https://github.com/rvats20/digit-recognizer
This competition is the perfect introduction to techniques like neural networks using a classic dataset including pre-extracted features.
https://github.com/rvats20/digit-recognizer
computer-vision digit-recognition kaggle kaggle-competition machine-learning-algorithms python-3
Last synced: about 2 months ago
JSON representation
This competition is the perfect introduction to techniques like neural networks using a classic dataset including pre-extracted features.
- Host: GitHub
- URL: https://github.com/rvats20/digit-recognizer
- Owner: rvats20
- License: mit
- Created: 2024-11-16T16:15:33.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-14T11:15:52.000Z (over 1 year ago)
- Last Synced: 2025-01-27T18:43:04.201Z (over 1 year ago)
- Topics: computer-vision, digit-recognition, kaggle, kaggle-competition, machine-learning-algorithms, python-3
- Language: Jupyter Notebook
- Homepage: https://rvats20.github.io/portfolio/
- Size: 928 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Digit Recognizer
Welcome to the **Digit Recognizer** repository! This project is part of a Kaggle competition aimed at developing models to recognize handwritten digits from the famous MNIST dataset.
## Table of Contents
- Introduction
- Competition Overview
- Project Structure
- Installation
- Usage
- Results
- Contributing
- License
- Contact
## Introduction
Handwritten digit recognition is a classic problem in the field of computer vision and machine learning. This repository contains the code and resources used to participate in the Kaggle Digit Recognizer competition, where the goal is to correctly identify digits (0-9) from a dataset of handwritten images.
## Competition Overview
- **Host**: Kaggle
- **Objective**: Build a model to accurately recognize handwritten digits.
- **Dataset**: MNIST dataset, consisting of 60,000 training images and 10,000 test images.
- **Evaluation Metric**: Accuracy of the model on the test set.
## Installation
To get started with this project, clone the repository and install the required dependencies:
```bash
git clone https://github.com/yourusername/Digit-Recognizer.git
cd Digit-Recognizer
pip install -r requirements.txt
```
## Usage
1. **Data Preprocessing**: Prepare the dataset for training and evaluation.
```bash
python src/data_preprocessing.py
```
2. **Train the Model**: Train the digit recognition model on the prepared dataset.
```bash
python src/model_training.py
```
3. **Evaluate the Model**: Assess the performance of the trained model.
```bash
python src/model_evaluation.py
```
## Results
Our model achieved an impressive accuracy of **XX.XX%** on the test set, demonstrating its effectiveness in recognizing handwritten digits. Detailed results and analysis can be found in the `Model_Evaluation.ipynb` notebook.
## Contributing
We welcome contributions from the community! If you have any suggestions or improvements, please feel free to submit a pull request or open an issue.
## License
This project is licensed under the MIT License. See the LICENSE file for more details.
## Contact
For any questions or inquiries, please contact yourname.