Geoad: Towards Geospatial Foundation Models via Efficient Continual Pre-Training

Network Overview

🔍️🔍️ NEWS

• [2025/11/17] ✨✨ Init Repo.

📄📄 TODO

• ❎ submit to arxiv
• ❎ upload training code
• ❎ upload model weights

Clone Repo

---

We add mmpretrain, mmsegmentation, and open-cd as our repository submodule .

So, one should clone this repository use the script as follows:

clone repository

git clone --recurse-submodules https://github.com/woldier/Geoad

Tips

If one already cloned the project and forgot --recurse-submodules,

 # cloned the project and forgot clone submodules 🥲🥲
 git clone https://github.com/woldier/Geoad 

 # initialize and update each submodule in the repository 🥰🥰
 git submodule update --init

after that, we link

submodules/mmpretrain/mmpretrain $\to$ mmpretrain

submodules/mmsegmentation/mmseg $\to$ mmseg

submodules/open-cd/opencd $\to$ opencd :

soft link

ln -s submodules/mmpretrain/mmpretrain mmpretrain
ln -s submodules/mmsegmentation/mmseg mmseg
ln -s submodules/open-cd/opencd opencd

1. Creating Virtual Environment

---

This repo use python-3.8, for nvcc -v with cuda >= 11.6.

torch 2.1.1, cuda 12.1, mmcv 2.1.0, mmengine 0.9.1

Install script

conda create -n  peft-mmpretrain  python==3.8 -y
conda activate peft-mmpretrain


pip install torch==2.1.2+cu121  torchvision==0.16.2+cu121 -f https://download.pytorch.org/whl/torch_stable.html
# for CN user use follow script
pip install torch==2.1.2+cu121  torchvision==0.16.2+cu121 -f https://mirrors.aliyun.com/pytorch-wheels/cu121/  

pip install mmcv==2.1.0 mmengine==0.9.1 -f https://download.openmmlab.com/mmcv/dist/cu121/torch2.1/index.html

pip install -r submodules/mmpretrain/mmpretrain/requirements/runtime.txt
pip install -r submodules/mmsegmentation/mmseg/requirements/runtime.txt
pip install -r submodules/open-cd/opencd/requirements/runtime.txt

Installation of the reference document refer:

Torch and torchvision versions relationship.

Acknowledgements

This project is built upon OpenMMLab. We thank the OpenMMLab developers.

Citation

If you use Geoad in your research, please cite:

@article{,
  title={},
  author={},
  journal={},
  year={}
}