{"id":34129981,"url":"https://github.com/dev6699/face","last_synced_at":"2026-03-12T19:16:48.748Z","repository":{"id":247012112,"uuid":"823090728","full_name":"dev6699/face","owner":"dev6699","description":"A collection of Face AI models","archived":false,"fork":false,"pushed_at":"2024-07-09T02:29:30.000Z","size":3429,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-07-09T05:55:44.079Z","etag":null,"topics":["face-detection","face-recognition","triton-inference-server"],"latest_commit_sha":null,"homepage":"","language":"Go","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/dev6699.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}},"created_at":"2024-07-02T12:05:16.000Z","updated_at":"2024-07-09T02:29:33.000Z","dependencies_parsed_at":"2024-07-09T06:06:09.204Z","dependency_job_id":null,"html_url":"https://github.com/dev6699/face","commit_stats":null,"previous_names":["dev6699/face"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dev6699/face","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev6699%2Fface","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev6699%2Fface/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev6699%2Fface/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev6699%2Fface/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dev6699","download_url":"https://codeload.github.com/dev6699/face/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dev6699%2Fface/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30439658,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-12T14:34:45.044Z","status":"ssl_error","status_checked_at":"2026-03-12T14:09:33.793Z","response_time":114,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["face-detection","face-recognition","triton-inference-server"],"created_at":"2025-12-15T00:19:10.529Z","updated_at":"2026-03-12T19:16:48.740Z","avatar_url":"https://github.com/dev6699.png","language":"Go","readme":"# face\n\n[![GoDoc](https://pkg.go.dev/badge/github.com/dev6699/face)](https://pkg.go.dev/github.com/dev6699/face)\n[![Go Report Card](https://goreportcard.com/badge/github.com/dev6699/face)](https://goreportcard.com/report/github.com/dev6699/face)\n[![License](https://img.shields.io/github/license/dev6699/face)](LICENSE)\n\nA comprehensive collection of face AI models with integrated pre and post-processing steps, utilizing NVIDIA Triton Inference Server for seamless inference. This repository aims to provide easy-to-use face detection, recognition, and analysis tools.\n\n## Table of Contents\n- [Introduction](#introduction)\n- [Features](#features)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Available Models](#available-models)\n- [Pre and Post Processing](#pre-and-post-processing)\n- [Disclaimer](#disclaimer)\n- [License](#license)\n\n## Introduction\nThis repository contains a suite of face AI models designed for various applications, such as face detection, recognition, and analysis. The models are optimized for performance and ease of use, leveraging NVIDIA Triton Inference Server for scalable and efficient inference.\n\n## Features\n- \u003cb\u003eDiverse Collection of Models:\u003c/b\u003e Includes models for face detection, recognition, age estimation, feature embedding, and landmark detection.\n- \u003cb\u003eIntegrated Pre and Post-Processing:\u003c/b\u003e  Ensures consistent and accurate results across different models.\n- \u003cb\u003eTriton Inference Server Integration:\u003c/b\u003e  Facilitates efficient and scalable model deployment.\n- \u003cb\u003eEasy-to-Use Interface:\u003c/b\u003e  Simple API for quick integration into various applications.\n\n## Installation\n- ### Use `go get` to install this package:\n\n    ```bash\n    go get github.com/dev6699/face\n    ```\n\n- ### Clone the Repository:\n\n    ```bash\n    git clone https://github.com/dev6699/face.git\n    cd face\n    ```\n\n### Download and Prepare Models:\n- Navigate to the [Available Models](#available-models) section to find the download links for each model.\n- Download each model and rename the file to `model.onnx`.\n- Place each `model.onnx` file into its respective directory within the model_repository folder.\n- Example: Setting up the YOLOFace model:\n\n    ```bash\n    mkdir -p model_repository/yoloface/1\n    wget -O model_repository/yoloface/1/model.onnx \u003cmodel_url\u003e\n    ```\n    Ensure to replace \u003cmodel_url\u003e with the actual URL provided in the [Available Models](#available-models) section.\n\n## Usage\nPlease refer to the [examples](examples) folder for more information on how to use the models and run various tasks.\n\n1. Start Triton Inference Server:\n\n    ```bash\n    docker-compose up tritonserver\n    ```\n\n## Available Models\n### 2DFAN4 for Landmark 68 Detection\n- Model Name: [2dfan4](model/2dfan4/2dfan4.go)\n- Description: Detects 68 facial landmarks for detailed facial analysis and alignment.