{"id":13641546,"url":"https://github.com/Deyht/CIANNA","last_synced_at":"2025-04-20T11:31:13.889Z","repository":{"id":199479418,"uuid":"204141825","full_name":"Deyht/CIANNA","owner":"Deyht","description":"Convolutional Interactive Artificial Neural Networks by/for Astrophysicists","archived":false,"fork":false,"pushed_at":"2024-04-16T09:41:25.000Z","size":59532,"stargazers_count":24,"open_issues_count":0,"forks_count":0,"subscribers_count":6,"default_branch":"CIANNA","last_synced_at":"2024-04-16T13:22:45.504Z","etag":null,"topics":["astronomy","astrophysics","convolutional-neural-networks","cuda","deep-learning","deep-neural-networks","gpu","machine-learning","ml","neural-network","object-detection","yolo"],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Deyht.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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}},"created_at":"2019-08-24T10:21:21.000Z","updated_at":"2024-04-23T12:56:16.702Z","dependencies_parsed_at":null,"dependency_job_id":"5d933bc2-9258-4570-bdd4-763883a49042","html_url":"https://github.com/Deyht/CIANNA","commit_stats":null,"previous_names":["deyht/cianna"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deyht%2FCIANNA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deyht%2FCIANNA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deyht%2FCIANNA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Deyht%2FCIANNA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Deyht","download_url":"https://codeload.github.com/Deyht/CIANNA/tar.gz/refs/heads/CIANNA","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223827388,"owners_count":17209785,"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","astrophysics","convolutional-neural-networks","cuda","deep-learning","deep-neural-networks","gpu","machine-learning","ml","neural-network","object-detection","yolo"],"created_at":"2024-08-02T01:01:21.671Z","updated_at":"2025-04-20T11:31:13.853Z","avatar_url":"https://github.com/Deyht.png","language":"C","funding_links":[],"categories":["Other Versions of YOLO"],"sub_categories":[],"readme":"\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/90708962-e7ed-4dcb-88e7-f832a04753ff\" alt=\"cianna_logo\" width=\"80%\"/\u003e\n\u003c/p\u003e\n*Logo made by \u0026copy; Sarah E. Anderson*  \n\n\u0026nbsp;\n\n\u003cp align=\"left\"\u003e\n\t\u003ca href=\"https://github.com/Deyht/CIANNA/releases\" alt=\"Release-version\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/Latest%20release-1.0-green\" /\u003e\u003c/a\u003e\n\t\u003ca href=\"https://github.com/Deyht/CIANNA/\" alt=\"Current-version\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/Current%20version-1.0-green\" /\u003e\u003c/a\u003e\n\t\u003ca href=\"https://github.com/Deyht/CIANNA/wiki\" alt=\"Wiki-read\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/Wiki-Read-blue\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"left\"\u003e\n\t\u003ca href=\"https://doi.org/10.5281/zenodo.12806324\" alt=\"DOI-ref\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/DOI-10.5281/zenodo.12806324-blue\" /\u003e\u003c/a\u003e\n\t\u003ca href=\"https://ascl.net/2501.005\" alt=\"ascl-id\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/ascl-2501.005-blue.svg?colorB=262255\" alt=\"ascl:2501.005\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"left\"\u003e\n\u003ca href=\"https://github.com/Deyht/CIANNA/wiki/2)-Installation-instructions#dockerfile-installer\" alt=\"Docker\"\u003e\n\t\t\u003cimg src=\"https://img.shields.io/badge/docker-%230db7ed.svg?logo=docker\u0026logoColor=white\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n### The first CIANNA release (V-1.0) is here! Check the [release page](https://github.com/Deyht/CIANNA/releases)!\n\n## CIANNA - Convolutional Interactive Artificial Neural Networks by/for Astrophysicists\n\nCIANNA is a general-purpose deep learning framework primarily developed and used for astronomical data analysis. Functionalities and optimizations are added based on relevance for astrophysical problem-solving. CIANNA can be used to build and train large neural network models for various tasks and is provided with a high-level Python interface (similar to keras, pytorch, etc.). One of the specificities of CIANNA is its custom implementation of a YOLO-inspired object detector used in the context of galaxy detection in 2D or 3D radio-astronomical data products. The framework is fully GPU-accelerated through low-level CUDA programming.\n\n**Development team**  \n[David Cornu](https://vm-weblerma.obspm.fr/dcornu/) - creator and lead dev, post-doc researcher, AI Fellow PR[AI]RIE, FR - LUX / Observatoire de Paris, PSL  \nGregory Sainton - dev, AI Research engineer, FR - LUX / Observatoire de Paris  \nAristide Doussot - dev, HPC Research engineer, FR - LUX / Observatoire de Paris\n\nPreferred contact point: david.cornu@observatoiredeparis.psl.eu\n\nSee Copyright \u0026copy; and [License](#License) terms at the end.\n\n\u0026nbsp;\n\n## CIANNA application examples\n\nPython scripts and Google-Colab-compatible notebooks are available under the [examples](https://github.com/Deyht/CIANNA/tree/CIANNA/examples) directory for most of the following examples.\n\n| \u0026#160;\u0026#160;\u0026#160;\u0026#160;\u0026#160;\u0026#160; Description\u0026#160;-\u0026#160;Dataset \u0026#160;\u0026#160;\u0026#160;\u0026#160;\u0026#160;\u0026#160;  |  Visualization | Animation\u0026#160;or\u0026#160;real\u0026#160;time |\n| :---:  | :---:   | :---: |\n| *** | \u003cbr\u003e ***Classical computer vision examples*** \u003cbr\u003e \u0026#160;| *** |\n| **Image\u0026#160;classification \u003cbr\u003e MNIST** \u003cbr\u003e Top-1 accuracy ~99.3% \u003cbr\u003e *Net. ~LeNet-5* \u003cbr\u003e *630000 ips \\@28p** \u003cbr\u003e [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/MNIST/mnist_train_notebook.ipynb)       | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/802f5772-da5f-415b-8e49-cea75fba510b\" alt=\"mnist_expl\"/\u003e |\n| **Image\u0026#160;classification \u003cbr\u003e Imagenet - 1000 classes** \u003cbr\u003e Top-1 acc ~74.7% \u003cbr\u003e Top-5 acc ~91.7%  \u003cbr\u003e *Net. ~Darknet19* \u003cbr\u003e *740 ips \\@448p** \u003cbr\u003e [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/ImageNET/imagenet_pred_notebook.ipynb) | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/b7adde2f-e435-4bc1-907d-fc8052e58409\" alt=\"imagenet_expl\"\u003e | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/81b60e1e-79c9-4861-b212-791dca33c8dc\" alt=\"imagenet_vid\" width=\"100%\"/\u003e |\n| **Object\u0026#160;detection \u003cbr\u003e COCO - 1000 classes** \u003cbr\u003e mAP\\@50 ~40.1% \u003cbr\u003e COCO-mAP ~21.9% \u003cbr\u003e *Net. ~Darknet19* \u003cbr\u003e *690 ips \\@416p** \u003cbr\u003e [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/COCO/coco_pred_notebook.ipynb) | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/98ab135d-bba8-4f33-9d5d-46b0e095904e\" alt=\"coco_expl\"\u003e | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/b1948394-597d-44aa-aa9c-602783ce55f6\" alt=\"coco_vid\" width=\"100%\"/\u003e \u003cbr\u003e *Real-time on a laptop GPU* |\n| *** | \u003cbr\u003e ***Astronomical dataset examples*** \u003cbr\u003e \u0026#160;| *** |\n| **Source\u0026#160;detection \u003cbr\u003e SKA SDC1 \u003cbr\u003e 2D continuum** \u003cbr\u003e 560MHz - 1000h \u003cbr\u003e score 479372 pts \u003cbr\u003e *Net. 17 conv. layers* \u003cbr\u003e *500 ips \\@512p** \u003cbr\u003e [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Deyht/CIANNA/blob/CIANNA/examples/SKAO_SDC1/sdc1_pred_notebook.ipynb) \u003cbr\u003e [![DOI](https://zenodo.org/badge/doi/10.1051/0004-6361/202449548.svg)](https://ui.adsabs.harvard.edu/abs/2024A%26A...690A.211C/abstract) | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/a96112ba-0399-45b6-9804-533c921eb3a2\" alt=\"apparent_flux_distribution\" width=\"90%\"/\u003e | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/10a31010-263b-4d97-887f-733b726f284e\" alt=\"galmap_vid\" width=\"75%\"/\u003e \u003cbr\u003e *Not real-time here, only animated* |\n| **Profile\u0026#160;regression \u003cbr\u003e 3D Galactic extinction mapping** \u003cbr\u003e *Net. [C5x5.12-P2-{D3072}x2-D2048-D128]* \u003cbr\u003e *120000 ips \\@64p**\u003cbr\u003e [![DOI](https://zenodo.org/badge/doi/10.48550/arXiv.2201.05571.svg)](https://ui.adsabs.harvard.edu/abs/2022arXiv220105571C/abstract) | \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/e3987887-8553-4cea-85e3-239112e6a74a\" alt=\"galmap_polar_map_disc\" width=\"70%\"/\u003e \u003cbr\u003e *Face-on view of the galactic plane in a 45° \"cone\" toward the Carina arm (derived from the 3D map)* | *Per LOS prediction examples* \u003cbr\u003e \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/67a4be8e-8de0-4aa9-9659-f77c3fe9f5bb\" alt=\"galmap_vid\" width=\"100%\"/\u003e \u003cbr\u003e \u003cbr\u003e *Integrated extinction skyview* \u003cbr\u003e \u003cimg src=\"https://github.com/Deyht/CIANNA/assets/21009408/797a895c-fd41-4fbc-8f57-6e9a231d59fa\" alt=\"integrated_ext_map\" width=\"100%\"/\u003e | \n| **Fake\u0026#160;galaxy\u0026#160;generation \u003cbr\u003e Based on galaxy zoo 2 \u003cbr\u003e Cascaded DDPM** \u003cbr\u003e *Ensemble of U-Nets* \u003cbr\u003e *~40M param.