{"id":47630150,"url":"https://github.com/ahestevenz/flood-detection-segmentation","last_synced_at":"2026-04-01T23:18:33.530Z","repository":{"id":177964054,"uuid":"661158008","full_name":"ahestevenz/flood-detection-segmentation","owner":"ahestevenz","description":"Flood detector using effientnet as semantic segmentation model","archived":false,"fork":false,"pushed_at":"2026-03-22T10:05:43.000Z","size":125516,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-03-23T00:59:07.525Z","etag":null,"topics":["computer-vision","effientnet","flood-detection","floods","machine-learning","segmentation-models"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ahestevenz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-07-02T01:14:21.000Z","updated_at":"2024-11-28T11:23:54.000Z","dependencies_parsed_at":"2023-10-11T09:02:59.226Z","dependency_job_id":"c027d452-5f84-4a30-a60f-162322ee0a89","html_url":"https://github.com/ahestevenz/flood-detection-segmentation","commit_stats":{"total_commits":10,"total_committers":1,"mean_commits":10.0,"dds":0.0,"last_synced_commit":"525291c84b3f40370fb086a493d1285f05efd450"},"previous_names":["ahestevenz/flood-detection-segmentation"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/ahestevenz/flood-detection-segmentation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahestevenz%2Fflood-detection-segmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahestevenz%2Fflood-detection-segmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahestevenz%2Fflood-detection-segmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahestevenz%2Fflood-detection-segmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ahestevenz","download_url":"https://codeload.github.com/ahestevenz/flood-detection-segmentation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ahestevenz%2Fflood-detection-segmentation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31292871,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T21:15:39.731Z","status":"ssl_error","status_checked_at":"2026-04-01T21:15:34.046Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["computer-vision","effientnet","flood-detection","floods","machine-learning","segmentation-models"],"created_at":"2026-04-01T23:18:32.979Z","updated_at":"2026-04-01T23:18:33.506Z","avatar_url":"https://github.com/ahestevenz.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Flood Detector\nA flood detector using effientnet as semantic segmentation model. \n\n## Dataset\n[Sen1Floods11](https://github.com/cloudtostreet/Sen1Floods11): a georeferenced dataset to train and test deep learning flood algorithms for Sentinel-1 (Example). This data was generated by Cloud to Street, a Public Benefit Corporation: https://www.cloudtostreet.info/. For questions about this dataset or code please email support@cloudtostreet.info. \n\nPaper:\nBonafilia, D., Tellman, B., Anderson, T., Issenberg, E. 2020. [Sen1Floods11: a georeferenced dataset to train and test deep learning flood algorithms for Sentinel-1](https://openaccess.thecvf.com/content_CVPRW_2020/html/w11/Bonafilia_Sen1Floods11_A_Georeferenced_Dataset_to_Train_and_Test_Deep_Learning_CVPRW_2020_paper.html). The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 210-211.\n\n\n## Training and Testing\n### Requirements\n\n#### Python environment\n\nIt is highly recomomended to run the training scrips inside of python environment, in case the system does not have any use the following procedure (check [Virtualenvwrapper Installation](https://virtualenvwrapper.readthedocs.io/en/latest/install.html) for more details).\n\n```setup\n$ pip install --user virtualenvwrapper virtualenv\n```\n\nAdd three lines to your shell startup file (.bashrc, .profile, etc.) to set the location where the virtual environments should live:\n\n```\nexport WORKON_HOME=$HOME/.virtualenvs\nexport PROJECT_HOME=$HOME/Devel\nsource /usr/local/bin/virtualenvwrapper.sh\n```\n\nAfter editing it, reload the startup file (e.g., run `source ~/.bashrc`) and create a python environment:\n\n```\n$ mkvirtualenv venv_py \n$ workon venv_py\n```\n\n#### Installing the package\n\nOnce the python environment was configured, run the following procedure to install all the required packages\n```setup\n(venv_py)$ git clone https://github.com/ahestevenz/flood-detection-segmentation\n(venv_py)$ cd flood-detection-segmentation\n(venv_py)$ pip install .\n```\n\n### Training\n\nThe following script will be used to train the model.\n```train\n(venv_py)$ bn-run-train --help                                                          \nusage: bn-run-train [-h] [-j JSON_FILE] [-v] [-p output.prof]\n\nWelcome to the Bushfires Detector training script\n\noptional arguments:\n  -h, --help            show this help message and exit\n  -j JSON_FILE, --json_file JSON_FILE\n                        JSON configuration (default: \"/Users/ahestevenz/Desktop/tech-projects/1_code/flood-detection-segmentation/config.json\")\n  -v, --verbose         Increase logging output (default: INFO)(can be specified several times)\n  -p output.prof, --profile output.prof\n                        Run with profiling and store output in given file\n\n```\nRun the above command to start the training (check the `data` and `artefacts` paths in `config.json` first)\n```train\n(venv_py)$ bn-run-train --json_file config.json   \n```\n\n### Testing\n\nTo evaluate the model indicated in `config.json` file, run this command:\n\n```test\n(venv_py)$ bn-run-test --json_file config.json \n```\n\n## Results\n\nQualitative results using the validation dataset\n\n![](https://github.com/ahestevenz/flood-detection-segmentation/blob/main/assets/valid_results.gif)\n\nIn the plot below, you can observe quantitative results using a similarity metric between ground truth and prediction masks.\n\n![](https://github.com/ahestevenz/flood-detection-segmentation/blob/main/assets/perf_result.png)\n\n## TODO List \n- [x] Add Docker container option to run/train models\n- [x] Add release revision for [NASA_IIAC_IEEE_GRSS_ESITC_Flood_Data](https://nasa-impact.github.io/etci2021/) dataset from the NASA Interagency Implementation and Advanced Concepts Team\n- [x] Notebook example\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fahestevenz%2Fflood-detection-segmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fahestevenz%2Fflood-detection-segmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fahestevenz%2Fflood-detection-segmentation/lists"}