# dhruvnet/synthetic-image-generation-for-ai-training architecture

> Architecture diagram of the GitHub repository dhruvnet/synthetic-image-generation-for-ai-training, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-07-10). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dhruvnet/synthetic-image-generation-for-ai-training
- Repository: https://github.com/dhruvnet/synthetic-image-generation-for-ai-training

## Overview

##### Project Type and Purpose
- This is a research‐oriented, open-source synthetic image generation pipeline implemented as Jupyter notebooks and Python modules.
- Purpose: Generate diverse, high-resolution images under varying conditions (day/night, weather effects) to augment AI training datasets, with built-in safeguards against adversarial/ deep-fake threats.

##### File Structure Analysis
- Top-level directories:
- Algorithm/ – Python modules or helper scripts for each generative model
- COMPARISiON/ – Evaluation scripts and output comparisons between models
- FINAL OP/ – Final output artifacts (generated images, notebooks)
- Notebooks:
- day-night-image-translations-using-cyclegan.ipynb – CycleGAN pipeline
- Train_ConditionalVAE_FINAL.ipynb – CVAE training for weather simulation
- FYP_dataset_building.ipynb – Orchestrator notebook, dataset creation, UI control
- Config/build: No explicit CI/CD or deployment scripts, this is a local/ research pipeline.

##### README Insights
- Core Modules: CycleGAN, CVAE, Real-ESRGAN, and a User Interface module.
- Data sources: Separate datasets for CycleGAN (~30k images) and CVAE (~89k images).
- Evaluation: Reconstruction and latent loss metrics; comparison against baselines (DALL-E2, RunwayML, Artbreeder).
- Tech Stack: Python (PyTorch/TensorFlow), OpenCV, Matplotlib/Seaborn, Jupyter.

a. Main Components
1. Data Ingestion & Preprocessing
– CycleGAN dataset loader
– CVAE attribute dataset loader
– Image augmentation & normalization (OpenCV)
2. Generative Modules
– CycleGAN module (day↔night)
– CVAE module (fog/rain/snow simulation)
– Real-ESRGAN module (super-resolution)
3. Control Interface
– Notebook-based UI to set intensity, select models, tune parameters
4. Security/Guard Module (optional)
– Adversarial‐attack detection or privacy filters
5. Evaluation & Comparison
– Metrics calculator (reconstruction, total, latent loss)
– Comparison scripts vs. baselines
6. Output & Storage
– Final images (FINAL OP/)
– Logs & plots (COMPARISiON/)

b. Relationships & Data Flow
- Feedback loop from Evaluation → Control Interface for parameter tuning

c. Architectural Patterns
- Modular pipeline: each generative component is a replaceable service
- Directed acyclic data flow (no circular dependencies)
- Notebook orchestration as a “controller” layer
- Separation of concerns: data, compute, evaluation, UI

d. Key Technologies
- PyTorch / TensorFlow code modules (Algorithm/)
- OpenCV preprocessing scripts
- Real-ESRGAN library integration
- Jupyter Notebook as UI & orchestrator
- Matplotlib & Seaborn for visualizations

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Documentation
    README["Project Documentation\n(README.md)"]:::doc

    %% Data Ingestion & Preprocessing
    subgraph "Data Ingestion & Preprocessing"
        direction TB
        DataIngest["CycleGAN Dataset Loader"]:::data
        CVAELoad["CVAE Dataset Loader"]:::data
        AugNorm["Augmentation &\nNormalization"]:::data
    end

    %% Generative Modules
    subgraph "Generative Modules"
        direction TB
        CycleGAN["CycleGAN Module\n(day↔night)"]:::compute
        CVAE["CVAE Module\n(weather sim)"]:::compute
        ESRGAN["Real-ESRGAN Module\n(super-res)"]:::compute
    end

    %% Control Interface
    UI("Notebook-Based UI\n(Orchestrator)"):::ui

    %% Evaluation & Comparison
    subgraph "Evaluation & Comparison"
        direction TB
        Metrics["Metrics Calculator\n(recon, latent loss)"]:::eval
        Compare["Comparison Scripts\n(vs DALL-E2, Artbreeder)"]:::eval
    end

    %% Output & Storage
    subgraph "Output & Storage"
        direction TB
        Images["Final Images"]:::data
        Logs["Logs & Plots"]:::data
    end

    %% Primary Data Flow
    DataIngest -->|“256×256 RGB images”| CycleGAN
    CVAELoad -->|“256×256 RGB images”| CVAE
    AugNorm -->|“normalized batches”| CycleGAN
    AugNorm -->|“normalized batches”| CVAE
    AugNorm -->|“normalized batches”| ESRGAN

    CycleGAN -->|“generated images”| Images
    CVAE -->|“weather-sim images”| Images
    ESRGAN -->|“super-res images”| Images

    CycleGAN -->|“256×256 outputs”| Metrics
    CVAE -->|“256×256 outputs”| Metrics
    ESRGAN -->|“512×512 outputs”| Metrics
    Metrics -->|“loss values”| Compare

    %% Control Flow
    UI -.->|“model params”| CycleGAN
    UI -.->|“model params”| CVAE
    UI -.->|“model params”| ESRGAN

    %% Feedback Loop
    Compare -.-|"tuning feedback"| UI

    %% Click Events
    click README "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/blob/main/README.md"
    click DataIngest "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click CVAELoad "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click AugNorm "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click CycleGAN "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click CVAENotebook "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/blob/main/Train_ConditionalVAE_FINAL.ipynb"
    click CVAE "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click CycleGANNotebook "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/blob/main/day-night-image-translations-using-cyclegan.ipynb"
    click ESRGAN "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/Algorithm/"
    click UI "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/blob/main/FYP_dataset_building.ipynb"
    click Compare "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/COMPARISiON/"
    click Images "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/FINAL OP/"
    click Logs "https://github.com/dhruvnet/synthetic-image-generation-for-ai-training/tree/main/FINAL OP/"

    %% Styles
    classDef data fill:#D0E8FF,stroke:#3399FF,color:#003366;
    classDef compute fill:#DFF2D8,stroke:#4CAF50,color:#26532B;
    classDef ui fill:#FFE8CC,stroke:#FF9800,color:#663C00;
    classDef eval fill:#F3E5F5,stroke:#9C27B0,color:#4A1454;
    classDef doc fill:#F5F5F5,stroke:#9E9E9E,color:#212121;
```
