# sarthakdem18/hrm architecture

> Architecture diagram of the GitHub repository sarthakdem18/hrm, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-17). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sarthakdem18/hrm
- Repository: https://github.com/sarthakdem18/hrm

## Overview

This is an end-to-end MNIST digit-classification project: training loads and preprocesses data, trains and evaluates a CNN, and saves a model; prediction accepts an image or demonstrates predictions on MNIST test samples. The README also describes an interactive notebook and project/viva documentation. Training and inference relationships below are grounded in the excerpts; notebook behavior is documented but its source was not sampled.

Main entry points: [`handwritten_digit_recognition/train.py`](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py) (Training pipeline), [`handwritten_digit_recognition/predict.py`](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py) (Prediction entry point), [`handwritten_digit_recognition/outputs`](https://github.com/sarthakdem18/hrm/tree/main/handwritten_digit_recognition/outputs) (Generated plots), [`handwritten_digit_recognition/model/digit_cnn.keras`](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/model/digit_cnn.keras) (Saved CNN model)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_training["Training"]
  node_data_prep["Data loading and preprocessing<br/>[train.py]"]
  node_sample_plot["Sample digit plot<br/>[train.py]"]
  node_cnn["CNN architecture<br/>[train.py]"]
  node_trainer["Training pipeline<br/>[train.py]"]
  node_model_artifact["Saved CNN model<br/>[digit_cnn.keras]"]
end

subgraph group_evaluation["Evaluation"]
  node_evaluation["Test evaluation<br/>[train.py]"]
  node_training_plots["Training curves<br/>[train.py]"]
  node_evaluation_plots["Evaluation visualizations<br/>[train.py]"]
  node_outputs["Generated plots"]
end

subgraph group_inference["Inference"]
  node_predict_cli["Prediction entry point<br/>[predict.py]"]
  node_image_prep["Image preprocessing<br/>[predict.py]"]
  node_model_loader["Model loading<br/>[predict.py]"]
  node_digit_predictor["Digit prediction<br/>[predict.py]"]
end

subgraph group_learning["Learning materials"]
  node_notebook["Interactive notebook"]
  node_project_guide["Project documentation"]
end

node_user(("User"))
node_mnist[("MNIST dataset")]

node_user -->|"runs training"| node_trainer
node_trainer -->|"loads and preprocesses"| node_data_prep
node_data_prep -->|"loads dataset"| node_mnist
node_data_prep -->|"creates sample plot"| node_sample_plot
node_trainer -->|"builds model"| node_cnn
node_trainer -->|"saves model"| node_model_artifact
node_trainer -->|"plots training history"| node_training_plots
node_trainer -->|"evaluates model"| node_evaluation
node_evaluation -->|"plots results"| node_evaluation_plots
node_sample_plot -->|"writes image"| node_outputs
node_training_plots -->|"writes curves"| node_outputs
node_evaluation_plots -->|"writes plots"| node_outputs
node_user -->|"runs prediction"| node_predict_cli
node_predict_cli -->|"loads demo samples"| node_mnist
node_predict_cli -->|"loads model"| node_model_loader
node_model_loader -->|"reads model"| node_model_artifact
node_predict_cli -->|"predicts samples"| node_digit_predictor
node_digit_predictor -->|"preprocesses image"| node_image_prep
node_digit_predictor -->|"loads when needed"| node_model_loader
node_user -->|"opens notebook"| node_notebook
node_user -->|"consults guide"| node_project_guide

click node_data_prep "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_sample_plot "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_cnn "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_trainer "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_model_artifact "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/model/digit_cnn.keras"
click node_evaluation "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_training_plots "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_evaluation_plots "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py"
click node_predict_cli "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py"
click node_image_prep "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py"
click node_model_loader "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py"
click node_digit_predictor "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py"
click node_notebook "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/notebooks/handwritten_digit_recognition.ipynb"
click node_project_guide "https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/documentation/project_documentation.md"
click node_outputs "https://github.com/sarthakdem18/hrm/tree/main/handwritten_digit_recognition/outputs"