\n- Download Link: [Download 2DFAN4 Model](https://github.com/facefusion/facefusion-assets/releases/download/models/2dfan4.onnx)\n\n    \u003cimg src=\"docs/2dfan4.jpg\" height=200\u003e\n\n### ArcFace for Feature Embedding\n- Model Name: [arcface_w600k_r50](model/arcface/arcface.go)\n- Description: Generates feature embeddings for faces, useful for identity verification and facial recognition tasks.\n- Download Link: [Download ArcFace Model](https://github.com/facefusion/facefusion-assets/releases/download/models/arcface_w600k_r50.onnx)\n\n    *Cosine distance of arcface embedding*\n    | Source\\Target | \u003cimg src=\"docs/arcface_1.jpg\" height=80 align=right\u003e | \u003cimg src=\"docs/arcface_2.jpg\" height=80 align=right\u003e | \u003cimg src=\"docs/arcface_3.jpg\" height=80 align=right\u003e |\n    | :-----: | :-: | :---: | :-----: | \n    | \u003cimg src=\"docs/arcface_1.jpg\" height=80 align=right\u003e | 0.00 | 0.29 | 0.48 |\n    | \u003cimg src=\"docs/arcface_2.jpg\" height=80 align=right\u003e | 0.29 | 0.00 | 0.45 |\n    | \u003cimg src=\"docs/arcface_3.jpg\" height=80 align=right\u003e | 0.48 | 0.45 | 0.00 |\n\n### Face Enhancer with GFPGAN\n- Model Name: [gfpgan_1.4](model/gfpgan/gfpgan.go)\n- Description: Enhances facial features and improves image quality, often used for face restoration and super-resolution tasks.\n- Download Link: [Download GFPGAN Model](https://github.com/facefusion/facefusion-assets/releases/download/models/gfpgan_1.4.onnx)\n\n    | Input | Output |\n    | :---: | :----: |\n    | \u003cimg src=\"docs/gfpgan_1.jpg\" height=200\u003e | \u003cimg src=\"docs/gfpgan_2.jpg\" height=200\u003e |\n    \n\n### Face Occluder Detection\n- Model Name: [face_occluder](model/faceoccluder/faceoccluder.go)\n- Description: Detects parts of a face that are not occluded by objects, providing insights into visible facial features.\n- Download Link: [Download Face Occluder Model](https://github.com/facefusion/facefusion-assets/releases/download/models/face_occluder.onnx)\n\n    \u003cimg src=\"docs/face_occluder_1.jpg\" height=200\u003e\n    \u003cimg src=\"docs/face_occluder_2.jpg\" height=200\u003e\n\n### Gender and Age Estimation\n- Model Name: [gender_age](model/genderage/genderage.go)\n- Description: Detects gender and estimates the age of detected faces.\n- Download Link: [Download Gender and Age Estimation Model](https://github.com/facefusion/facefusion-assets/releases/download/models/yoloface_8n.onnx)\n\n    \u003cimg src=\"docs/gender_age.jpg\" height=200\u003e\n\n### Inswapper\n- Model Name: [inswapper_128_fp16](model/inswapper/inswapper.go)\n- Description: Swaps the target face with a source face, enabling realistic face replacement in images.\n- Download Link: [Download Inswapper Model](https://github.com/facefusion/facefusion-assets/releases/download/models/inswapper_128_fp16.onnx)\n\n    | Source | Target | Output |\n    | :----: | :----: | :----: | \n    | \u003cimg src=\"docs/inswapper_1.jpg\" height=200\u003e | \u003cimg src=\"docs/inswapper_2.jpg\" height=200\u003e | \u003cimg src=\"docs/inswapper_3.jpg\" height=200\u003e |\n\n### YOLOFace\n- Model Name: [yoloface](model/yoloface/yoloface.go)\n- Description: Detects face bounding boxes and the 5 key facial landmarks (landmark5) using the YOLO architecture.\n- Download Link: [Download YOLOFace Model](https://github.com/facefusion/facefusion-assets/releases/download/models/yoloface_8n.onnx)\n\n    \u003cimg src=\"docs/yoloface.jpg\" height=200\u003e\n\n## Pre and Post Processing\n### Pre-processing\nEach model has specific pre-processing steps to ensure accurate results. Common steps include:\n\n- \u003cb\u003eResizing:\u003c/b\u003e Scaling the input image to the required dimensions.\n- \u003cb\u003eNormalization:\u003c/b\u003e Adjusting pixel values to a standard range.\n- \u003cb\u003eFace Alignment:\u003c/b\u003e Aligning faces for consistent feature extraction.\n\n### Post-processing\nPost-processing varies by model and typically includes:\n\n- \u003cb\u003eBounding Box Extraction:\u003c/b\u003e Extracting face locations from detection models.\n- \u003cb\u003eFeature Extraction:\u003c/b\u003e Computing facial features for recognition models.\n- \u003cb\u003eLabel Assignment:\u003c/b\u003e Assigning predicted labels or scores.\n\n## Disclaimer\nModel assets are subject to their individual licenses. Ensure that you review and comply with the specific license terms for each model you use. The repository does not grant rights to use third-party models beyond the scope defined in their respective licenses.\n\n## License\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdev6699%2Fface","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdev6699%2Fface","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdev6699%2Fface/lists"}