* \u003cbr\u003e *A few ips @192p** \u003cbr\u003e *Made with the dev-exp branch of CIANNA, unavailable ATM* | \u003cimg src=\"https://github.com/user-attachments/assets/a0d98fa7-74a2-439f-b0ee-2821a88d069c\" alt=\"cascaded_scheme_illust\" width=\"100%\"/\u003e \u003cbr\u003e *Cascading pipeline with 3 DDPM models* | *Generated examples* \u003cbr\u003e \u003cimg src=\"https://github.com/user-attachments/assets/e1617c98-6460-46c7-aa24-2a8772c66871\" alt=\"gen_real_galaxy_comp\" width=\"100%\"/\u003e |\n\n**Images (or Inputs) per second (ips) are given for an RTX 4090 GPU in inference using FP16C_FP32A mixed-precision at the specified resolution and with maximum batch size to saturate performances*.\n\n\n\u0026nbsp;\n\n###\n\n## Installation\n\n#### \n\nPlease take a look at the [system requirements](https://github.com/Deyht/CIANNA/wiki/1\\)-System-Requirements) and the [installation instructions](https://github.com/Deyht/CIANNA/wiki/2\\)-Installation-instructions) wiki pages.  \n=\u003e A complete **step-by-step installation guide** of CIANNA and its dependencies from a fresh Ubuntu 20.04 is accessible [here](https://github.com/Deyht/CIANNA/wiki/Step-by-step-installation-guide-\\(Ubuntu-20.04\\)).\n\n\u0026nbsp;\n\n## How to use\n\nPlease read the [How to use](https://github.com/Deyht/CIANNA/wiki/3\\)-How-to-use-(Python-interface)) Wiki page for a minimalistic tour of CIANNA capabilities on a simple example script and dataset.  \nA full description of all the Python interface functions is available as an [API documentation](https://github.com/Deyht/CIANNA/wiki/4\\)-Interface-API-documentation) page on the Wiki.  \nPlease also consider consulting the [Step-by-step installation guide](https://github.com/Deyht/CIANNA/wiki/Step-by-step-installation-guide-\\(Ubuntu-20.04\\)) to verify everything was installed correctly.  \nSeveral Python scripts and notebooks are provided as [examples](https://github.com/Deyht/CIANNA/tree/CIANNA/examples) for different datasets and applications.\n\n\n\u0026nbsp;\n\n\n## Publications\n\nList of known [publications](https://github.com/Deyht/CIANNA/wiki/Related-publications) that make use or directly refer to the CIANNA framework.\n\n####\n\n\n## Preferred citation method\n\nWhen referring to a specific functionality or application, feel free to cite the relevant publication.\nIn all cases, if your work makes use of any version of CIANNA, please cite the non-version-specific DOI from Zenodo [10.5281/zenodo.12806324](https://doi.org/10.5281/zenodo.12806324).\n\n####\n\n\u0026nbsp;\n\n\n###########################################################################\n\n## License\n\nThese files are Copyright \u0026copy; 2024 [David Cornu](https://vm-weblerma.obspm.fr/dcornu/), but released under the [Apache2 License](https://github.com/Deyht/CIANNA/blob/master/LICENSE.md).\n\n\u0026nbsp;\n\n#### Contributor License Agreement\n*While you are free to duplicate and modify this repository under the Apache2 License above, by being allowed to submit a contribution to this repository, you agree to the following terms:*\n\n- *You grant to the present CIANNA framework (and its Author) your copyright license to reproduce and distribute your contributions and such derivative works.*\n\n- *To the fullest extent permitted, you agree not to assert all of your \"moral rights\" in or relating to your contributions to the benefit of the present CIANNA framework.*\n\n- *Your contribution was created in whole or in part by you and you have the right to submit it under the open source license indicated in the LICENSE file; or the contribution is based upon previous work that, to the best of your knowledge, is covered under an appropriate open source license and you have the right to submit that work with modifications.*\n\n\n\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDeyht%2FCIANNA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FDeyht%2FCIANNA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FDeyht%2FCIANNA/lists"}