和B的影像,label怎么去实现?图片分辨率最大支持多少?

@croros
Copy link

croros commented Sep 30, 2024

Suggestion: add xview2 as a supported dataset.
Thanks

xview2 (xBD) seems to be a building segmentation dataset.

xView2 is meant for assessing building damage i.e. building that were demolished. While not explicitly stated one of the tasks of the challenge is change detection in the form of damaged buildings. ChangeStar used the dataset when training their network.

Change labels can be easily created for it similar to Levir-CD.
However despite the similarities to Levir-CD I am having trouble creating a custom dataset for it as per your instructions here:
#74

Edit: I think I got it working. The issue was a corrupt png file and as a result an imbalance in the from/to img dirs

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