# poorvikanp/ai-driven-diabetic-retinopathy-detection architecture

> Architecture diagram of the GitHub repository poorvikanp/ai-driven-diabetic-retinopathy-detection, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/poorvikanp/ai-driven-diabetic-retinopathy-detection
- Repository: https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection

## Overview

This is a notebook-based diabetic-retinopathy image-classification project. Its documented workflow loads retinal images, preprocesses and splits them, trains CNN and EfficientNetB3 models, evaluates performance, and visualizes predictions with Grad-CAM. The notebook is the only implementation file shown; the README documents the stages and capabilities, but the notebook contents were not provided, so internal calls and data flow cannot be verified. The README also mentions saved models, though no model directory appears in the supplied file tree.

Main entry points: [`DR_Classification_Notebook (2).ipynb`](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb) (EfficientNetB3 transfer learning)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Image data"]
  node_fundus[("Fundus images")]
  node_loading["Dataset loading"]
  node_preprocess["Preprocessing and augmentation"]
  node_split["Train-validation split"]
end

subgraph group_models["Model training"]
  node_cnn["Simple CNN"]
  node_efficientnet["EfficientNetB3 transfer learning"]
  node_savedmodels[("Saved models")]
end

subgraph group_analysis["Evaluation and interpretation"]
  node_evaluation["Model evaluation"]
  node_comparison["Model comparison"]
  node_prediction["Prediction visualization"]
  node_gradcam["Grad-CAM explanations"]
end

node_user(("Project user"))

node_user -->|"runs notebook"| node_loading
node_fundus -->|"provides images"| node_loading
node_loading -->|"precedes"| node_preprocess
node_preprocess -->|"precedes"| node_split
node_split -->|"trains"| node_cnn
node_split -->|"trains"| node_efficientnet
node_cnn -->|"evaluated by"| node_evaluation
node_efficientnet -->|"evaluated by"| node_evaluation
node_evaluation -->|"compared in"| node_comparison
node_efficientnet -->|"supports"| node_prediction
node_efficientnet -->|"explained by"| node_gradcam
node_cnn -.->|"saved as"| node_savedmodels
node_efficientnet -.->|"saved as"| node_savedmodels

click node_loading "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_preprocess "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_split "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_cnn "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_efficientnet "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_evaluation "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_comparison "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_prediction "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"
click node_gradcam "https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_fundus,node_loading,node_preprocess,node_split,node_user toneBlue
class node_cnn,node_efficientnet,node_savedmodels toneAmber
class node_evaluation,node_comparison,node_prediction,node_gradcam toneMint
```

## Components

### Image data

- **Fundus images**
- [Dataset loading](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [Preprocessing and augmentation](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [Train-validation split](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`

### Model training

- [Simple CNN](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [EfficientNetB3 transfer learning](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- **Saved models**

### Evaluation and interpretation

- [Model evaluation](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [Model comparison](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [Prediction visualization](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`
- [Grad-CAM explanations](https://github.com/poorvikanp/ai-driven-diabetic-retinopathy-detection/blob/main/DR_Classification_Notebook%20(2).ipynb): `DR_Classification_Notebook (2).ipynb`

### Other components

- **Project user**

## Connections

- Project user → Dataset loading: runs notebook (evidence: `README.md`)
- Fundus images → Dataset loading: provides images (evidence: `README.md`)
- Dataset loading → Preprocessing and augmentation: precedes (evidence: `README.md`)
- Preprocessing and augmentation → Train-validation split: precedes (evidence: `README.md`)
- Train-validation split → Simple CNN: trains (evidence: `README.md`)
- Train-validation split → EfficientNetB3 transfer learning: trains (evidence: `README.md`)
- Simple CNN → Model evaluation: evaluated by (evidence: `README.md`)
- EfficientNetB3 transfer learning → Model evaluation: evaluated by (evidence: `README.md`)
- Model evaluation → Model comparison: compared in (evidence: `README.md`)
- EfficientNetB3 transfer learning → Prediction visualization: supports (evidence: `README.md`)
- EfficientNetB3 transfer learning → Grad-CAM explanations: explained by (evidence: `README.md`)
- Simple CNN → Saved models: saved as (evidence: `README.md`)
- EfficientNetB3 transfer learning → Saved models: saved as (evidence: `README.md`)
