# Clay documentation
<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
## Overview
Clay is a [foundational model](#) of Earth using Earth Observation data.
As the AI Deep Learning architecture, it uses an expanded [visual
transformer](#) upgraded to understant geospatial and temporal relations
on Earth data, from any instrument/spectral data. The AI self-supervised
fundational task is a [Masked Autoencoder
(MAE)](https://arxiv.org/abs/2111.06377) approach for training.
The Clay model primarily functions in two ways: first, by directly
generating semantic embeddings for tasks like similarity searches, and
second, through fine-tuning its outputs with additional data labels.
This fine-tuning supports various tasks, including classification
(e.g. flood detection and deforestation monitoring), regression
(e.g. estimating carbon stock or crop yields), and generative tasks such
as creating RGB imagery from SAR data. Moreover, users can further
enhance model performance by incorporating higher-resolution data.
This documentation uses [nbdev](#), which combines documentation, code
samples and an SDK. This means that every page is also a python notebook
anyone can use, with practical code examples for each functionality, and
use case. Moreover, you can install `pip install clay` and use the same
functions.
Clay is open source, open data and open for business.
## Where is what
- Our **website** is [madewithclay.org](https://madewithclay.org).
- The Clay model **code** lives on
[Github](https://github.com/Clay-foundation/model). License:
[Apache](https://github.com/Clay-foundation/model/LICENSE).
- The Clay model **weights** live on [Huggin
Face](https://huggingface.co/made-with-clay/Clay/). License:
[OpenRAIL-M](https://github.com/Clay-foundation/model/blob/main/LICENSE-MODEL.md).
- The Clay **documentation** [lives on this
site](https://clay-foundation.github.io/documentation/). License:
[CC-BY](#).
- The Clay **SDK** lives on
[PyPi](https://pypi.org/project/madewithclay/). License: [Apache](#).
- We maintain a set of **embeddings** on [Source Cooperative](#).
License: [ODC-BY](#).
## How to use Clay
The model can be used in two main ways:
1. Directly, use it to make inference. See [Model](Model.html)
1. Check and run Benchmarks on the model. See
[Benchmarks](Benchmarks.html)
2. Generating semantic **embeddings**. E.g. for Similarity search. See
[Embeddings](Embeddings.html).
3. **Fine-tunning** the model for other tasks, or for other input data.
E.g. flood detection, crop yields, … See
[Fine-tunning](Fine-tunning.html).
## How to contribute
Clay is an open source project, and we welcome contributions of all
kinds.
The Documentation, python package and notebooks are all the same
[NBdev](https://nbdev.fast.ai/) project, located
[here](https://github.com/Clay-foundation/documentation).
> Note: If you want to contribute to the model code, please check the
> [model repository](https://github.com/Clay-foundation/model).
To install the nbdev project locally, you can use:
``` bash
git clone git@github.com:Clay-foundation/documentation.git
cd documentation
pip install nbdev
nbdev_install_git_hooks
```
After you make changes, you can export the notebooks into both the
package, rendered documentation and clean jupyter notebook execution
metadata with:
``` bash
nbdev_prepare
```
If you want to preview the documentation locally, you can use:
``` bash
nbdev_preview
```
To run the test locally, you need to install [Github
CLI](https://cli.github.com/) and act extension
`sudo gh extension install nektos/gh-act`.
The “Clay model releases” folder uses a lot of resources to document the
version releases. To run these you also need access to the `S3` bucket
with outputs and all the embeddgins. You will need a local file
(e.g. `.secrets`) with the AWS credentials to read the Clay buckets.
Remember to confirm this file is on `.gitignore` to avoid commiting it.
Then you can run the tests with:
``` bash
gh act --secret-file .secrets
```
–
Clay is a fiscally sponsored project of [Radiant Earth](), a USA
registered 501(c)3 non-profit.
