# houdaipha/morad architecture

> Architecture diagram of the GitHub repository houdaipha/morad, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-03-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/houdaipha/morad
- Repository: https://github.com/houdaipha/morad

## Overview

##### Project Type & Purpose
- This is a multimodal emotion recognition framework that benchmarks various models (unimodal and multimodal) on a curated dataset (MORAD).
- The core purpose is to evaluate deep learning models across different modalities, as evidenced by the diverse configurations and modules for audio, vision, text, and their combinations.

##### Analyzing the File Structure
- Top-level directories include:
- configs: Contains configuration YAML files for different model setups and modalities. They are grouped by modality (audio, text, vision) and multi (for multimodal configurations).
- data: Provides data processing, including utilities and loaders for different types of input (audio, vision, text, and a unified multi-modal component).
- engines: Implements the core execution logic for each model during training or evaluation. Modules are again separated by modality.
- models: Defines the model architectures for different modalities. They mirror the engines’ directory structure.
- training: Contains scripts for handling the training routines across modalities.
- Additional files like main.py and test.py act as entry points for training and testing respectively.
- The separation of directories by modality (audio, vision, text) and by purpose (data, engines, models) clearly indicates a modular design that can be diagrammed into layers.

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Configuration/Data Layer
    subgraph "Configuration/Data Layer"
        direction TB
        Configs["Configs: audio, vision, text, multi"]:::config
        DataProcessing["Data Processing: audio, vision, text, multi pipelines"]:::data
    end

    %% Processing & Model Layer
    subgraph "Processing & Model Layer"
        direction TB
        Engines["Engines: audio, vision, text, multi controllers"]:::engine
        Models["Models: audio, vision, text, multi architectures"]:::model
    end

    %% Training/Testing Layer
    subgraph "Training/Testing Layer"
        direction TB
        Training["Training Module (training scripts)"]:::training
        Main["Entry Point (main.py)"]:::trainingEntry
        Testing["Testing Routine (test.py)"]:::testing
    end

    %% Infrastructure/Environment
    subgraph "Infrastructure/Environment"
        direction TB
        Infra["Hardware: CUDA-enabled GPU (Nvidia A100)\nSoftware: Python3.11, PyTorch, Transformers, CUDA"]:::infra
    end

    %% Data Flow Connections
    Configs -->|"feeds"| DataProcessing
    DataProcessing -->|"supplies"| Engines
    DataProcessing -->|"feeds"| Models
    Engines -->|"triggers"| Models
    Training -->|"orchestrates"| Engines
    Main -->|"initiates"| Training
    Testing -->|"evaluates"| Engines
    Infra -->|"supports"| Engines
    Infra -->|"supports"| Models
    Infra -->|"supports"| Training

    %% Legend (placed via a linking node)
    Infra --- Legend["Legend:\nGreen: Configurations\nBlue: Data Processing\nPink: Engines\nOrange: Models\nPurple: Training/Testing\nGray: Infrastructure"]:::legend

    %% Click Events
    click Configs "https://github.com/houdaipha/morad/tree/master/configs/"
    click DataProcessing "https://github.com/houdaipha/morad/tree/master/data/"
    click Engines "https://github.com/houdaipha/morad/tree/master/engines/"
    click Models "https://github.com/houdaipha/morad/tree/master/models/"
    click Training "https://github.com/houdaipha/morad/tree/master/training/"
    click Testing "https://github.com/houdaipha/morad/blob/master/test.py"
    click Main "https://github.com/houdaipha/morad/blob/master/main.py"

    %% Styles
    classDef config fill:#a1d490,stroke:#333,stroke-width:2px;
    classDef data fill:#a0c4ff,stroke:#333,stroke-width:2px;
    classDef engine fill:#ffb7b2,stroke:#333,stroke-width:2px;
    classDef model fill:#ffdfba,stroke:#333,stroke-width:2px;
    classDef training fill:#c5bed8,stroke:#333,stroke-width:2px;
    classDef trainingEntry fill:#c5bed8,stroke:#333,stroke-width:2px;
    classDef testing fill:#d4a5a5,stroke:#333,stroke-width:2px;
    classDef infra fill:#e0e0e0,stroke:#333,stroke-width:2px;
    classDef legend fill:#f8f9fa,stroke:#666,stroke-dasharray:5 5,stroke-width:1px;
```
