Diabetic Retinopathy Detection

About the Project

This project uses deep learning models (VGG16, MobileNet) to detect diabetic retinopathy from retina images. Early detection is critical to prevent vision loss.

• Predict DR severity from retina images
• Uses pre-trained deep learning models
• Integrates with MIT App Inventor for mobile users

MIT App Inventor App

The mobile app allows users to upload retina images and get predictions for DR severity.

Pre-trained Models

The trained models are available on Google Drive. Download and place them in the Model/ folder before running the scripts.

Project Report

View or download the detailed report of the project:

GitHub Repository

Access the source code, scripts, and dataset instructions: