{"id":46035136,"url":"https://github.com/electricalgorithm/hologen","last_synced_at":"2026-03-01T05:02:29.566Z","repository":{"id":323249334,"uuid":"1092625374","full_name":"electricalgorithm/hologen","owner":"electricalgorithm","description":"The HoloGen toolkit generates paired object-domain images and their inline or off-axis holograms for machine learning workflows.","archived":false,"fork":false,"pushed_at":"2026-01-31T19:18:45.000Z","size":13907,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"v1-stable","last_synced_at":"2026-02-01T07:18:46.531Z","etag":null,"topics":["dataset-generation","holography","in-line","off-axis","optics","optics-simulation","simulation"],"latest_commit_sha":null,"homepage":"","language":"Python","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/electricalgorithm.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","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":"2025-11-09T01:18:48.000Z","updated_at":"2025-11-23T11:10:35.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/electricalgorithm/hologen","commit_stats":null,"previous_names":["electricalgorithm/hologen"],"tags_count":8,"template":false,"template_full_name":null,"purl":"pkg:github/electricalgorithm/hologen","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/electricalgorithm%2Fhologen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/electricalgorithm%2Fhologen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/electricalgorithm%2Fhologen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/electricalgorithm%2Fhologen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/electricalgorithm","download_url":"https://codeload.github.com/electricalgorithm/hologen/tar.gz/refs/heads/v1-stable","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/electricalgorithm%2Fhologen/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29960261,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T01:47:18.291Z","status":"online","status_checked_at":"2026-03-01T02:00:07.437Z","response_time":124,"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":["dataset-generation","holography","in-line","off-axis","optics","optics-simulation","simulation"],"created_at":"2026-03-01T05:02:23.964Z","updated_at":"2026-03-01T05:02:24.697Z","avatar_url":"https://github.com/electricalgorithm.png","language":"Python","readme":"# HoloGen: Synthetic Hologram Dataset Toolkit\n\n[![DOI](https://zenodo.org/badge/1092625374.svg)](https://doi.org/10.5281/zenodo.17622375)\n\nThe HoloGen toolkit generates paired object-domain images and their inline or off-axis holograms for machine learning workflows.\n\n\u003e [See the first dataset (100k, 157.4GB!) generated with the HoloGen in HuggingFace 🤗](https://huggingface.co/datasets/gokhankocmarli/inline-digital-holography/)\n\n## Features\n* Binary object-domain sample generation with diverse analytic shapes\n* **Complex field support** for amplitude, phase, and mixed object types\n* Strategy-based hologram creation supporting inline and off-axis methods\n* Reconstruction pipeline for object-domain recovery from holograms\n* Dataset writer for NumPy bundles and preview imagery with multiple field representations\n* Realistic noise and aberration modeling for physically accurate simulations\n\n## Quickstart\n1. Create a virtual environment and install the package:\n\n```sh\n   python3 -m venv .venv\n   source .venv/bin/activate\n   pip install -r requirements.txt\n   pip install -e .\n```\n\n2. Generate a sample dataset:\n\n```bash\n   python scripts/generate_dataset.py\n```\n\nThe default dataset is written to the ``dataset/`` directory with both ``.npz`` tensors and PNG previews.\n\n## Configuration\nKey parameters reside in ``scripts/generate_dataset.py``. Adjust them to change:\n\n* Grid resolution and pixel pitch\n* Optical wavelength and propagation distance\n* Holography method (inline or off-axis)\n* Carrier parameters for off-axis holography\n* Noise levels and aberration coefficients (see [docs](docs/NOISE_SIMULATION.md))\n\n## Complex Field Support\nHoloGen supports complex-valued optical fields with amplitude, phase, and mixed representations. Generate phase-only objects (transparent samples), amplitude-only objects (absorbing samples), or full complex fields. Export data as intensity, amplitude, phase, or complex representations. See [docs/COMPLEX_FIELDS.md](docs/COMPLEX_FIELDS.md) for detailed documentation.\n\n#### Quick Example: Phase-Only Objects\n```bash\npython scripts/generate_dataset.py \\\n    --samples 100 \\\n    --object-type phase \\\n    --output-domain complex \\\n    --phase-shift 1.5708\n```\n\n## Noise Simulation \u0026 Realistic Modeling\nHoloGen includes comprehensive noise and aberration modeling to bridge the gap between synthetic and experimental holography. See [docs/NOISE_SIMULATION.md](docs/NOISE_SIMULATION.md) for detailed parameter explanations.\n\n#### Basic Noise Configuration\n```py\npython scripts/generate_dataset.py \\\n    --samples 100 \\\n    --output ./dataset_noisy \\\n    --method inline \\\n    --height 512 \\\n    --width 512 \\\n    --pixel-pitch 6.4e-6 \\\n    --wavelength 532e-9 \\\n    --distance 0.05 \\\n    --speckle-contrast 0.8 \\\n    --sensor-read-noise 3.0 \\\n    --sensor-shot-noise \\\n    --sensor-dark-current 0.5 \\\n    --sensor-bit-depth 12\n```\n\n## Licensing\n\nReleased under the MIT License. See ``LICENSE`` for details.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Felectricalgorithm%2Fhologen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Felectricalgorithm%2Fhologen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Felectricalgorithm%2Fhologen/lists"}