{"id":15903573,"url":"https://github.com/runningleon/albumcluster","last_synced_at":"2025-09-10T05:39:18.630Z","repository":{"id":79131744,"uuid":"324993327","full_name":"RunningLeon/AlbumCluster","owner":"RunningLeon","description":null,"archived":false,"fork":false,"pushed_at":"2021-01-08T19:27:16.000Z","size":4769,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-08T10:44:04.822Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RunningLeon.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2020-12-28T11:26:10.000Z","updated_at":"2023-02-20T23:38:12.000Z","dependencies_parsed_at":"2023-05-23T10:00:32.538Z","dependency_job_id":null,"html_url":"https://github.com/RunningLeon/AlbumCluster","commit_stats":{"total_commits":19,"total_committers":2,"mean_commits":9.5,"dds":"0.42105263157894735","last_synced_commit":"dd29fae8da4dfea7865dddf1543b0ff84cffb1da"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RunningLeon%2FAlbumCluster","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RunningLeon%2FAlbumCluster/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RunningLeon%2FAlbumCluster/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RunningLeon%2FAlbumCluster/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RunningLeon","download_url":"https://codeload.github.com/RunningLeon/AlbumCluster/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246884772,"owners_count":20849554,"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":[],"created_at":"2024-10-06T12:02:56.402Z","updated_at":"2025-04-02T20:15:43.632Z","avatar_url":"https://github.com/RunningLeon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Album Clustering\n![avatar](images/pipeline.png)\n## Brief Introduction\n\nThis repository contains a tool to cluster albums by face.\nThe main procedures are:\n\n- Input an album, which has photos of multiple people.\n- Detect all face bounding boxes and five facial landmarks using [RetinaFace](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFace).\n- Align all cropped face images using five facial landmarks.\n- Extract all 512-D face features using [insightface](https://github.com/deepinsight/insightface).\n- Cluster all face features with [Chinese Whispers](https://en.wikipedia.org/wiki/Chinese_Whispers_(clustering_method)) and output a clustered album.\n\n## How to use this tool?\n\n### Clone Repository\n\n```bash\ngit clone git@github.com:RunningLeon/AlbumCluster.git\nexport ALBUM_HOME=$(pwd)/AlbumCluster\n```\n\n### Create Environment\n\nStrongly suggest use `conda` to manage Python environment.\nIf you do not have conda on your system, please goto download and install [miniconda](https://docs.conda.io/en/latest/miniconda.html)\n\n- create conda environment\nOnce `conda` is installed, please follow steps below to create the environment.\n\n```bash\nconda create -n env python==3.7.0\nsource activate env\npip install -r requirements.txt\n```\n\n- Install mxnet-gpu\nBy defaults, there is mxnet-cpu in [requirements.txt](./requirements.txt). If you have cuda installed on your system, you can install mxnet-gpu. Supported version is from 1.2 to 1.6.\nFirst confirm the cuda version on your system, than use `pip` to install.\nExample for cuda==10.2\n\n```bash\npip install mxnet-cu102==1.6.0\n```\n\n- Compile rcnn\n\n```bash\ncd $ALBUM_HOME/AlbumCluster/app/retinaface\nmake\n```\n\n- Download models\nLink: [Baidu YunPan](https://pan.baidu.com/s/1SQHu5fHB8SGB-7bJ0WmErQ)\nCode: `fsfl`\n\nDownload `models.zip` and put it in `$AlbumCluster/models` directory.\n\n```bash\ncd $AlbumCluster/models\nunzip models.zip\n```\n\n### Run\n\n```bash\npython run.py --input ./images --output ./output\n```\n\nAfter a few minutes, results would be saved to `output` directory.\n\n## Example Results\n\n![avatar](images/clusters.png)\n## FAQs\n\n- None\n\n## References\n\n- [RetinaFace](https://github.com/deepinsight/insightface/tree/master/detection/RetinaFace)\n- [insightface](https://github.com/deepinsight/insightface)\n- [Chinese Whispers](https://blog.csdn.net/u011808673/article/details/78644485/)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frunningleon%2Falbumcluster","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frunningleon%2Falbumcluster","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frunningleon%2Falbumcluster/lists"}