Download RetinaFace

Free, MIT licensed, no account required. Get the complete model package and start detecting faces immediately.

🤖

RetinaFace Model Package

Pre-trained weights, Python implementation, usage examples, and complete documentation

Version
1.0.0
File Size
48 MB
Format
ZIP Archive
License
MIT — Free
Python
3.7 and above
Platform
Win / Mac / Linux

✓ Clean & safe  ·  ✓ No adware  ·  ✓ No sign-up  ·  ✓ MIT Licensed

What's Inside the RetinaFace Package

🧠

Pre-Trained Weights

MobileNet and ResNet-50 backbone weights trained on WIDER FACE, ready for immediate inference.

🐍

Python Scripts

Complete Python implementation with inference examples, alignment utilities, and a simple CLI tool.

📄

Documentation

Step-by-step installation guide, API reference, and annotated example notebooks.

🔧

Configuration Files

Default configuration files for both backbone variants with recommended anchor settings.

📊

Benchmark Results

Reproduction scripts and results tables for verifying performance on WIDER FACE subsets.

📜

MIT License

Full license text confirming free use for personal and commercial projects without restriction.

Installation in 3 Steps

1

Download & Extract

Click the download button above, save the ZIP file, and extract it to your project directory.

2
🐍

Install Dependencies

Run pip install retinaface in your terminal to install all required Python packages.

3
🎯

Start Detecting

Import RetinaFace in Python, call detect_faces(), and receive bounding boxes and landmarks instantly.

📖 Read the Full Installation Guide