{"id":21525757,"url":"https://github.com/jakeret/unet","last_synced_at":"2025-04-07T07:18:09.938Z","repository":{"id":37215487,"uuid":"254096837","full_name":"jakeret/unet","owner":"jakeret","description":"Generic U-Net Tensorflow 2 implementation for semantic segmentation","archived":false,"fork":false,"pushed_at":"2022-12-26T21:38:41.000Z","size":7056,"stargazers_count":257,"open_issues_count":15,"forks_count":88,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-31T06:06:47.425Z","etag":null,"topics":["deep-learning","keras-tensorflow","semantic-segmentation","tensorflow"],"latest_commit_sha":null,"homepage":"https://u-net.readthedocs.io/en/latest/?badge=latest","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jakeret.png","metadata":{"files":{"readme":"README.rst","changelog":"CHANGELOG.rst","contributing":"CONTRIBUTING.rst","funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-04-08T13:33:05.000Z","updated_at":"2025-03-26T13:23:08.000Z","dependencies_parsed_at":"2023-01-31T02:00:22.521Z","dependency_job_id":null,"html_url":"https://github.com/jakeret/unet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jakeret%2Funet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jakeret%2Funet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jakeret%2Funet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jakeret%2Funet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jakeret","download_url":"https://codeload.github.com/jakeret/unet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247608160,"owners_count":20965953,"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":["deep-learning","keras-tensorflow","semantic-segmentation","tensorflow"],"created_at":"2024-11-24T01:38:19.430Z","updated_at":"2025-04-07T07:18:09.910Z","avatar_url":"https://github.com/jakeret.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"=============================\nTensorflow Unet\n=============================\n\n.. image:: https://readthedocs.org/projects/u-net/badge/?version=latest\n        :target: https://u-net.readthedocs.io/en/latest/?badge=latest\n        :alt: Documentation Status\n\n.. image:: https://travis-ci.com/jakeret/unet.svg?branch=master\n    :target: https://travis-ci.com/jakeret/unet\n\n.. image:: http://img.shields.io/badge/arXiv-1609.09077-orange.svg?style=flat\n        :target: http://arxiv.org/abs/1609.09077\n\n.. image:: https://camo.githubusercontent.com/c8e5db7a5d15b0e7c13480a0ed81db1ae2128b80/68747470733a2f2f62696e6465722e70616e67656f2e696f2f62616467655f6c6f676f2e737667\n        :target: https://mybinder.org/v2/gh/jakeret/unet/master?filepath=notebooks%2Fcicles.ipynb\n\n.. image:: https://camo.githubusercontent.com/52feade06f2fecbf006889a904d221e6a730c194/68747470733a2f2f636f6c61622e72657365617263682e676f6f676c652e636f6d2f6173736574732f636f6c61622d62616467652e737667\n        :target: https://colab.research.google.com/drive/1laPoOaGcqEBB3jTvb-pGnmDU21zwtgJB\n\nThis is a generic **U-Net** implementation as proposed by `Ronneberger et al. \u003chttps://arxiv.org/pdf/1505.04597.pdf\u003e`_ developed with **Tensorflow 2**. This project is a reimplementation of the original `tf_unet \u003chttps://github.com/jakeret/tf_unet\u003e`_.\n\nOriginally, the code was developed and used for `Radio Frequency Interference mitigation using deep convolutional neural networks \u003chttp://arxiv.org/abs/1609.09077\u003e`_ .\n\nThe network can be trained to perform image segmentation on arbitrary imaging data. Checkout the `Usage \u003chttp://u-net.readthedocs.io/en/latest/usage.html\u003e`_ section, the included `Jupyter notebooks \u003chttps://github.com/jakeret/unet/blob/master/notebooks/circles.ipynb\u003e`_  or `on Google Colab \u003chttps://colab.research.google.com/drive/1BArjvM_DiPlEfMjVRjlkz4JF2-7movLK\u003e`_ for a toy problem or the Oxford Pet Segmentation example available on `Google Colab \u003chttps://colab.research.google.com/drive/1laPoOaGcqEBB3jTvb-pGnmDU21zwtgJB\u003e`_.\n\nThe code is not tied to a specific segmentation such that it can be used in a toy problem to detect circles in a noisy image.\n\n.. image:: https://raw.githubusercontent.com/jakeret/unet/master/docs/toy_problem.png\n   :alt: Segmentation of a toy problem.\n   :align: center\n\nTo more complex application such as the detection of radio frequency interference (RFI) in radio astronomy.\n\n.. image:: https://raw.githubusercontent.com/jakeret/unet/master/docs/rfi.png\n   :alt: Segmentation of RFI in radio data.\n   :align: center\n\nOr to detect galaxies and star in wide field imaging data.\n\n.. image:: https://raw.githubusercontent.com/jakeret/unet/master/docs/galaxies.png\n   :alt: Segmentation of a galaxies.\n   :align: center\n\n\nThe architectural elements of a U-Net consist of a contracting and expanding path:\n\n.. image:: https://raw.githubusercontent.com/jakeret/unet/master/docs/unet.png\n   :alt: Unet architecture.\n   :align: center\n\n\nAs you use **unet** for your exciting discoveries, please cite the paper that describes the package::\n\n\n\t@article{akeret2017radio,\n\t  title={Radio frequency interference mitigation using deep convolutional neural networks},\n\t  author={Akeret, Joel and Chang, Chihway and Lucchi, Aurelien and Refregier, Alexandre},\n\t  journal={Astronomy and Computing},\n\t  volume={18},\n\t  pages={35--39},\n\t  year={2017},\n\t  publisher={Elsevier}\n\t}\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjakeret%2Funet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjakeret%2Funet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjakeret%2Funet/lists"}