{"id":20127255,"url":"https://github.com/code2k13/starrem2k13","last_synced_at":"2025-08-17T05:05:28.483Z","repository":{"id":179784085,"uuid":"584139899","full_name":"code2k13/starrem2k13","owner":"code2k13","description":"Open-source tool for removing stars from deep sky images.","archived":false,"fork":false,"pushed_at":"2025-06-16T01:22:20.000Z","size":54072,"stargazers_count":7,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-06-16T02:19:21.019Z","etag":null,"topics":["artificial-intelligence","astrophotography","astrophotos-editor","deep-learning","gan","neural-network","pix2pix-tensorflow","python","tensorflow"],"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/code2k13.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,"zenodo":null}},"created_at":"2023-01-01T14:47:26.000Z","updated_at":"2025-06-16T01:19:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"538f9991-e1e1-4e66-9250-3b38d6565105","html_url":"https://github.com/code2k13/starrem2k13","commit_stats":null,"previous_names":["code2k13/starrem2k13"],"tags_count":16,"template":false,"template_full_name":null,"purl":"pkg:github/code2k13/starrem2k13","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code2k13%2Fstarrem2k13","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code2k13%2Fstarrem2k13/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code2k13%2Fstarrem2k13/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code2k13%2Fstarrem2k13/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/code2k13","download_url":"https://codeload.github.com/code2k13/starrem2k13/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code2k13%2Fstarrem2k13/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270807934,"owners_count":24649346,"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":"2025-08-17T02:00:09.016Z","response_time":129,"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":["artificial-intelligence","astrophotography","astrophotos-editor","deep-learning","gan","neural-network","pix2pix-tensorflow","python","tensorflow"],"created_at":"2024-11-13T20:20:00.231Z","updated_at":"2025-08-17T05:05:23.466Z","avatar_url":"https://github.com/code2k13.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Star reduction in deep sky images\n\nStarrem2k13 is a simple tool for removing stars from astronomical images. Starrem2k13 uses a GAN trained on augmented data. It's code was inspired from a [sample at Tensorflow's website](https://www.tensorflow.org/tutorials/generative/pix2pix). The training data consists of only three base images.\n\nBelow are examples of what it can do:\n\n![images/example2.png](images/example2.jpg)\n\n![images/example.png](images/example.jpg)\n\n\n# Installing\nCurrently binaries for Windows, Linux and MacOS are available in the releases section. These were created using PyInstaller. Using pre-complied binary is the recommended way of running Starrem2k13. Once you have downloaded and installed the program you can run it simply by typing the following in command prompt/terminal\n\n```shell\nstarrem2k13 image_with_stars.jpg  image_without_stars.jpg\n```\n\n## Running using Docker (if binaries don't work)\n\n```\ndocker run   -v $PWD:/usr/src/app/starrem2k13/data  \\\n-it code2k13/starrem2k13 \\\n/bin/bash -c \"./starrem2k13.py ./data/example.jpg  ./data/example_starless.jpg\"\n```\nNote that *$PWD* refers to your current working directory. In the above example it is assumed that the file *example.jpg* resides in your current working directory. This directory is mounted as a volume with the path */usr/src/app/starrem2k13/data* inside the docker container. The output image *example_starless.jpg* will also be written to same directory.\n\n\n## Running with local python installation (for geeks)\nClone the repository and navigate to the 'starrem2k13' folder. Install required packages :\n\n```shell\ngit clone https://github.com/code2k13/starrem2k13.git\ncd starrem2k13\npip install -r requirements.txt\n```\n\nAdditionally you may also have to install lfs support for git\n```shell\nsudo apt-get install git-lfs\ngit lfs pull\n```\n\u003e 📍If you run into bandwidth issues with git-lfs, you can simply download weights [from here]( https://github.com/code2k13/starrem2k13/releases/download/v1.0_weights/weights.zip) and unzip to root directory (a folder with weights will\n\u003e get created beside starrem2k13 executable. This folder contains weights required by the program).\n\nRun inference on image. \n```shell\npython starrem2k13.py image_with_stars.jpg  image_without_stars.jpg\n```\n\n\u003e Supprots greyscale and RGB images. Alpha channel (if any) in the source image is removed during processing. Gives issues on some types of TIFF files.\n\n\n## Trying out the model in a web browser\nHere is link to a online demo of star reduction created using a trained model, TFJS and ReactJS. Please use a **desktop browser** to access the demo (for memory and performance reasons). The demo runs locally inside your browser, no data outside of your computer. Here is the link to the demo : https://ashishware.com/static/star_removal/index.html\n\n![](https://ashishware.com/images/star_removal_demo1.jpg)\n\n## Training model on your images\n\nThe [notebook](train/star-removal-from-astronomical-images-with-pix2pix.ipynb) is available in the train folder.\n\nYou can also view/run it on Kaggle:\n[https://www.kaggle.com/finalepoch/star-removal-from-astronomical-images-with-pix2pix](https://www.kaggle.com/finalepoch/star-removal-from-astronomical-images-with-pix2pix)\n\n\n## Attribution\n\nThe training images used in this code were sourced from Wikimedia Commons and processed using GIMP.\n\n\n### Star cluster NGC 3572 and its surroundings\nThis image was downloaded from Wikimedia Commons and star mask was created by me using GIMP\n\nLink to the processed image: [training_data/star_map_base.png](training_data/star_map_base.png)\n\n\u003e [ESO/G. Beccari, CC BY 4.0](https://creativecommons.org/licenses/by/4.0), via Wikimedia Commons\n\nUrl: [https://commons.wikimedia.org/wiki/File:The_star_cluster_NGC_3572_and_its_dramatic_surroundings.jpg](https://commons.wikimedia.org/wiki/File:The_star_cluster_NGC_3572_and_its_dramatic_surroundings.jpg) \n\nDirect Link: [https://upload.wikimedia.org/wikipedia/commons/9/95/The_star_cluster_NGC_3572_and_its_dramatic_surroundings.jpg](https://upload.wikimedia.org/wikipedia/commons/9/95/The_star_cluster_NGC_3572_and_its_dramatic_surroundings.jpg)\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcode2k13%2Fstarrem2k13","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcode2k13%2Fstarrem2k13","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcode2k13%2Fstarrem2k13/lists"}