---
title: Age Detection Demo
emoji: 👶👴
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit
---

# Age Detection Demo

This is a demo of an age regression model trained on the UTKFace dataset. Upload a face image and the model will predict the person's age.

## Model Information

- **Model**: MobileNetV2-based regression model
- **Dataset**: UTKFace
- **Task**: Age estimation from face images
- **Input**: RGB face image (224x224)
- **Output**: Predicted age in years

## Usage

1. Upload a cropped face image (crop to face for best results)
2. Click submit
3. View the predicted age

The model works best with:
- Clear, well-lit face images
- Images cropped to show mainly the face
- Front-facing or near-front-facing poses

## Model Repository

The model is hosted at: [Sharris/age_detection_regression](https://huggingface.co/Sharris/age_detection_regression)

## Limitations

- This model provides age estimates for research and educational purposes
- Results may vary based on image quality, lighting, and pose
- The model reflects biases present in the training data
- Not suitable for high-stakes decision making