{"id":16224206,"url":"https://github.com/vladmandic/insightface","last_synced_at":"2025-10-24T22:32:52.342Z","repository":{"id":53260876,"uuid":"521329498","full_name":"vladmandic/insightface","owner":"vladmandic","description":"InsightFace for TFJS","archived":true,"fork":false,"pushed_at":"2022-09-18T17:04:07.000Z","size":43907,"stargazers_count":11,"open_issues_count":0,"forks_count":0,"subscribers_count":4,"default_branch":"main","last_synced_at":"2024-10-27T22:44:45.021Z","etag":null,"topics":["face-recognition","insightface","tensorflow","tfjs"],"latest_commit_sha":null,"homepage":"http://vladmandic.github.io/insightface/public","language":"TypeScript","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/vladmandic.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}},"created_at":"2022-08-04T15:59:32.000Z","updated_at":"2024-10-02T01:44:08.000Z","dependencies_parsed_at":"2023-01-18T13:30:36.277Z","dependency_job_id":null,"html_url":"https://github.com/vladmandic/insightface","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladmandic%2Finsightface","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladmandic%2Finsightface/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladmandic%2Finsightface/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vladmandic%2Finsightface/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vladmandic","download_url":"https://codeload.github.com/vladmandic/insightface/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":238043943,"owners_count":19407117,"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":["face-recognition","insightface","tensorflow","tfjs"],"created_at":"2024-10-10T12:23:15.651Z","updated_at":"2025-10-24T22:32:43.612Z","avatar_url":"https://github.com/vladmandic.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# InsightFace for TFJS\n\nTFJS port of InsightFace\n\n## Models\n\nRepository contains pretrained **TFJS graph models** for the following **InsightFace** variations  \n\n- `human-faceres`: *included for reference*, 6.7MB weights\n- `human-mobilefacenet`: *included for reference*, 5.0MB weights\n- `insightface-mobilenet-emore`: 6.7MB weights, 1.6ms avg\n- `insightface-mobilenet-swish`: 12MB weights, 3.0ms avg\n- `insightface-ghostnet-strides1`: 7.8MB weighs, 9.3ms avg\n- `insightface-ghostnet-strides2`: 7.7MB weights, 7.4ms avg\n- `insightface-efficientnet-b0`: 13MB weights, 9.8ms avg\n\n### Notes\n- Models have been quantized to **F16** for size  \n- All models take `[1, 112, 112, 3]` cropped and normalized `[0..1]` image of a face as input  \n  and produce as single float array as output which represents face embedding  \n- Performance numbers are using RTX3060  \n\n## Demo \u0026 Compare\n\nDemo app in `/src` uses `Human` library to detect and crop faces from input images before running `InsightFace` models to calculate face descriptors (embeddings)  \n\nAnd yes, you can use any other face detection method  \n\n### Sample Images\n\nGitHub repository is void of sample images, beforing running demo place any number of images of any resolution containing one or more faces into `/assets/samples/`\n\n## Sample Screenshot\n\n![screenshot](assets/screenshot.jpg)\n### Run\n\nUse built-in dev server to compile sources and start a web server:\n\n\u003e npm run dev\n\n## Credits\n\n- Original implementation: \u003chttps://github.com/deepinsight/insightface\u003e\n- Keras port: \u003chttps://github.com/leondgarse/Keras_insightface\u003e\n\n## TBD\n\n- Optimize `similarity` in (%) from raw `distance`\n- Find best `face.scale` per model\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvladmandic%2Finsightface","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvladmandic%2Finsightface","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvladmandic%2Finsightface/lists"}