Clay Foundation Model - v1.0

Release v1.0 (2024/06/06)

💫 Highlights

• 🎉 Release of Clay Foundation Model v1.0 🎉

🚀 Model

• Datamodule & Model for Clay v1 by @srmsoumya in https://github.com/Clay-foundation/model/pull/253

🗃️ Data Pipeline

• Moved data pipeline code into stacchip a dedicated library for the data wrangling

📖 Documentation

• Clay over aoi by @yellowcap in https://github.com/Clay-foundation/model/pull/116
• Convert run-over-aoi ipynb to md by @yellowcap in https://github.com/Clay-foundation/model/pull/122
• Static Documentation for v0.1 by @brunosan in https://github.com/Clay-foundation/model/pull/118
• Document data sampling strategy by @yellowcap in https://github.com/Clay-foundation/model/pull/124
• Updating location to download imagery script in docs by @MaxLenormand in https://github.com/Clay-foundation/model/pull/198
• Change "Radiant Earth Foundation" to "Radiant Earth" in docs by @kbgg in https://github.com/Clay-foundation/model/pull/214
• Update instructions to re-lock conda-lock.yml file by @weiji14 in https://github.com/Clay-foundation/model/pull/225
• chore(docs): correct typos and improve stylistic consistency by @kelseyjosund in https://github.com/Clay-foundation/model/pull/232
• Partial inputs - Pakistan flood tutorial by @lillythomas in https://github.com/Clay-foundation/model/pull/154
• Obtain patch level metadata (e.g. geospatial bounds and cloud cover), save and demo DEP use case (sim search) by @lillythomas in https://github.com/Clay-foundation/model/pull/172
• Obtain patch level cloud coverage percentages by @lillythomas in https://github.com/Clay-foundation/model/pull/184
• Tutorial on burn scar analysis using embeddings from partial inputs by @yellowcap in https://github.com/Clay-foundation/model/pull/149
• Doc updates by @brunosan in https://github.com/Clay-foundation/model/pull/230
• Update specification.md by @brunosan in https://github.com/Clay-foundation/model/pull/250
• Add notebook showing how to run v1 by @yellowcap in https://github.com/Clay-foundation/model/pull/254
• Documented v1 sampling strategy by @yellowcap in https://github.com/Clay-foundation/model/pull/249
• Updates the mamba install instructions link. by @dbonomo in https://github.com/Clay-foundation/model/pull/252
• Remove clay-v0-tutorials & add visualize embeddings for v1 by @srmsoumya in https://github.com/Clay-foundation/model/pull/256
• Minor spelling fix by @tylere in https://github.com/Clay-foundation/model/pull/260
• Shorten comment line length by @yellowcap in https://github.com/Clay-foundation/model/pull/261
• Refactor docs by moving v0 docs into separate section by @yellowcap in https://github.com/Clay-foundation/model/pull/262
• Docs v1 continued by @yellowcap in https://github.com/Clay-foundation/model/pull/263
• Documented metadata file for normalization and wavelenghts by @yellowcap in https://github.com/Clay-foundation/model/pull/266
• [small change] add source.coop link by @brunosan in https://github.com/Clay-foundation/model/pull/137
• Segmentation on Clay by @srmsoumya in https://github.com/Clay-foundation/model/pull/257

🧰 Maintenance

• [pre-commit.ci] pre-commit autoupdate by @pre-commit-ci in https://github.com/Clay-foundation/model/pull/206
• Bump conda-lock from 2.5.1 to 2.5.6 by @weiji14 in https://github.com/Clay-foundation/model/pull/183
• Remove scripts folder by @yellowcap in https://github.com/Clay-foundation/model/pull/265
• Unified v1 and v0 environments by @yellowcap in https://github.com/Clay-foundation/model/pull/264
• Add osx-arm64 platform to conda-lock.yml file and GitHub Actions CI by @weiji14 in https://github.com/Clay-foundation/model/pull/164
• Move pipeline scripts into dedicated folder by @yellowcap in https://github.com/Clay-foundation/model/pull/163
• Memory buildup clean by @brunosan in https://github.com/Clay-foundation/model/pull/158
• Add osx platform to conda lock file and CI by @chuckwondo in https://github.com/Clay-foundation/model/pull/162
• Add scikit-learn by @weiji14 in https://github.com/Clay-foundation/model/pull/159
• Remove float16 dype in favor of float32 by @yellowcap in https://github.com/Clay-foundation/model/pull/143
• Remove stale bands argument from clay model classes by @yellowcap in https://github.com/Clay-foundation/model/pull/144

