{"id":15664528,"url":"https://github.com/dmitryduev/braai","last_synced_at":"2025-07-12T18:32:48.798Z","repository":{"id":39737237,"uuid":"192021502","full_name":"dmitryduev/braai","owner":"dmitryduev","description":"braai [Bogus/Real Adversarial AI]: Real-bogus astrophysical event classification for the Zwicky Transient Facility (ZTF) using deep learning","archived":false,"fork":false,"pushed_at":"2023-10-30T22:24:25.000Z","size":19754,"stargazers_count":19,"open_issues_count":4,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-20T05:49:31.738Z","etag":null,"topics":["astronomy","deep-learning","ztf"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dmitryduev.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2019-06-15T00:58:59.000Z","updated_at":"2025-04-02T06:42:07.000Z","dependencies_parsed_at":"2024-10-23T08:56:54.580Z","dependency_job_id":"9f42bb5f-7e5e-41d3-9d38-fd7341ee8cb7","html_url":"https://github.com/dmitryduev/braai","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dmitryduev/braai","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmitryduev%2Fbraai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmitryduev%2Fbraai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmitryduev%2Fbraai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmitryduev%2Fbraai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dmitryduev","download_url":"https://codeload.github.com/dmitryduev/braai/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmitryduev%2Fbraai/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265032991,"owners_count":23700916,"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":["astronomy","deep-learning","ztf"],"created_at":"2024-10-03T13:43:01.507Z","updated_at":"2025-07-12T18:32:48.733Z","avatar_url":"https://github.com/dmitryduev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# `braai` \\[Bogus/Real Adversarial AI\\]\n## Real-bogus classification for the Zwicky Transient Facility using deep learning\n\nEfficient automated detection of flux-transient, reoccurring flux-variable, and moving objects \nis increasingly important for large-scale astronomical surveys. `braai` is a convolutional-neural-network, \ndeep-learning real/bogus classifier designed to separate genuine astrophysical events and objects \nfrom false positive, or bogus, detections in the data of the [Zwicky Transient Facilty (ZTF)](https://ztf.caltech.edu), \na new robotic time-domain survey currently in operation at the Palomar Observatory in California, USA.\n`braai` demonstrates a state-of-the-art performance as quantified by \nits low false negative and false positive rates.\n\nFor details, please see [Duev et al. 2019, MNRAS, 489 (3), 3582-3590](https://academic.oup.com/mnras/article/489/3/3582/5554758).\n\n[arXiv:1907.11259](https://arxiv.org/pdf/1907.11259.pdf)\n\n### `braai` architecture\n\n![](doc/fig-braai.png)\n\n### Dataset\n\ntodo: plots  \n\n### Classifier performance\n\n![](doc/fig-perf_d6_m7.png)\n\n### Use `braai`\n\nSee [this jupyter notebook](https://github.com/dmitryduev/braai/blob/master/nb/braai_run.ipynb)\n\n#### Edge TPU\n\n### Transfer learning with `braai`\n\n#### Jupyter/Colab\n\nSee [this jupyter notebook](https://github.com/dmitryduev/braai/blob/master/nb/braai_tl.ipynb), or \n[![Open In Google Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/dmitryduev/braai/blob/master/nb/braai_tl.ipynb)\n\n### Train your own `braai`\n\n#### Jupyter/Colab\n\nSee [this jupyter notebook](https://github.com/dmitryduev/braai/blob/master/nb/braai_train.ipynb), or \n[![Open In Google Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/dmitryduev/braai/blob/master/nb/braai_train.ipynb)\n\n#### Docker\n\nBuild and launch the app container:\n```bash\n# without GPU support:\ndocker build --rm -t braai:cpu -f Dockerfile .\n# with GPU support (requires nvidia-docker):\ndocker build --rm -t braai:gpu -f gpu.Dockerfile .\n\n# run:\n# without GPU support:\ndocker run -it --rm --name braai -v /path/to/store/data:/data braai:cpu\n# with GPU support (requires nvidia-docker) exposing the first GPU:\ndocker run --runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=0 -it --rm --name braai -v /path/to/store/data:/data braai:gpu\n\n```\n\n---\n\nTrain `braai`:\n\n```bash\npython /app/braai.py --t_stamp 20190614_003916 --model VGG6 --epochs 200 --patience 50 --batch_size 64 --verbose\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmitryduev%2Fbraai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdmitryduev%2Fbraai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdmitryduev%2Fbraai/lists"}