# securdrgorp/model_crafter_project architecture

> Architecture diagram of the GitHub repository securdrgorp/model_crafter_project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-27). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/securdrgorp/model_crafter_project
- Repository: https://github.com/securdrgorp/model_crafter_project

## Overview

##### Project type and purpose
- This is an image‐classification pipeline combining deep learning (CNN via TensorFlow/Keras) and traditional ML (SVM, KNN, Random Forest) to detect diseases in fruits and vegetables.
- It provides end-to-end functionality: data ingestion, preprocessing, model training, evaluation, and a prediction service for inference.

##### File structure
- Top level:
- main.py – orchestrates the full pipeline
- config.py – holds global settings (paths, hyperparameters)
- requirements.txt – lists dependencies
- preprocess/ – modules that clean, balance, convert, split, and validate images
- train/ – scripts and model definitions for CNN and traditional ML pipelines
- utils/ – shared utilities for data loading, feature extraction, evaluation, visualization
- services/ – prediction_service.py exposes the trained model for inference

##### README for additional insights
- Confirms a two‐pronged training strategy (CNN vs. traditional ML).
- Describes custom checkpoint logic, visualization outputs, and the dataset structure.

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Configuration & Orchestration
    subgraph "Configuration & Orchestration"
        CFG["config.py"]:::config
        MAIN["main.py"]:::config
    end

    %% Data Source
    DS(["Raw Images (Kaggle Dataset)"]):::data

    %% Preprocessing Pipeline
    subgraph "Data Preprocessing Pipeline"
        CLEAN["clean_images.py"]:::preprocess
        CONVERT["convert_images.py"]:::preprocess
        BALANCE["class_balancer.py"]:::preprocess
        PALETTE["palette_transparency.py"]:::preprocess
        SPLIT["split_data.py"]:::preprocess
        VALIDATE["validate_images.py"]:::preprocess
    end

    %% Data Storage
    RAW[("data/raw")]:::storage
    PROCESSED[("data/processed")]:::storage

    %% Feature Extraction & Training
    subgraph "Model Training"
        subgraph "CNN Training"
            CNN["train_cnn.py"]:::training
            MODELDEF["model.py"]:::training
        end
        subgraph "Traditional ML Training"
            FEATURE["feature_extraction.py"]:::utils
            TRAD["train_traditional_ml.py"]:::training
        end
    end

    %% Evaluation & Visualization
    subgraph "Evaluation & Visualization"
        EVAL["evaluate.py"]:::utils
        VIS["visualize.py"]:::utils
    end

    %% Prediction Service
    PS["prediction_service.py"]:::service

    %% Orchestration arrows
    MAIN -->|uses| CFG
    MAIN -->|orchestrates| DS

    %% Data flow
    DS -->|"ingest data"| CLEAN
    CLEAN --> CONVERT
    CONVERT --> BALANCE
    BALANCE --> PALETTE
    PALETTE --> SPLIT
    SPLIT --> VALIDATE
    VALIDATE --> RAW
    VALIDATE --> PROCESSED

    RAW --> CNN
    PROCESSED --> CNN
    PROCESSED --> FEATURE
    FEATURE --> TRAD

    CNN --> EVAL
    TRAD --> EVAL
    EVAL --> VIS
    VIS --> PS

    %% Click Events
    click CLEAN "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/clean_images.py"
    click CONVERT "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/convert_images.py"
    click BALANCE "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/class_balancer.py"
    click PALETTE "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/palette_transparency.py"
    click SPLIT "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/split_data.py"
    click VALIDATE "https://github.com/securdrgorp/model_crafter_project/blob/main/preprocess/validate_images.py"
    click CFG "https://github.com/securdrgorp/model_crafter_project/blob/main/config.py"
    click MAIN "https://github.com/securdrgorp/model_crafter_project/blob/main/main.py"
    click CNN "https://github.com/securdrgorp/model_crafter_project/blob/main/train/train_cnn.py"
    click MODELDEF "https://github.com/securdrgorp/model_crafter_project/blob/main/train/model.py"
    click TRAD "https://github.com/securdrgorp/model_crafter_project/blob/main/train/train_traditional_ml.py"
    click FEATURE "https://github.com/securdrgorp/model_crafter_project/blob/main/utils/feature_extraction.py"
    click EVAL "https://github.com/securdrgorp/model_crafter_project/blob/main/utils/evaluate.py"
    click VIS "https://github.com/securdrgorp/model_crafter_project/blob/main/utils/visualize.py"
    click PS "https://github.com/securdrgorp/model_crafter_project/blob/main/services/prediction_service.py"

    %% Styles
    classDef data fill:#AED6F1,stroke:#1B4F72,stroke-width:1px;
    classDef preprocess fill:#FCF3CF,stroke:#7D6608,stroke-width:1px;
    classDef storage fill:#D5DBDB,stroke:#566573,stroke-width:1px,stroke-dasharray: 5 5;
    classDef training fill:#ABEBC6,stroke:#1D8348,stroke-width:1px;
    classDef utils fill:#D6EAF8,stroke:#21618C,stroke-width:1px;
    classDef service fill:#F5B7B1,stroke:#922B21,stroke-width:1px;
    classDef config fill:#FADBD8,stroke:#943126,stroke-width:1px;
```
