# mirl-iitm/da6401_assignment_1 architecture

> Architecture diagram of the GitHub repository mirl-iitm/da6401_assignment_1, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-02-10). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/mirl-iitm/da6401_assignment_1
- Repository: https://github.com/mirl-iitm/da6401_assignment_1

## Overview

##### Project Type and Purpose
- This is an educational, NumPy-only implementation of a Multi-Layer Perceptron (MLP) for image classification (MNIST/Fashion-MNIST).
- It provides the full training and inference pipeline, including forward/backward propagation, optimizers, loss functions, and experiment logging via Weights & Biases.

##### File Structure Analysis
Top-level:
- README.md – Describes the assignment and learning objectives
- requirements.txt – Python dependencies (NumPy, wandb, etc.)
- models/ – Directory to save trained model files
- src/
– ann/ – Core neural network library
› activations.py
› neural_layer.py
› neural_network.py
› objective_functions.py
› optimizers.py
– utils/ – Utility modules
› data_loader.py
– train.py – Orchestrates training loop
– inference.py – Loads a saved model and runs predictions

##### Key Components
a. Data Pipeline
- Data Loader (src/utils/data_loader.py)
- Datasets (MNIST/Fashion-MNIST)
b. Core MLP Library (src/ann)
- Layers (neural_layer.py)
- Activations (activations.py)
- Loss Functions (objective_functions.py)
- Optimizers (optimizers.py)
- Network Orchestration (neural_network.py)
c. Training Orchestrator (src/train.py)
- Loads data → builds the network → runs forward/backward passes → updates weights → logs metrics to Weights & Biases → saves model files to models/
d. Inference Orchestrator (src/inference.py)
- Loads a saved model → loads test data → runs forward pass → outputs predictions
e. External Services
- Weights & Biases for experiment logging

##### Architectural Patterns and Principles
- Modular Layering: Core library (ann) is isolated from orchestration scripts (train, inference)
- Pipeline Pattern: Clear separation of data loading, model definition, training loop, and inference

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Pipeline
    subgraph "Data Pipeline"
        Dataset["Dataset (MNIST / Fashion-MNIST)"]:::data
        DataLoader["Data Loader"]:::data
    end

    %% Orchestration
    subgraph "Orchestration"
        Train["Training Orchestrator"]:::orches
        Infer["Inference Orchestrator"]:::orches
    end

    %% Core Library
    subgraph "Core MLP Library"
        Layers["Layers"]:::core
        Activations["Activations"]:::core
        Objectives["Loss Functions"]:::core
        Optimizers["Optimizers"]:::core
        Network["Network Orchestration"]:::core
    end

    %% Storage & Services
    subgraph "Storage & Services"
        Models["Model Storage"]:::storage
        WandB["Weights & Biases"]:::storage
    end

    %% Data Flow
    Dataset -->|"raw data"| DataLoader
    DataLoader -->|"mini-batch"| Train
    Train <-->|"calls forward/backward"| Network
    Train -->|"checkpoint"| Models
    Train -->|"metrics"| WandB
    Models -->|"load checkpoint"| Infer
    Infer -->|"test batch"| DataLoader
    Infer -->|"forward pass"| Network
    Network -->|"predictions"| Infer

    %% Click Events
    click DataLoader "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/utils/data_loader.py"
    click Activations "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/ann/activations.py"
    click Layers "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/ann/neural_layer.py"
    click Network "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/ann/neural_network.py"
    click Objectives "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/ann/objective_functions.py"
    click Optimizers "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/ann/optimizers.py"
    click Train "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/train.py"
    click Infer "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/src/inference.py"
    click Models "https://github.com/mirl-iitm/da6401_assignment_1/tree/main/models/"
    click WandB "https://github.com/mirl-iitm/da6401_assignment_1/blob/main/requirements.txt"

    %% Styles
    classDef core fill:#bbdefb,stroke:#0d47a1,color:#0d47a1
    classDef data fill:#c8e6c9,stroke:#1b5e20,color:#1b5e20
    classDef orches fill:#ffe0b2,stroke:#e65100,color:#e65100
    classDef storage fill:#eeeeee,stroke:#424242,color:#424242
```
