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

Do you have trained checkpoints? It will be very grateful if you upload it! #10

Open
SchultzWe opened this issue Apr 1, 2024 · 1 comment

Comments

@SchultzWe
Copy link

It is awosome and I want follow your work, how can I transfrom all block polygons to a full city map, is this repo contains related scripts to do that? Thank you for your kindness reply!

@Arking1995
Copy link
Owner

Hi, since our dataset expands a lot, and new version keeps going on, we currently have no plan to release checkpoint yet. You may process your own data by downloading from OSM dataset by using OSMNX library and using warp_bldg_axis function in this repo. Then take training from scratch. GNN won't consume too much resources and training usually converges in hours.

The full city map processed by looping simple matplotlib draw function for each building and block contours. The key point is the inverse converting from your warped coordinate to real projected coordinate system (UTM, etc.). This is mostly done by the inverse_warp function in this repo.

Hope this helps!

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