{"id":31615334,"url":"https://github.com/chanzuckerberg/saber","last_synced_at":"2025-10-06T11:14:39.403Z","repository":{"id":304046508,"uuid":"988563007","full_name":"chanzuckerberg/saber","owner":"chanzuckerberg","description":"Segment Organelles from Electron Microscopy Datasets with Segment-Anything 2","archived":false,"fork":false,"pushed_at":"2025-09-30T04:13:11.000Z","size":19253,"stargazers_count":5,"open_issues_count":3,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-30T06:11:34.878Z","etag":null,"topics":["computer-vision","deep-learning","segmentation"],"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/chanzuckerberg.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","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":"2025-05-22T18:24:35.000Z","updated_at":"2025-09-23T21:51:17.000Z","dependencies_parsed_at":"2025-09-30T06:18:24.078Z","dependency_job_id":null,"html_url":"https://github.com/chanzuckerberg/saber","commit_stats":null,"previous_names":["chanzuckerberg/saber"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/chanzuckerberg/saber","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanzuckerberg%2Fsaber","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanzuckerberg%2Fsaber/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanzuckerberg%2Fsaber/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanzuckerberg%2Fsaber/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chanzuckerberg","download_url":"https://codeload.github.com/chanzuckerberg/saber/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chanzuckerberg%2Fsaber/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278598805,"owners_count":26013335,"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","status":"online","status_checked_at":"2025-10-06T02:00:05.630Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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","deep-learning","segmentation"],"created_at":"2025-10-06T11:14:35.646Z","updated_at":"2025-10-06T11:14:39.395Z","avatar_url":"https://github.com/chanzuckerberg.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SABER⚔️\n\n[![License](https://img.shields.io/pypi/l/saber-em.svg?color=green)](https://github.com/chanzuckerberg/saber/blob/main/LICENSE)\n[![PyPI](https://img.shields.io/pypi/v/saber-em.svg?color=green)](https://pypi.org/project/saber-em/)\n[![Python Version](https://img.shields.io/pypi/pyversions/saber-em.svg?color=green)](https://www.python.org/)\n\n\n**S**egment **A**nything **B**ased **E**lectron tomography **R**ecognition is a robust platform designed for autonomous segmentation of organelles from cryo-electron tomography (cryo-ET) or electron microscopy (EM) datasets. \n\n## Introduction\nLeveraging foundational models, SABER enables segmentation directly from video-based training translated into effective 3D tomogram analysis. Users can utilize zero-shot inference with morphological heuristics or enhance prediction accuracy through data-driven training.\n\n## 💫 Key Features\n* 🔍 Zero-shot segmentation: Segment EM/cryo-ET data without explicit retraining, using foundational vision models.\n* 🖼️ Interactive GUI for labeling: Intuitive graphical interface for manual annotation and segmentation refinement.\n* 🧠 Expert-driven classifier training: Fine-tune segmentation results by training custom classifiers on curated annotations.\n* 🧊 3D organelle segmentation: Generate volumetric segmentation masks across tomographic slices.\n\n## 🚀 Getting Started\n\n### Installation\n\nSaber is available on PyPI and can be installed using pip:\n```bash\npip install saber-em\n```\n\n⚠️ **Note**: \n\n- By default, the GUI is not included in the base installation.\nTo enable the graphical interface for manual annotation, install with:\n```bash\npip install saber-em[gui]\n```\n- One of the current dependencies is currently not working with pip 25.1. We recommend using pip 25.2 or higher when installing saber:\n```bash\npip install --upgrade \"pip\u003e=25.2\"\n```\n\n### Basic Usage\nSABER provides a clean, scriptable command-line interface. Run the following command to view all available subcommands:\n```\nsaber --help\n```\n\n## 📚 Documentation\n\nFor detailed documentation, tutorials, CLI and API reference, visit our [documentation](http://chanzuckerberg.github.io/saber/)\n\n\n## 🤝 Contributing\n\nThis project adheres to the Contributor Covenant [code of conduct](https://github.com/chanzuckerberg/.github/blob/master/CODE_OF_CONDUCT.md).\nBy participating, you are expected to uphold this code. \nPlease report unacceptable behavior to [opensource@chanzuckerberg.com](mailto:opensource@chanzuckerberg.com).\n\n## 🔒 Security\n\nIf you believe you have found a security issue, please responsibly disclose by contacting us at security@chanzuckerberg.com.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchanzuckerberg%2Fsaber","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchanzuckerberg%2Fsaber","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchanzuckerberg%2Fsaber/lists"}