RetinaVision-MNet / README.md
DrakeBlaze's picture
Create README.md
c3f3dd4 verified
|
raw
history blame
635 Bytes

RetinaVision-MNet is a custom-trained MobileNetV2-based deep learning model for multi-class retinal disease detection. It predicts 10 retinal conditions from fundus images and generates Grad-CAM heatmaps for interpretable diagnosis. The model was trained from scratch and is hosted on Hugging Face due to GitHub size limits.

Key Features

10-class retinal disease classification

MobileNetV2 backbone (lightweight + high accuracy)

Grad-CAM visual explanations

Trained from scratch on curated dataset

Optimized for FastAPI deployment

Usage

Download the model file from the Files and Versions tab and load it into your application.