🛠️ v0.2 updates

• Add normalization parameters to documentation by @yellowcap in https://github.com/Clay-foundation/model/pull/152
• Worldcover embeddings conus by @yellowcap in https://github.com/Clay-foundation/model/pull/153
• Create data/minicubes directory if it doesn't already exist by @weiji14 in https://github.com/Clay-foundation/model/pull/160
• Clay pipeline v04 by @yellowcap in https://github.com/Clay-foundation/model/pull/173
• Shuffle patches only during training by @yellowcap in https://github.com/Clay-foundation/model/pull/135
• Add option to output raw patch embeddings by @yellowcap in https://github.com/Clay-foundation/model/pull/133

🧑‍🤝‍🧑 New Contributors

• @chuckwondo made their first contribution in https://github.com/Clay-foundation/model/pull/162
• @MaxLenormand made their first contribution in https://github.com/Clay-foundation/model/pull/198
• @kbgg made their first contribution in https://github.com/Clay-foundation/model/pull/214
• @kelseyjosund made their first contribution in https://github.com/Clay-foundation/model/pull/232
• @dbonomo made their first contribution in https://github.com/Clay-foundation/model/pull/252
• @tylere made their first contribution in https://github.com/Clay-foundation/model/pull/260

Full Changelog: https://github.com/Clay-foundation/model/compare/v0.0.1...v1.0

Sustainable Development - Data Catalogs and Interfaces - Python
Published by yellowcap 11 months ago

Clay Foundation Model - v0.0.1

Release v0.0.1 (2024/01/12)

💫 Highlights

• 🎉 First release of Clay Foundation Model 🎉
• Implement MAE with support for position, time, latlon & channel embeddings (#47)

🚀 Model

• Generate embeddings from CLAYModule trained with latlon/time encodings (#96)
• Add multigpu support & UI to test embeddings (#109)
• Refactor model for multi-device usage and easier disabling of masking (#95)
• Rename embeddings file to include MGRS code and store GeoTIFF source_url (#86)
• Callback function to log Masked Autoencoder reconstructions to WandB (#88)
• Adapt model to load 512x512 images from s3 bucket (#85)
• Save embeddings with spatiotemporal metadata to GeoParquet (#73)
• Generate embeddings via prediction loop (#56)
• Initial Vision Transformer architecture with MAE decoder (#37)

🗃️ Data Pipeline

• Adapted sampling strategy (#81)
• Allow ClayDataModule to load GeoTIFF files directly from s3 (#92)
• Let ClayDataModule return same spatiotemporal fields as GeoTIFFDataModule (#91)
• Improve date handling for data pipeline (#76)
• Let LightningDataModule return spatiotemporal metadata (#66)
• check for no data on a tile level in sentinel 1 vv and vh, sentinel 2 and DEM (#60)
• Batch setup (#54)
• LightningDataModule to load GeoTIFF files (#52)
• Ready for batch (#44)
• Tiler module (#41)
• Landcover based sampling strategy (#29)
• Datacube (#27)

📖 Documentation

• Document how the benchmark dataset labels were prepared (#100)
• Document how to finetune pretrained model on downstream task (#99)
• Document how to generate vector embeddings (#98)
• Document how to run the datacube pipeline with a batch job (#97)
• Initialize Jupyter Book documentation (#89)
• Setting the model license to OpenRail-M (#63)
• Create CODE_OF_CONDUCT.md (#53)

🧰 Maintenance

• Bump pytorch from 2.0.0 to 2.1.0, CUDA from 11.8 to 12.0 (#51)
• Add pre-commit hooks with ruff formatter/linter rules (#26)
• Setup GitHub Actions Continuous Integration tests (#25)
• Setup LightningCLI trainer script (#24)
• Initial conda environment and binder links (#15)

🧑‍🤝‍🧑 Contributors

• @brunosan
• @lillythomas
• @srmsoumya
• @yellowcap
• @weiji14

Full Changelog: https://github.com/Clay-foundation/model/compare/v0.0.0...v0.0.1

Sustainable Development - Data Catalogs and Interfaces - Python
Published by weiji14 over 1 year ago