{"id":13735617,"url":"https://github.com/dymaxionlabs/ap-latam","last_synced_at":"2025-05-08T11:34:00.694Z","repository":{"id":30909932,"uuid":"136063037","full_name":"dymaxionlabs/ap-latam","owner":"dymaxionlabs","description":"Detection of slums and informal settlements from satellite imagery","archived":false,"fork":false,"pushed_at":"2024-07-30T20:51:12.000Z","size":8904,"stargazers_count":35,"open_issues_count":6,"forks_count":24,"subscribers_count":7,"default_branch":"master","last_synced_at":"2024-08-04T03:05:11.994Z","etag":null,"topics":["keras","machine-learning","remote-sensing","tensorflow"],"latest_commit_sha":null,"homepage":"https://ap-latam.dymaxionlabs.com/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dymaxionlabs.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2018-06-04T17:55:10.000Z","updated_at":"2024-07-19T20:44:33.000Z","dependencies_parsed_at":"2022-09-02T06:36:52.485Z","dependency_job_id":null,"html_url":"https://github.com/dymaxionlabs/ap-latam","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fap-latam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fap-latam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fap-latam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dymaxionlabs%2Fap-latam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dymaxionlabs","download_url":"https://codeload.github.com/dymaxionlabs/ap-latam/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224727181,"owners_count":17359532,"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":["keras","machine-learning","remote-sensing","tensorflow"],"created_at":"2024-08-03T03:01:08.886Z","updated_at":"2024-11-15T03:32:28.245Z","avatar_url":"https://github.com/dymaxionlabs.png","language":"Jupyter Notebook","funding_links":[],"categories":["`Python` processing of optical imagery (non deep learning)"],"sub_categories":["Case studies / Projects"],"readme":"# AP Latam\n\n[![Build Status](https://travis-ci.org/dymaxionlabs/ap-latam.svg?branch=master)](https://travis-ci.org/dymaxionlabs/ap-latam)\n[![codecov](https://codecov.io/gh/dymaxionlabs/ap-latam/branch/master/graph/badge.svg)](https://codecov.io/gh/dymaxionlabs/ap-latam)\n[![Join the chat at https://gitter.im/dymaxionlabs/ap-latam](https://badges.gitter.im/dymaxionlabs/ap-latam.svg)](https://gitter.im/dymaxionlabs/ap-latam?utm_source=badge\u0026utm_medium=badge\u0026utm_campaign=pr-badge\u0026utm_content=badge)\n\nThis is the main repository of AP Latam project.\n\nFor more information on the website frontend, see the repository at\n[https://github.com/dymaxionlabs/ap-latam-web](https://github.com/dymaxionlabs/ap-latam-web).\n\n\n## Dependencies\n\n* Python 3+\n* GDAL\n* Proj4\n* libspatialindex\n* Dependencies for TensorFlow with GPU support\n\n\n## Install\n\n### Quick install and usage: Docker image\n\nIf you have [Docker](https://www.docker.com/community-edition) installed on\nyour machine, with NVIDIA CUDA installed and configured, you can simply pull\nour image and run the scripts for training and detection.\n\nOtherwise, follow the steps in this\n[tutorial](https://medium.com/google-cloud/jupyter-tensorflow-nvidia-gpu-docker-google-compute-engine-4a146f085f17)\nto install Docker, CUDA and `nvidia-docker`.  This has been tested on an Ubuntu\n16.04 LTS instance on Google Cloud Platform.\n\nFor all scripts you will need to mount a data volume so that the scripts can\nread the input rasters and vector files, and write the resulting vector file.\n\nIt is recommended that you first set an environment variable that points to the\ndata directory in your host machine, like this:\n\n```\nexport APLATAM_DATA=$HOME/aplatam-data\n```\n\nThen, to use any of the scripts, you would have to run them using\n`nvidia-docker` and mounting a volume to `$APLATAM_DATA` like this:\n\n```\nnvidia-docker run -ti -v $APLATAM_DATA:/data dymaxionlabs/ap-latam SCRIPT_TO_RUN [ARGS...]\n```\n\nwhere `SCRIPT_TO_RUN` is either `ap_train` or `ap_detect` and `[ARGS...]` the\ncommand line arguments of the specified script. You can run with `--help` to\nsee all available options on each script.\n\nFor example, suppose you have the following files inside the `$APLATAM_DATA`\ndirectory:\n\n* Training rasters on `images/`\n* A settlements vector file `settlements.geojson`\n\nTo prepare a dataset and train a model you would run:\n\n```\nnvidia-docker run -ti -v $APLATAM_DATA:/data dymaxionlabs/ap-latam \\\n  ap_train /data/images /data/settlements.geojson /data/dataset\n```\n\nWhen using `[nvidia-]docker run` for the first time, it will pull the image\nautomatically for you, so it is not neccessary to do `[nvidia-]docker pull`\nfirst.\n\n#### `run_with_docker.sh`\n\nYou can also use `run_with_docker.sh` to do the same:\n\n```\nexport APLATAM_DATA=$HOME/data/\n./run_with_docker.sh ap_train /data/images /data/settlements.geojson /data/dataset\n...\n```\n\n## Development\n\nFirst you will need to install the following packages.  On Debian-based distros\nrun:\n\n```\nsudo apt install libproj-dev gdal-bin build-essential libgdal-dev libspatialindex-dev python3-venv virtualenv\n```\n\nClone the repository and run `python setup.py install` to install the package\nwith its dependencies.  Add `--extras gpu` to install GPU dependencies\n(TensorFlow for GPUs).\n\nRun `make` to run tests and `make cov` to build a code coverage report. You can\nrun `make` to do both.\n\n\n## Issue tracker\n\nPlease report any bugs and enhancement ideas using the GitHub issue tracker:\n\n  https://github.com/dymaxionlabs/ap-latam/issues\n\nFeel free to also ask questions on our\n[Gitter channel](https://gitter.im/dymaxionlabs/ap-latam), or by email.\n\n\n## Help wanted\n\nAny help in testing, development, documentation and other tasks is highly\nappreciated and useful to the project.\n\nFor more details, see the file [CONTRIBUTING.md](CONTRIBUTING.md).\n\n\n## License\n\nSource code is released under a BSD-2 license.  Please refer to\n[LICENSE.md](LICENSE.md) for more information.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdymaxionlabs%2Fap-latam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdymaxionlabs%2Fap-latam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdymaxionlabs%2Fap-latam/lists"}