Raw data
{
"_id": null,
"home_page": "https://github.com/Clay-foundation/documentation",
"name": "madewithclay",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": "",
"keywords": "EO AI ML Geospatial Remote-Sensing foundational-models",
"author": "Clay and collaborators",
"author_email": "info@madewithclay.org",
"download_url": "https://files.pythonhosted.org/packages/68/b7/cb9cd5f89179308c3b3d7460f5e5b599ded9fb4ae965e222eabca50df002/madewithclay-0.0.5.tar.gz",
"platform": null,
"description": "# Clay documentation\n\n<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->\n\n## Overview\n\nClay is a [foundational model](#) of Earth using Earth Observation data.\nAs the AI Deep Learning architecture, it uses an expanded [visual\ntransformer](#) upgraded to understant geospatial and temporal relations\non Earth data, from any instrument/spectral data. The AI self-supervised\nfundational task is a [Masked Autoencoder\n(MAE)](https://arxiv.org/abs/2111.06377) approach for training.\n\nThe Clay model primarily functions in two ways: first, by directly\ngenerating semantic embeddings for tasks like similarity searches, and\nsecond, through fine-tuning its outputs with additional data labels.\nThis fine-tuning supports various tasks, including classification\n(e.g.\u00a0flood detection and deforestation monitoring), regression\n(e.g.\u00a0estimating carbon stock or crop yields), and generative tasks such\nas creating RGB imagery from SAR data. Moreover, users can further\nenhance model performance by incorporating higher-resolution data.\n\nThis documentation uses [nbdev](#), which combines documentation, code\nsamples and an SDK. This means that every page is also a python notebook\nanyone can use, with practical code examples for each functionality, and\nuse case. Moreover, you can install `pip install clay` and use the same\nfunctions.\n\nClay is open source, open data and open for business.\n\n## Where is what\n\n- Our **website** is [madewithclay.org](https://madewithclay.org).\n- The Clay model **code** lives on\n [Github](https://github.com/Clay-foundation/model). License:\n [Apache](https://github.com/Clay-foundation/model/LICENSE).\n- The Clay model **weights** live on [Huggin\n Face](https://huggingface.co/made-with-clay/Clay/). License:\n [OpenRAIL-M](https://github.com/Clay-foundation/model/blob/main/LICENSE-MODEL.md).\n- The Clay **documentation** [lives on this\n site](https://clay-foundation.github.io/documentation/). License:\n [CC-BY](#).\n- The Clay **SDK** lives on\n [PyPi](https://pypi.org/project/madewithclay/). License: [Apache](#).\n- We maintain a set of **embeddings** on [Source Cooperative](#).\n License: [ODC-BY](#).\n\n## How to use Clay\n\nThe model can be used in two main ways:\n\n1. Directly, use it to make inference. See [Model](Model.html)\n 1. Check and run Benchmarks on the model. See\n [Benchmarks](Benchmarks.html)\n2. Generating semantic **embeddings**. E.g. for Similarity search. See\n [Embeddings](Embeddings.html).\n3. **Fine-tunning** the model for other tasks, or for other input data.\n E.g. flood detection, crop yields, \u2026 See\n [Fine-tunning](Fine-tunning.html).\n\n## How to contribute\n\nClay is an open source project, and we welcome contributions of all\nkinds.\n\nThe Documentation, python package and notebooks are all the same\n[NBdev](https://nbdev.fast.ai/) project, located\n[here](https://github.com/Clay-foundation/documentation).\n\n> Note: If you want to contribute to the model code, please check the\n> [model repository](https://github.com/Clay-foundation/model).\n\nTo install the nbdev project locally, you can use:\n\n``` bash\ngit clone git@github.com:Clay-foundation/documentation.git\ncd documentation\npip install nbdev\nnbdev_install_git_hooks\n```\n\nAfter you make changes, you can export the notebooks into both the\npackage, rendered documentation and clean jupyter notebook execution\nmetadata with:\n\n``` bash\nnbdev_prepare\n```\n\nIf you want to preview the documentation locally, you can use:\n\n``` bash\nnbdev_preview\n```\n\nTo run the test locally, you need to install [Github\nCLI](https://cli.github.com/) and act extension\n`sudo gh extension install nektos/gh-act`.\n\nThe \u201cClay model releases\u201d folder uses a lot of resources to document the\nversion releases. To run these you also need access to the `S3` bucket\nwith outputs and all the embeddgins. You will need a local file\n(e.g.\u00a0`.secrets`) with the AWS credentials to read the Clay buckets.\nRemember to confirm this file is on `.gitignore` to avoid commiting it.\n\nThen you can run the tests with:\n\n``` bash\ngh act --secret-file .secrets\n```\n\n\u2013\n\nClay is a fiscally sponsored project of [Radiant Earth](), a USA\nregistered 501(c)3 non-profit.\n",
"bugtrack_url": null,
"license": "Apache Software License 2.0",
"summary": "SDK to use Clay, the AI for Earth",
"version": "0.0.5",
"project_urls": {
"Homepage": "https://github.com/Clay-foundation/documentation"
},
"split_keywords": [
"eo",
"ai",
"ml",
"geospatial",
"remote-sensing",
"foundational-models"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "28dfde3038ba3abae3816ac039c26756d090a939e22c5ea200cd58b62a9dfa1c",
"md5": "8e6f54105fbc09193d9e387629c9ceb8",
"sha256": "16e63e3f900fb514044b374c6b34ebb35ea6a55dfc2e26e0d272e40e39cd48b4"
},
"downloads": -1,
"filename": "madewithclay-0.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "8e6f54105fbc09193d9e387629c9ceb8",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.7",
"size": 14379,
"upload_time": "2024-01-01T22:10:02",
"upload_time_iso_8601": "2024-01-01T22:10:02.945716Z",
"url": "https://files.pythonhosted.org/packages/28/df/de3038ba3abae3816ac039c26756d090a939e22c5ea200cd58b62a9dfa1c/madewithclay-0.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "68b7cb9cd5f89179308c3b3d7460f5e5b599ded9fb4ae965e222eabca50df002",
"md5": "f34da71ea672022882edb9f66e1cadd5",
"sha256": "bd7a5426a84aad68bf74f70842ca27bf37f554690aa33c806a59edb8b143c4ac"
},
"downloads": -1,
"filename": "madewithclay-0.0.5.tar.gz",
"has_sig": false,
"md5_digest": "f34da71ea672022882edb9f66e1cadd5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 16315,
"upload_time": "2024-01-01T22:10:04",
"upload_time_iso_8601": "2024-01-01T22:10:04.447462Z",
"url": "https://files.pythonhosted.org/packages/68/b7/cb9cd5f89179308c3b3d7460f5e5b599ded9fb4ae965e222eabca50df002/madewithclay-0.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-01-01 22:10:04",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Clay-foundation",
"github_project": "documentation",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "madewithclay"
}
JSON
