{"id":16465062,"url":"https://github.com/ghaiszaher/foggy-cyclegan","last_synced_at":"2025-09-03T08:36:28.288Z","repository":{"id":254695799,"uuid":"245259491","full_name":"ghaiszaher/Foggy-CycleGAN","owner":"ghaiszaher","description":"Fog Simulation using Generative Adversarial Networks (GAN). This code is the implementation of the master thesis Simulating Weather Conditions on Digital Images. It uses a modified CycleGAN model to synthesize fog on clear images.","archived":false,"fork":false,"pushed_at":"2025-03-11T17:11:26.000Z","size":70432,"stargazers_count":81,"open_issues_count":2,"forks_count":15,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-19T23:05:25.139Z","etag":null,"topics":["cyclegan","cyclegan-tensorflow","deep-learning","dissertation","fog","gan","generative-adversarial-network","image-processing","msc-thesis","simulating-weather-conditions"],"latest_commit_sha":null,"homepage":"http://ghaiszaher.me/Foggy-CycleGAN/","language":"Python","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/ghaiszaher.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":"2020-03-05T20:19:11.000Z","updated_at":"2025-05-17T08:28:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"968eca0a-7a0f-4aef-8a03-dfe08f181e43","html_url":"https://github.com/ghaiszaher/Foggy-CycleGAN","commit_stats":{"total_commits":203,"total_committers":2,"mean_commits":101.5,"dds":"0.014778325123152691","last_synced_commit":"a6cee167e6aaeb47836017a373271fa4e12ce856"},"previous_names":["ghaiszaher/foggy-cyclegan"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ghaiszaher/Foggy-CycleGAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ghaiszaher%2FFoggy-CycleGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ghaiszaher%2FFoggy-CycleGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ghaiszaher%2FFoggy-CycleGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ghaiszaher%2FFoggy-CycleGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ghaiszaher","download_url":"https://codeload.github.com/ghaiszaher/Foggy-CycleGAN/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ghaiszaher%2FFoggy-CycleGAN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273415254,"owners_count":25101593,"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":"2025-09-03T02:00:09.631Z","response_time":76,"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":["cyclegan","cyclegan-tensorflow","deep-learning","dissertation","fog","gan","generative-adversarial-network","image-processing","msc-thesis","simulating-weather-conditions"],"created_at":"2024-10-11T11:32:02.877Z","updated_at":"2025-09-03T08:36:28.243Z","avatar_url":"https://github.com/ghaiszaher.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003e [!NOTE]  \n\u003e November 2024: New Pre-trained Models are available, check the [Pre-trained Models](#pre-trained-models) section.\n\n# Foggy-CycleGAN\n\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"images/banner-cropped-rnd.png\"\u003e\n\u003c/p\u003e\n\nThis project is the implementation for my Computer Science MSc thesis in the University of Debrecen.\n\nDissertation: \n\u003ca href=\"./dissertation/Simulating%20Weather%20Conditions%20on%20Digital%20Images%20-%20Final.pdf\" target=\"_blank\"\u003e[PDF] Simulating Weather Conditions on Digital Images\u003c/a\u003e (Debrecen, 2020).\n\n# Table of Content\n- [Description](#description)\n- [Code](#code)\n- [Notebook](#notebook-)\n- [Results (2020)](#results-2020)\n- [Pre-trained Models](#pre-trained-models)\n- [Results (2024)](#results-2024)\n- [2024-11-17-rev1-000 Test Notebook](#2024-11-17-rev1-000-test-notebook-)\n\n## Description\n**Foggy-CycleGAN** is a\nA Jupyter Notebook file \u003ca href=\"https://github.com/ghaiszaher/Foggy-CycleGAN/blob/master/Foggy_CycleGAN.ipynb\" target=\"_blank\"\u003eFoggy_CycleGAN.ipynb\u003c/a\u003e is available in the repository.\n\n## Code\nThe full source code is available under GPL-3.0 License in my Github repository \u003ca href=\"https://github.com/ghaiszaher/Foggy-CycleGAN\" target=\"_blank\"\u003eghaiszaher/Foggy-CycleGAN\u003c/a\u003e\n\n## Notebook \u003ca href=\"https://colab.research.google.com/github/ghaiszaher/Foggy-CycleGAN/blob/master/Foggy_CycleGAN.ipynb\" target=\"_blank\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/\u003e\u003c/a\u003e\nA Jupyter Notebook file \u003ca href=\"./Foggy_CycleGAN.ipynb\" target=\"_blank\"\u003eFoggy_CycleGAN.ipynb\u003c/a\u003e is available in the repository.\n\n## Results (2020)\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"images/results/2020-06/result-animated-01.gif\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"images/results/2020-06/result-sample-0.2.jpg\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"images/results/2020-06/result-sample-0.3.jpg\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n \u003cimg src=\"images/results/2020-06/result-sample-0.25.jpg\"\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\u0026copy; Ghais Zaher 2020\n\u003c/div\u003e\n\n## Pre-trained Models\nAs legacy pre-trained models are no longer compatible with newer Keras/Tensorflow versions, I have retrained the model and made the new weights available to download.