{"id":28957198,"url":"https://github.com/developmentseed/chabud2023","last_synced_at":"2025-06-23T21:41:45.714Z","repository":{"id":163783987,"uuid":"638667080","full_name":"developmentseed/chabud2023","owner":"developmentseed","description":"Change detection for Burned area Delineation (ChaBuD) ECML/PKDD 2023 challenge","archived":false,"fork":false,"pushed_at":"2023-06-14T06:01:49.000Z","size":203,"stargazers_count":5,"open_issues_count":6,"forks_count":1,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-04-10T03:11:33.120Z","etag":null,"topics":["change-detection","ecml-pkdd","ecmlpkdd","lightning","ml-competition","remote-sensing","sentinel-2","torchdata"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/developmentseed.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-05-09T21:00:16.000Z","updated_at":"2024-03-23T05:59:07.000Z","dependencies_parsed_at":"2023-09-24T10:14:21.520Z","dependency_job_id":null,"html_url":"https://github.com/developmentseed/chabud2023","commit_stats":{"total_commits":16,"total_committers":2,"mean_commits":8.0,"dds":0.125,"last_synced_commit":"576c8f344bf4b3dd0dcbca3001d9250ef98044cb"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/developmentseed/chabud2023","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developmentseed%2Fchabud2023","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developmentseed%2Fchabud2023/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developmentseed%2Fchabud2023/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developmentseed%2Fchabud2023/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/developmentseed","download_url":"https://codeload.github.com/developmentseed/chabud2023/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/developmentseed%2Fchabud2023/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261561482,"owners_count":23177615,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["change-detection","ecml-pkdd","ecmlpkdd","lightning","ml-competition","remote-sensing","sentinel-2","torchdata"],"created_at":"2025-06-23T21:41:45.497Z","updated_at":"2025-06-23T21:41:45.706Z","avatar_url":"https://github.com/developmentseed.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ChaBuD2023\n\nA Machine Learning data pipeline for the\n[Change detection for Burned area Delineation (ChaBuD)](https://huggingface.co/spaces/competitions/ChaBuD-ECML-PKDD2023)\nchallenge at the [ECML/PKDD 2023](https://2023.ecmlpkdd.org/submissions/discovery-challenge/challenges)\nconference.\n\n[![Weights and Biases experiments](https://img.shields.io/static/v1?label=WandB\u0026message=experiments\u0026color=FFBE00\u0026logo=weightsandbiases)](https://wandb.ai/devseed/chabud2023)\n\n# Getting started\n\n### Quickstart\n\nLaunch into a [JupyterLab](https://jupyterlab.readthedocs.io) environment on\n\n| [Binder](https://mybinder.readthedocs.io/en/latest) | [SageMaker Studio Lab](https://studiolab.sagemaker.aws) | [Planetary  Computer](https://planetarycomputer.microsoft.com) |\n|:--:|:--:|:--:|\n| [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/developmentseed/chabud2023/main) | [![Open in SageMaker Studio Lab](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/developmentseed/chabud2023/blob/main/train_chabud.ipynb) | [![Open on Planetary Computer](https://img.shields.io/badge/Open-Planetary%20Computer-black?style=flat\u0026logo=microsoft)](https://pccompute.westeurope.cloudapp.azure.com/compute/hub/user-redirect/git-pull?repo=https%3A%2F%2Fgithub.com%2Fdevelopmentseed%2Fchabud2023\u0026urlpath=lab%2Ftree%2Fchabud2023%2Ftrain_chabud.ipynb\u0026branch=main) |\n\n## Installation\n\n### Basic\n\nTo help out with development, start by cloning this [repo-url](/../../)\n\n    git clone \u003crepo-url\u003e\n\nThen I recommend [using mamba](https://mamba.readthedocs.io/en/latest/installation.html)\nto install the dependencies.\nA virtual environment will also be created with Python and\n[JupyterLab](https://github.com/jupyterlab/jupyterlab) installed.\n\n    cd chabud2023\n    mamba env create --file environment.yml\n\nActivate the virtual environment first.\n\n    mamba activate chabud\n\nFinally, double-check that the libraries have been installed.\n\n    mamba list\n\n### Advanced\n\nThis is for those who want full reproducibility of the virtual environment.\nCreate a virtual environment with just Python and conda-lock installed first.\n\n    mamba create --name chabud python=3.11 conda-lock=2.0.0\n    mamba activate chabud\n\nGenerate a unified [`conda-lock.yml`](https://github.com/conda/conda-lock) file\nbased on the dependency specification in `environment.yml`. Use only when\ncreating a new `conda-lock.yml` file or refreshing an existing one.\n\n    conda-lock lock --mamba --file environment.yml\n\nInstalling/Updating a virtual environment from a lockile. Use this to sync your\ndependencies to the exact versions in the `conda-lock.yml` file.\n\n    conda-lock install --mamba --name chabud conda-lock.yml\n\nSee also https://conda.github.io/conda-lock/output/#unified-lockfile for more\nusage details.\n\n## Usage\n\n### Running jupyter lab\n\n    mamba activate chabud\n    python -m ipykernel install --user --name chabud  # to install virtual env properly\n    jupyter kernelspec list --json                    # see if kernel is installed\n    jupyter lab \u0026\n\n### Running the model\n\nThe neural network model can be ran via\n[LightningCLI v2](https://pytorch-lightning.medium.com/introducing-lightningcli-v2-supercharge-your-training-c070d43c7dd6).\nTo check out the different options available, and look at the hyperparameter\nconfigurations, run:\n\n    python trainer.py --help\n    python trainer.py test --print_config\n\nTo quickly test the model on one batch in the validation set:\n\n    python trainer.py validate --trainer.fast_dev_run=True\n\nTo train the model for a hundred epochs and log metrics to\n[WandB](https://wandb.ai/devseed/chabud2023):\n\n    python trainer.py fit --trainer.max_epochs=100 \\\n                          --trainer.logger=WandbLogger \\\n                          --trainer.logger.entity=devseed \\\n                          --trainer.logger.project=chabud2023\n\nTo generate the CSV file of predicted masks on the validation set for\n[submission](https://huggingface.co/datasets/chabud-team/chabud-ecml-pkdd2023/blob/main/create_sample_submission.py)\nto https://huggingface.co/spaces/competitions/ChaBuD-ECML-PKDD2023.\n\n    python trainer.py test --model.submission_filepath=submission.csv\n\nMore options can be found using `python trainer.py fit --help`, or at the\n[LightningCLI docs](https://lightning.ai/docs/pytorch/2.0.2/cli/lightning_cli.html).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevelopmentseed%2Fchabud2023","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdevelopmentseed%2Fchabud2023","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdevelopmentseed%2Fchabud2023/lists"}