# abishagj/pneumonia-detection-vgg16 architecture

> Architecture diagram of the GitHub repository abishagj/pneumonia-detection-vgg16, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/abishagj/pneumonia-detection-vgg16
- Repository: https://github.com/abishagj/pneumonia-detection-vgg16

## Overview

This repository is a notebook-based chest X-ray pneumonia classifier. The principal workflow prepares labeled images, trains and saves a VGG16 model, then loads it in a separate notebook to classify new images and derive Grad-CAM visualizations and heuristic severity estimates. The README documents these responsibilities and data handoffs; notebook internals were not sampled, so relationships below rely on README statements only.

Main entry points: [`finalTest.ipynb`](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb) (Classification), [`finalModel.ipynb`](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb) (Classifier training)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_training["Model training"]
  node_preparation["Image preparation<br/>[finalModel.ipynb]"]
  node_model_build["VGG16 model<br/>[finalModel.ipynb]"]
  node_training_run["Classifier training<br/>[finalModel.ipynb]"]
  node_evaluation["Model evaluation<br/>[finalModel.ipynb]"]
end

subgraph group_inference["Prediction and interpretation"]
  node_inference_prep["Inference preprocessing<br/>[finalTest.ipynb]"]
  node_prediction["Classification<br/>[finalTest.ipynb]"]
  node_gradcam["Grad-CAM heatmap<br/>[finalTest.ipynb]"]
  node_severity["Severity estimate<br/>[finalTest.ipynb]"]
  node_results["Prediction results<br/>[finalTest.ipynb]"]
end

subgraph group_inputs["Image inputs and artifacts"]
  node_dataset["Labeled X-rays"]
  node_samples["Sample images"]
  node_model_file["Saved model"]
end

node_user(("Notebook user"))

node_user -->|"runs training"| node_preparation
node_dataset -->|"provides images"| node_preparation
node_preparation -->|"supplies arrays"| node_model_build
node_model_build -->|"trains model"| node_training_run
node_training_run -->|"validates model"| node_evaluation
node_training_run -->|"saves model"| node_model_file
node_user -->|"runs predictions"| node_inference_prep
node_model_file -->|"loads model"| node_prediction
node_samples -->|"provides images"| node_inference_prep
node_inference_prep -->|"prepares input"| node_prediction
node_prediction -->|"computes heatmap"| node_gradcam
node_gradcam -->|"estimates severity"| node_severity
node_prediction -->|"reports class"| node_results
node_severity -->|"reports estimate"| node_results

click node_preparation "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb"
click node_model_build "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb"
click node_training_run "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb"
click node_evaluation "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb"
click node_inference_prep "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb"
click node_prediction "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb"
click node_gradcam "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb"
click node_severity "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb"
click node_results "https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.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_preparation,node_model_build,node_training_run,node_evaluation,node_user toneBlue
class node_inference_prep,node_prediction,node_gradcam,node_severity,node_results toneAmber
class node_dataset,node_samples,node_model_file toneMint
```

## Components

### Model training

- [Image preparation](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb): `finalModel.ipynb`
- [VGG16 model](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb): `finalModel.ipynb`
- [Classifier training](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb): `finalModel.ipynb`
- [Model evaluation](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalModel.ipynb): `finalModel.ipynb`

### Prediction and interpretation

- [Inference preprocessing](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb): `finalTest.ipynb`
- [Classification](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb): `finalTest.ipynb`
- [Grad-CAM heatmap](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb): `finalTest.ipynb`
- [Severity estimate](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb): `finalTest.ipynb`
- [Prediction results](https://github.com/abishagj/pneumonia-detection-vgg16/blob/main/finalTest.ipynb): `finalTest.ipynb`

### Image inputs and artifacts

- **Labeled X-rays**
- **Sample images**
- **Saved model**

### Other components

- **Notebook user**

## Connections

- Notebook user → Image preparation: runs training (evidence: `README.md`)
- Labeled X-rays → Image preparation: provides images (evidence: `README.md`)
- Image preparation → VGG16 model: supplies arrays (evidence: `README.md`)
- VGG16 model → Classifier training: trains model (evidence: `README.md`)
- Classifier training → Model evaluation: validates model (evidence: `README.md`)
- Classifier training → Saved model: saves model (evidence: `README.md`)
- Notebook user → Inference preprocessing: runs predictions (evidence: `README.md`)
- Saved model → Classification: loads model (evidence: `README.md`)
- Sample images → Inference preprocessing: provides images (evidence: `README.md`)
- Inference preprocessing → Classification: prepares input (evidence: `README.md`)
- Classification → Grad-CAM heatmap: computes heatmap (evidence: `README.md`)
- Grad-CAM heatmap → Severity estimate: estimates severity (evidence: `README.md`)
- Classification → Prediction results: reports class (evidence: `README.md`)
- Severity estimate → Prediction results: reports estimate (evidence: `README.md`)
