{"id":23193456,"url":"https://github.com/william-versatile/face-recognition-python","last_synced_at":"2025-04-05T07:25:38.198Z","repository":{"id":230306664,"uuid":"768938520","full_name":"William-versatile/face-recognition-python","owner":"William-versatile","description":"Face recognition by using python","archived":false,"fork":false,"pushed_at":"2024-03-08T02:25:43.000Z","size":107,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-10T15:17:06.799Z","etag":null,"topics":["python","recognition"],"latest_commit_sha":null,"homepage":"","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/William-versatile.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}},"created_at":"2024-03-08T02:25:17.000Z","updated_at":"2024-03-08T02:26:23.000Z","dependencies_parsed_at":"2024-03-29T02:33:46.713Z","dependency_job_id":"f4c07b13-0da2-47a7-88fb-7f3dfa501d0c","html_url":"https://github.com/William-versatile/face-recognition-python","commit_stats":null,"previous_names":["william-versatile/face-recognition-python"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/William-versatile%2Fface-recognition-python","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/William-versatile%2Fface-recognition-python/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/William-versatile%2Fface-recognition-python/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/William-versatile%2Fface-recognition-python/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/William-versatile","download_url":"https://codeload.github.com/William-versatile/face-recognition-python/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247302160,"owners_count":20916645,"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":["python","recognition"],"created_at":"2024-12-18T13:11:35.254Z","updated_at":"2025-04-05T07:25:38.179Z","avatar_url":"https://github.com/William-versatile.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Face Recognition based on DeepID\n\nImplementation of DeepID based on the paper \"Sun Y, Wang X, Tang X. Deep learning face representation from predicting 10,000 classes[C]//Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014: 1891-1898.\"\n\n## Dataset preparation\nLFW - refer to sklearn.dataset\n\nFacescrub - http://vintage.winklerbros.net/facescrub.html\n\nCropped only faces, separate them into train, val, and test set with ratio of 0.7, 0.1, 0.2 respectively\n\n## Current state\nOnly done face identification, working on face verification\n\n## Training\nInitially learning rate of 0.01 using exponential decay on 100000 steps/0.9 decay rate\n\nMonitor the training graph, if it stays at a loss/accuracy for a long time, initialise learning rate with 0.005 or lower (my guess on it, i think it is because it reaches a local minimum gradient, couldn't go deeper)\n\n## Reminder\n1. Small dataset will be easily overfit as there is nothing much to \"learn\" from the dataset\n\n2. Due to Internet speed and storage problem, I choose a smaller than CASIA dataset (stated in the paper), but bigger than LFW which is facescrub\n\n3. My code is in continue training state, if you want a new training, comment the \"load\" code\n\n## Performance\nTraining on LFW - maximum of 80% accuracy (only 68 classes, I choose minimum of 10 faces)\n\nTraining on Facescrub - still training, but reached 75% accuracy by the time I commit (530 classes)\n\n## Contact\n\nEmail: kamwoh@gmail.com\n\n## Reference\n\n[1]. https://github.com/RiweiChen/DeepFace\n\n[2]. https://github.com/stdcoutzyx/DeepID_FaceClassify\n\n[3]. Sun Y, Wang X, Tang X. Deep learning face representation from predicting 10,000 classes[C]//Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on. IEEE, 2014: 1891-1898.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwilliam-versatile%2Fface-recognition-python","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwilliam-versatile%2Fface-recognition-python","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwilliam-versatile%2Fface-recognition-python/lists"}