# sifatahammed/diabetic-retinopathy-classification-using-deep-learning architecture

> Architecture diagram of the GitHub repository sifatahammed/diabetic-retinopathy-classification-using-deep-learning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning
- Repository: https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning

## Overview

This repository is a notebook-based research project comparing deep-learning approaches to diabetic-retinopathy severity classification from fundus images. Its documented workflow starts with the Kaggle dataset, uses a preprocessing notebook, then evaluates five model experiments using accuracy and Cohen’s kappa. The README identifies the models and reported results, but notebook contents were not sampled, so implementation details and precise call or data-transfer wiring cannot be verified; the diagram shows only the documented high-level workflow.

Main entry points: [`Dataset_Preprocessing.ipynb`](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Dataset_Preprocessing.ipynb) (Dataset preprocessing), [`Experiments`](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/tree/main/Experiments) (Accuracy and kappa), [`Experiments/3. CNN.ipynb`](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/3.%20CNN.ipynb) (Custom CNN), [`Experiments/2. InceptionV3.ipynb`](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/2.%20InceptionV3.ipynb) (InceptionV3)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_preprocess["Dataset preprocessing"]
end

subgraph group_models["Model experiments"]
  node_cnn["Custom CNN<br/>[3. CNN.ipynb]"]
  node_inception["InceptionV3"]
  node_resnet["ResNet50<br/>[4. ResNet50.ipynb]"]
  node_densenet["DenseNet121"]
  node_efficientnet["EfficientNetB6"]
end

subgraph group_evaluation["Evaluation"]
  node_metrics["Accuracy and kappa"]
end

node_dataset[("Kaggle DR dataset")]

node_dataset -->|"provides images"| node_preprocess
node_preprocess -->|"prepares data"| node_cnn
node_preprocess -->|"prepares data"| node_inception
node_preprocess -->|"prepares data"| node_resnet
node_preprocess -->|"prepares data"| node_densenet
node_preprocess -->|"prepares data"| node_efficientnet
node_cnn -->|"evaluates with"| node_metrics
node_inception -->|"evaluates with"| node_metrics
node_resnet -->|"evaluates with"| node_metrics
node_densenet -->|"evaluates with"| node_metrics
node_efficientnet -->|"evaluates with"| node_metrics

click node_preprocess "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Dataset_Preprocessing.ipynb"
click node_cnn "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/3.%20CNN.ipynb"
click node_inception "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/2.%20InceptionV3.ipynb"
click node_resnet "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/4.%20ResNet50.ipynb"
click node_densenet "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/1.%20DenseNet121.ipynb"
click node_efficientnet "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/5.%20EfficientNet.ipynb"
click node_metrics "https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/tree/main/Experiments"

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_preprocess toneBlue
class node_cnn,node_inception,node_resnet,node_densenet,node_efficientnet,node_dataset toneAmber
class node_metrics toneMint
```

## Components

### Data preparation

- [Dataset preprocessing](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Dataset_Preprocessing.ipynb): `Dataset_Preprocessing.ipynb`

### Model experiments

- [Custom CNN](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/3.%20CNN.ipynb): `Experiments/3. CNN.ipynb`
- [InceptionV3](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/2.%20InceptionV3.ipynb): `Experiments/2. InceptionV3.ipynb`
- [ResNet50](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/4.%20ResNet50.ipynb): `Experiments/4. ResNet50.ipynb`
- [DenseNet121](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/1.%20DenseNet121.ipynb): `Experiments/1. DenseNet121.ipynb`
- [EfficientNetB6](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/blob/main/Experiments/5.%20EfficientNet.ipynb): `Experiments/5. EfficientNet.ipynb`

### Evaluation

- [Accuracy and kappa](https://github.com/sifatahammed/diabetic-retinopathy-classification-using-deep-learning/tree/main/Experiments): `Experiments`

### Other components

- **Kaggle DR dataset**

## Connections

- Kaggle DR dataset → Dataset preprocessing: provides images
- Dataset preprocessing → Custom CNN: prepares data
- Dataset preprocessing → InceptionV3: prepares data
- Dataset preprocessing → ResNet50: prepares data
- Dataset preprocessing → DenseNet121: prepares data
- Dataset preprocessing → EfficientNetB6: prepares data
- Custom CNN → Accuracy and kappa: evaluates with
- InceptionV3 → Accuracy and kappa: evaluates with
- ResNet50 → Accuracy and kappa: evaluates with
- DenseNet121 → Accuracy and kappa: evaluates with
- EfficientNetB6 → Accuracy and kappa: evaluates with