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_data_prep,node_sample_plot,node_cnn,node_trainer,node_model_artifact,node_user toneBlue
class node_evaluation,node_training_plots,node_evaluation_plots,node_outputs,node_mnist toneAmber
class node_predict_cli,node_image_prep,node_model_loader,node_digit_predictor toneMint
class node_notebook,node_project_guide toneRose
```

## Components

### Training

- [Data loading and preprocessing](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Sample digit plot](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [CNN architecture](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Training pipeline](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Saved CNN model](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/model/digit_cnn.keras): `handwritten_digit_recognition/model/digit_cnn.keras`

### Evaluation

- [Test evaluation](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Training curves](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Evaluation visualizations](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/train.py): `handwritten_digit_recognition/train.py`
- [Generated plots](https://github.com/sarthakdem18/hrm/tree/main/handwritten_digit_recognition/outputs): `handwritten_digit_recognition/outputs`

### Inference

- [Prediction entry point](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py): `handwritten_digit_recognition/predict.py`
- [Image preprocessing](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py): `handwritten_digit_recognition/predict.py`
- [Model loading](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py): `handwritten_digit_recognition/predict.py`
- [Digit prediction](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/predict.py): `handwritten_digit_recognition/predict.py`

### Learning materials

- [Interactive notebook](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/notebooks/handwritten_digit_recognition.ipynb): `handwritten_digit_recognition/notebooks/handwritten_digit_recognition.ipynb`
- [Project documentation](https://github.com/sarthakdem18/hrm/blob/main/handwritten_digit_recognition/documentation/project_documentation.md): `handwritten_digit_recognition/documentation/project_documentation.md`

### Other components

- **User**
- **MNIST dataset**

## Connections

- User → Training pipeline: runs training (evidence: `README.md`)
- Training pipeline → Data loading and preprocessing: loads and preprocesses (evidence: `handwritten_digit_recognition/train.py`)
- Data loading and preprocessing → MNIST dataset: loads dataset (evidence: `handwritten_digit_recognition/train.py`)
- Data loading and preprocessing → Sample digit plot: creates sample plot (evidence: `handwritten_digit_recognition/train.py`)
- Training pipeline → CNN architecture: builds model (evidence: `handwritten_digit_recognition/train.py`)
- Training pipeline → Saved CNN model: saves model (evidence: `handwritten_digit_recognition/train.py`)
- Training pipeline → Training curves: plots training history (evidence: `handwritten_digit_recognition/train.py`)
- Training pipeline → Test evaluation: evaluates model (evidence: `handwritten_digit_recognition/train.py`)
- Test evaluation → Evaluation visualizations: plots results (evidence: `handwritten_digit_recognition/train.py`)
- Sample digit plot → Generated plots: writes image (evidence: `handwritten_digit_recognition/train.py`)
- Training curves → Generated plots: writes curves (evidence: `handwritten_digit_recognition/train.py`)
- Evaluation visualizations → Generated plots: writes plots (evidence: `handwritten_digit_recognition/train.py`)
- User → Prediction entry point: runs prediction (evidence: `README.md`)
- Prediction entry point → MNIST dataset: loads demo samples (evidence: `handwritten_digit_recognition/predict.py`)
- Prediction entry point → Model loading: loads model (evidence: `handwritten_digit_recognition/predict.py`)
- Model loading → Saved CNN model: reads model (evidence: `handwritten_digit_recognition/predict.py`)
- Prediction entry point → Digit prediction: predicts samples (evidence: `handwritten_digit_recognition/predict.py`)
- Digit prediction → Image preprocessing: preprocesses image (evidence: `handwritten_digit_recognition/predict.py`)
- Digit prediction → Model loading: loads when needed (evidence: `handwritten_digit_recognition/predict.py`)
- User → Interactive notebook: opens notebook (evidence: `README.md`)
- User → Project documentation: consults guide (evidence: `README.md`)
