Skip to content

Latest commit

 

History

History
44 lines (33 loc) · 1.13 KB

README.md

File metadata and controls

44 lines (33 loc) · 1.13 KB

USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery

USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery
Jeremy Irvin*, Lucas Tao*, Joanne Zhou, Yuntao Ma, Langston Nashold, Benjamin Liu, Andrew Y. Ng

*Equal contribution

Official implementation of the paper "USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery".

Highlights

TBD

Data Downloading

TBD

Environment Set-up

Performing the following step in USat directory.

  1. Create a Python 3.9 conda enviroment.
conda create -n usat python=3.9
  1. Install dependency
pip install -r requirements.txt
  1. Editable install the project code.
pip install --no-deps -e ./

Data Preprocessing

TBD

Model Training

TBD

Model Evaluation

TBD

Citation

TBD

Contact

TBD