# adhammostafaa/ae-mega-project-team-2 architecture

> Architecture diagram of the GitHub repository adhammostafaa/ae-mega-project-team-2, 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/adhammostafaa/ae-mega-project-team-2
- Repository: https://github.com/adhammostafaa/ae-mega-project-team-2

## Overview

The visible runtime is a command-line generator for synthetic object-detection images and YOLO labels. Its workflow creates backgrounds and labeled shapes, composes randomized images, then writes split image/label files and dataset metadata. The README also describes a separate Wikipedia-to-text-generation Transformer pipeline, including training, generation, and attention visualization, but no corresponding source file appears in the supplied tree; that branch is therefore shown only at the documented level. The RAR archive’s contents are unknown.

Main entry points: [`generate_odlc_dataset.py`](https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py) (Dataset CLI)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_dataset["ODLC Dataset Generator"]
  node_generator["Dataset CLI"]
  node_background["Background maker"]
  node_object["Object composer"]
  node_shape["Shape drawer"]
  node_images["Image splits"]
  node_labels["YOLO labels"]
  node_metadata["Dataset metadata"]
end

subgraph group_text["Text Generation Pipeline"]
  node_wiki[("Wikipedia corpus")]
  node_preprocess["Corpus preprocessing"]
  node_transformer["Causal Transformer"]
  node_training["Model training"]
  node_generation["Text generation"]
  node_visualization["Attention heatmap"]
end

node_user(("Dataset user"))

node_user -->|"runs"| node_generator
node_generator -->|"creates"| node_background
node_generator -->|"creates"| node_object
node_object -->|"draws"| node_shape
node_generator -->|"writes"| node_images
node_generator -->|"writes"| node_labels
node_generator -->|"writes"| node_metadata
node_wiki -->|"provides text"| node_preprocess
node_preprocess -->|"provides blocks"| node_transformer
node_transformer -->|"trains"| node_training
node_training -->|"produces model"| node_generation
node_transformer -->|"provides attention"| node_visualization

click node_generator "https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py"
click node_background "https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py"
click node_object "https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py"
click node_shape "https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py"

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_generator,node_background,node_object,node_shape,node_images,node_labels,node_metadata,node_user toneBlue
class node_wiki,node_preprocess,node_transformer,node_training,node_generation,node_visualization toneAmber
```

## Components

### ODLC Dataset Generator

- [Dataset CLI](https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py): `generate_odlc_dataset.py`
- [Background maker](https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py): `generate_odlc_dataset.py`
- [Object composer](https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py): `generate_odlc_dataset.py`
- [Shape drawer](https://github.com/adhammostafaa/ae-mega-project-team-2/blob/main/generate_odlc_dataset.py): `generate_odlc_dataset.py`
- **Image splits**
- **YOLO labels**
- **Dataset metadata**

### Text Generation Pipeline

- **Wikipedia corpus**
- **Corpus preprocessing**
- **Causal Transformer**
- **Model training**
- **Text generation**
- **Attention heatmap**

### Other components

- **Dataset user**

## Connections

- Dataset user → Dataset CLI: runs (evidence: `generate_odlc_dataset.py`)
- Dataset CLI → Background maker: creates (evidence: `generate_odlc_dataset.py`)
- Dataset CLI → Object composer: creates (evidence: `generate_odlc_dataset.py`)
- Object composer → Shape drawer: draws (evidence: `generate_odlc_dataset.py`)
- Dataset CLI → Image splits: writes (evidence: `generate_odlc_dataset.py`)
- Dataset CLI → YOLO labels: writes (evidence: `generate_odlc_dataset.py`)
- Dataset CLI → Dataset metadata: writes (evidence: `generate_odlc_dataset.py`)
- Wikipedia corpus → Corpus preprocessing: provides text (evidence: `README.md`)
- Corpus preprocessing → Causal Transformer: provides blocks (evidence: `README.md`)
- Causal Transformer → Model training: trains (evidence: `README.md`)
- Model training → Text generation: produces model (evidence: `README.md`)
- Causal Transformer → Attention heatmap: provides attention (evidence: `README.md`)
