{"id":23112973,"url":"https://github.com/subpic/koniq","last_synced_at":"2025-06-14T06:33:56.799Z","repository":{"id":193251629,"uuid":"205844317","full_name":"subpic/koniq","owner":"subpic","description":"KonIQ-10k Deep Learning Models","archived":false,"fork":false,"pushed_at":"2021-09-29T14:22:37.000Z","size":571,"stargazers_count":127,"open_issues_count":8,"forks_count":22,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-04T16:53:40.834Z","etag":null,"topics":["image-quality-assessment"],"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/subpic.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}},"created_at":"2019-09-02T11:41:53.000Z","updated_at":"2025-03-26T13:23:18.000Z","dependencies_parsed_at":null,"dependency_job_id":"f89d6641-f2c1-415f-b178-dc8e52f61bb6","html_url":"https://github.com/subpic/koniq","commit_stats":null,"previous_names":["subpic/koniq"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/subpic/koniq","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subpic%2Fkoniq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subpic%2Fkoniq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subpic%2Fkoniq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subpic%2Fkoniq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/subpic","download_url":"https://codeload.github.com/subpic/koniq/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/subpic%2Fkoniq/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259774597,"owners_count":22909163,"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":["image-quality-assessment"],"created_at":"2024-12-17T02:21:16.335Z","updated_at":"2025-06-14T06:33:56.775Z","avatar_url":"https://github.com/subpic.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## NR-IQA models trained on the KonIQ-10k dataset\n\nThis is part of the code for the paper [\"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment\"](https://arxiv.org/abs/1910.06180). The included Python 2.7 notebooks rely on the [kutils library](https://github.com/subpic/kutils). The Google colab requires the [ku library](https://github.com/subpic/ku). Project data is available for download from [osf.io](https://osf.io/hcsdy/). \n\nTo quickly  try out the `Koncept512` model:\n```\npip install koncept\n```\n\nPlease cite the following paper if you use the code or package:\n```\n@article{koniq10k,\nauthor={V. {Hosu} and H. {Lin} and T. {Sziranyi} and D. {Saupe}},\njournal={IEEE Transactions on Image Processing},\ntitle={KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment},\nyear={2020},\nvolume={29},\npages={4041-4056}}\n```\n\n## Overview\n\nGoogle colab notebook, Python 3 compatible:\n\n**[koncept512_train_test_py3_with_kuti.ipynb](https://github.com/subpic/koniq/blob/master/koncept512_train_test_py3_with_kuti.ipynb)** *(updated Sept 2021)*\n- Download KonIQ-10k dataset, train the KonCept512 model and test it\n- Load a pre-trained KonCept512 model, and use it to predict the quality of an image\n\nPython 2.7 notebooks:\n\n**[train_koncept512.ipynb](https://github.com/subpic/koniq/blob/master/train_koncept512.ipynb), [train_koncept224.ipynb](https://github.com/subpic/koniq/blob/master/train_koncept224.ipynb)**:\n\n- Training and testing code for the KonCept512 and KonCept224 model (on KonIQ-10k).\n- Ready-trained model weights for [KonCept512](https://osf.io/uznf8/download) and [KonCept224](https://osf.io/cxtyp/download).\n\n**[train_deeprn.ipynb](https://github.com/subpic/koniq/blob/master/train_deeprn.ipynb)**\n\n- Reimplementation of the [DeepRN](https://www.uni-konstanz.de/mmsp/pubsys/publishedFiles/VaSaSz18.pdf) model trained on KonIQ-10k, following the advice of the original author, Domonkos Varga.\n- Re-trained model weights (on SPP features) are available [here](https://osf.io/avyd5/download).\n- The features extracted from KonIQ-10k are available [here](https://osf.io/y6brn/download).\n\n**[metadata/koniq10k_distributions_sets.csv](https://github.com/subpic/koniq/blob/master/metadata/koniq10k_distributions_sets.csv)**\n\n- Contains image file names, scores, and train/validation/test split assignment (random).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsubpic%2Fkoniq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsubpic%2Fkoniq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsubpic%2Fkoniq/lists"}