Repository files navigation

An open source AI model and interface for Earth.

Clay Model is licensed under theApache. This applies to the source code as well as the trained model weights.

The Documentation is licensed under theCC-BY-4.0 license.

Launch into aJupyterLab environment on

Binder	SageMaker Studio Lab

The easiest way to install Clay Foundation Model is via pip:

pip install git+https://github.com/Clay-foundation/model.git

This will install theclaymodel package and all its dependencies. You can then import and use it in your Python code:

fromclaymodel.datamoduleimportClayDataModulefromclaymodel.moduleimportClayMAEModule

For development or advanced usage, you can set up the full development environment:

To help out with development, start by cloning thisrepo-url

git clone <repo-url>cd model

Then we recommendusing mambato install the dependencies. A virtual environment will also be created with Python andJupyterLab installed.

mamba env create --file environment.yml

Activate the virtual environment first.

mamba activate claymodel

Finally, double-check that the libraries have been installed.

mamba list

mamba activate claymodelpython -m ipykernel install --user --name claymodel  # to install virtual env properlyjupyter kernelspec list --json                       # see if kernel is installedjupyter lab &

The neural network model can be ran viaLightningCLI v2.

To check out the different options available, and look at the hyperparameterconfigurations, run:

python trainer.py --help

To quickly test the model on one batch in the validation set:

python trainer.py fit --model ClayMAEModule --data ClayDataModule --config configs/config.yaml --trainer.fast_dev_run=True

To train the model:

python trainer.py fit --model ClayMAEModule --data ClayDataModule --config configs/config.yaml

More options can be found usingpython trainer.py fit --help, or at theLightningCLI docs.

Our Documentation usesJupyter Book.

Install it with:

pip install -U jupyter-book

Then build it with:

jupyter-book build docs/

You can preview the site locally with:

python -m http.server --directory _build/html

There is a GitHub Action on./github/workflows/deploy-docs.yml that builds the site and pushes it to GitHub Pages.