{"id":23500515,"url":"https://github.com/gully/helloworldnet","last_synced_at":"2025-07-17T08:39:26.413Z","repository":{"id":72174222,"uuid":"201337933","full_name":"gully/HelloWorldNet","owner":"gully","description":"Finding new worlds from Kepler/TESS data with PyTorch-- A fork of ExoNet from Ansdell et al. 2018","archived":false,"fork":false,"pushed_at":"2019-12-19T02:46:58.000Z","size":85232,"stargazers_count":13,"open_issues_count":2,"forks_count":1,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-15T18:51:06.478Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://gitlab.com/frontierdevelopmentlab/exoplanets/exonet-pytorch","language":"Jupyter Notebook","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/gully.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}},"created_at":"2019-08-08T21:09:14.000Z","updated_at":"2025-03-06T03:52:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"d644a30b-8ef5-4ce3-be30-20b73adc8ab4","html_url":"https://github.com/gully/HelloWorldNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gully/HelloWorldNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2FHelloWorldNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2FHelloWorldNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2FHelloWorldNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2FHelloWorldNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gully","download_url":"https://codeload.github.com/gully/HelloWorldNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gully%2FHelloWorldNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265586124,"owners_count":23792858,"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":[],"created_at":"2024-12-25T06:44:30.042Z","updated_at":"2025-07-17T08:39:26.402Z","avatar_url":"https://github.com/gully.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# HelloWorldNet\n\n![Kepler Data](https://github.com/google-research/exoplanet-ml/raw/master/exoplanet-ml/astronet/docs/transit.gif)\n*fig credit: Chris Shallue*\n\nHelloWorldnet is a modified version of [Exonet](https://gitlab.com/frontierdevelopmentlab/exoplanets/exonet-pytorch), which is in turn a modified version of [Astronet](https://github.com/tensorflow/models/tree/master/research/astronet)\n\nThis work is a direct result of the [2019 PyTorch Summer Hackathon](https://info.devpost.com/pytorchmpkrules), hosted at Facebook HQ, with team members:\n\n- [Gully](https://github.com/gully)\n- [Grant](https://github.com/GrantRVD) ([twitter](https://twitter.com/usethespacebar))\n- [Humayun](https://github.com/humayun)\n\nOur goal is to apply PyTorch to improve the speed and reliability of detecting exoplanets in [lightcurve](https://imagine.gsfc.nasa.gov/features/yba/M31_velocity/lightcurve/lightcurve_more.html) data. Specifically, we're attempting to\n\n- extend Exonet and Astronet for better precision and recall\n- creating dataloaders for various data sources, such as Kepler, TESS, and K2\n- exploring model architectures to improve transfer learning between exoplanet monitoring and detection tasks\n\n### Performance Benchmark\n\n| Model | Avg. Precision |\n| --  | -- |\n|Astronet (TensorFlow) | 0.955|\n|Exonet (PyTorch) Replication| 0.969|\n|Exonet (PyTorch) Reported (Ansdell et al. (2018))| 0.980 |\n|**HelloWorldNet (PyTorch Hackathon)**| **0.977**|\n\n![Training Curves for HelloWorldNet](./graphs/Training.png)\n\n### Finding planets is a needle in a haystack problem\n\n\u003cimg width=500 src=https://keplerscience.arc.nasa.gov/images/shareable_-_kepler_-_numbers_12may2015-2_1041sq.jpeg\u003e\u003c/img\u003e\n\n\n### Neural networks can distinguish rare exoplanets from spurious astrophysical signals\n\nWe used data from the Gaia Mission Data Release 2 to improve our knowledge of the stars, making the model more accurate and precise.\n\n![PyTorch Helps](graphs/gaiaDR2_neural_network.png)\n\n\n### Training Performance\n\n![how we did](graphs/pytorch_hackathon_performance.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgully%2Fhelloworldnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgully%2Fhelloworldnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgully%2Fhelloworldnet/lists"}