Romilagarwal/diabetic_retinoplasty

A hybrid deep learning framework for automated diabetic retinopathy detection combining EfficientNetB0 with Swin Transformer attention mechanisms. Features Bayesian uncertainty quantification through Monte Carlo Dropout, explainable AI visualizations with Grad-CAM, and specialized preprocessing techniques.

Language: Python - Size: 52.4 MB - Last synced at: 20 days ago - Pushed at: 21 days ago - Stars: 0 - Forks: 0