\n\nEach of the following models was trained in Google Colab using the same dataset, the parameters for building the models and number of trained epochs are a bit different:\n\u003cdiv align=\"center\"\u003e\n\n\u003ctable align=\"center\"\u003e\n  \u003cthead\u003e\n    \u003ctr\u003e\n      \u003cth\u003eModel\u003c/th\u003e\n      \u003cth\u003eTrained Epochs\u003c/th\u003e\n      \u003cth\u003eConfig\u003c/th\u003e\n    \u003c/tr\u003e\n  \u003c/thead\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003ca href=\"https://drive.google.com/drive/folders/1QKsiaGkMFvtGcp072IG57MfY1o_D-L3k?usp=sharing\"\u003e2020-06 (legacy)\u003c/a\u003e\u003c/td\u003e\n      \u003ctd\u003e145\u003c/td\u003e\n      \u003ctd\u003e\n        use_transmission_map=False\u003cbr\u003e\n        use_gauss_filter=False\u003cbr\u003e\n        use_resize_conv=False\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003ca href=\"https://drive.google.com/drive/folders/1--W53NNrVxS5pvrf8jDKCRmg4h4vD5lx?usp=sharing\"\u003e2024-11-17-rev1-000\u003c/a\u003e\u003c/td\u003e\n      \u003ctd\u003e522\u003c/td\u003e\n      \u003ctd\u003e\n        use_transmission_map=False\u003cbr\u003e\n        use_gauss_filter=False\u003cbr\u003e\n        use_resize_conv=False\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003ca href=\"https://drive.google.com/drive/folders/1rQ7jmsv63uv6v45IVZmZ8w9CVktqJAfn?usp=sharing\"\u003e2024-11-17-rev2-110\u003c/a\u003e\u003c/td\u003e\n      \u003ctd\u003e100\u003c/td\u003e\n      \u003ctd\u003e\n        use_transmission_map=True\u003cbr\u003e\n        use_gauss_filter=True\u003cbr\u003e\n        use_resize_conv=False\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003ca href=\"https://drive.google.com/drive/folders/1-0-z7KTMXTrwwUdeJtkUOBCWkwD6behO?usp=sharing\"\u003e2024-11-17-rev3-111\u003c/a\u003e\u003c/td\u003e\n      \u003ctd\u003e103\u003c/td\u003e\n      \u003ctd\u003e\n        use_transmission_map=True\u003cbr\u003e\n        use_gauss_filter=True\u003cbr\u003e\n        use_resize_conv=True\n      \u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003ca href=\"https://drive.google.com/drive/folders/1hDxJtU0agbnPO2XrrPo26RQJKOePa6WX?usp=sharing\"\u003e2024-11-17-rev4-001\u003c/a\u003e\u003c/td\u003e\n      \u003ctd\u003e39\u003c/td\u003e\n      \u003ctd\u003e\n        use_transmission_map=False\u003cbr\u003e\n        use_gauss_filter=False\u003cbr\u003e\n        use_resize_conv=True\n      \u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\n## Results (2024)\nThe results of the new models are similar to the previous ones, here are some samples:\n\u003cdiv align=\"center\"\u003e\n\n\u003ctable align=\"center\"\u003e\n  \u003cthead\u003e\n    \u003ctr\u003e\n      \u003cth\u003eClear\u003c/th\u003e\n      \u003cth\u003e2024-11-17-rev1-000\u003c/th\u003e\n      \u003cth\u003e2024-11-17-rev2-110\u003c/th\u003e\n      \u003cth\u003e2024-11-17-rev3-111\u003c/th\u003e\n      \u003cth\u003e2024-11-17-rev4-001\u003c/th\u003e\n    \u003c/tr\u003e\n  \u003c/thead\u003e\n  \u003ctbody\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/clear/sample1.jpg\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev1-000/sample1.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev2-110/sample1.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev3-111/sample1.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev4-001/sample1.gif\"\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/clear/sample2.jpg\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev1-000/sample2.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev2-110/sample2.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev3-111/sample2.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev4-001/sample2.gif\"\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/clear/sample3.jpg\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev1-000/sample3.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev2-110/sample3.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev3-111/sample3.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev4-001/sample3.gif\"\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/clear/sample4.jpg\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev1-000/sample4.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev2-110/sample4.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev3-111/sample4.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev4-001/sample4.gif\"\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n    \u003ctr\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/clear/sample5.jpg\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev1-000/sample5.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev2-110/sample5.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev3-111/sample5.gif\"\u003e\u003c/td\u003e\n      \u003ctd\u003e\u003cimg src=\"images/results/2024-11-17/rev4-001/sample5.gif\"\u003e\u003c/td\u003e\n    \u003c/tr\u003e\n  \u003c/tbody\u003e\n\u003c/table\u003e\n\u003c/div\u003e\n\n## 2024-11-17-rev1-000 Test Notebook \u003ca href=\"https://colab.research.google.com/github/ghaiszaher/Foggy-CycleGAN/blob/master/2024-11-17-rev1-000-test.ipynb\" target=\"_blank\"\u003e\u003cimg src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/\u003e\u003c/a\u003e\nA Jupyter Notebook file \u003ca href=\"https://github.com/ghaiszaher/Foggy-CycleGAN/blob/master/2024-11-17-rev1-000-test.ipynb\" target=\"_blank\"\u003e2024-11-17-rev1-000-test.ipynb\u003c/a\u003e is available in the repository to test the 2024-11-17-rev1-000 model.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fghaiszaher%2Ffoggy-cyclegan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fghaiszaher%2Ffoggy-cyclegan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fghaiszaher%2Ffoggy-cyclegan/lists"}