# aryan-sz13/aiml-recruitment-2026-aryan-singh architecture

> Architecture diagram of the GitHub repository aryan-sz13/aiml-recruitment-2026-aryan-singh, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/aryan-sz13/aiml-recruitment-2026-aryan-singh
- Repository: https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh

## Overview

This repository is a Python/TensorFlow MNIST digit-classification and analysis application. Its main workflow loads and preprocesses MNIST, runs a controlled model-ablation suite, and uses the results for metric analysis and diagnostic plots. The README also documents dataset exploration, training/validation curves, confusion matrices, per-class metrics, and error inspection. Source excerpts show the main orchestration and data-loading calls; the experiment module’s indexed references support its core dependencies, but not every internal call detail is shown.

Main entry points: [`src/experiment.py`](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/experiment.py) (Ablation suite), [`main.py`](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/main.py) (Pipeline entry), [`src/data.py`](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/data.py) (Data preparation), [`src/mnist_download.py`](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/mnist_download.py) (Dataset download)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ingestion["Data ingestion"]
  node_download["Dataset download<br/>[mnist_download.py]"]
  node_parser["IDX parser<br/>[mnist_parser.py]"]
  node_data["Data preparation<br/>[data.py]"]
end

subgraph group_modeling["Modeling and experiments"]
  node_model["MLP builder<br/>[model.py]"]
  node_train["Model training<br/>[train.py]"]
  node_experiment["Ablation suite<br/>[experiment.py]"]
end

subgraph group_analysis["Evaluation and visualization"]
  node_evaluate["Metric analysis<br/>[evaluate.py]"]
  node_visualize["Diagnostic plots<br/>[visualize.py]"]
end

subgraph group_runtime["Application runtime"]
  node_config["Run configuration<br/>[config.py]"]
  node_main["Pipeline entry<br/>[main.py]"]
end

node_user(("Assessment user"))
node_mirror["MNIST mirror"]

node_user -->|"runs pipeline"| node_main
node_main -->|"ensures directories"| node_config
node_main -->|"loads data"| node_data
node_data -->|"downloads missing files"| node_download
node_mirror -->|"provides archives"| node_download
node_data -->|"loads IDX samples"| node_parser
node_main -->|"runs suite"| node_experiment
node_experiment -->|"uses settings"| node_config
node_experiment -->|"loads data"| node_data
node_experiment -->|"builds variants"| node_model
node_experiment -->|"trains variants"| node_train
node_experiment -->|"evaluates models"| node_evaluate
node_main -->|"finds error cases"| node_evaluate
node_main -->|"renders diagnostics"| node_visualize

click node_download "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/mnist_download.py"
click node_parser "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/mnist_parser.py"
click node_data "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/data.py"
click node_config "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/config.py"
click node_main "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/main.py"
click node_model "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/model.py"
click node_train "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/train.py"
click node_experiment "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/experiment.py"
click node_evaluate "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/evaluate.py"
click node_visualize "https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/visualize.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_download,node_parser,node_data,node_user toneBlue
class node_model,node_train,node_experiment toneAmber
class node_evaluate,node_visualize toneMint
class node_config,node_main toneRose
class node_mirror toneIndigo
```

## Components

### Data ingestion

- [Dataset download](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/mnist_download.py): `src/mnist_download.py`
- [IDX parser](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/mnist_parser.py): `src/mnist_parser.py`
- [Data preparation](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/data.py): `src/data.py`

### Modeling and experiments

- [MLP builder](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/model.py): `src/model.py`
- [Model training](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/train.py): `src/train.py`
- [Ablation suite](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/experiment.py): `src/experiment.py`

### Evaluation and visualization

- [Metric analysis](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/evaluate.py): `src/evaluate.py`
- [Diagnostic plots](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/visualize.py): `src/visualize.py`

### Application runtime

- [Run configuration](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/src/config.py): `src/config.py`
- [Pipeline entry](https://github.com/aryan-sz13/aiml-recruitment-2026-aryan-singh/blob/main/main.py): `main.py`

### Other components

- **Assessment user**
- **MNIST mirror**

## Connections

- Assessment user → Pipeline entry: runs pipeline (evidence: `main.py`)
- Pipeline entry → Run configuration: ensures directories (evidence: `main.py`)
- Pipeline entry → Data preparation: loads data (evidence: `main.py`)
- Data preparation → Dataset download: downloads missing files (evidence: `src/data.py`)
- MNIST mirror → Dataset download: provides archives (evidence: `src/mnist_download.py`)
- Data preparation → IDX parser: loads IDX samples (evidence: `src/data.py`)
- Pipeline entry → Ablation suite: runs suite (evidence: `main.py`)
- Ablation suite → Run configuration: uses settings (evidence: `src/experiment.py`)
- Ablation suite → Data preparation: loads data (evidence: `src/experiment.py`)
- Ablation suite → MLP builder: builds variants (evidence: `src/experiment.py`)
- Ablation suite → Model training: trains variants (evidence: `src/experiment.py`)
- Ablation suite → Metric analysis: evaluates models (evidence: `src/experiment.py`)
- Pipeline entry → Metric analysis: finds error cases (evidence: `main.py`)
- Pipeline entry → Diagnostic plots: renders diagnostics (evidence: `main.py`)
