The objective of this project is to develop a robust digit classification model capable of accurately identifying handwritten digits. The model is trained and evaluated using the MNIST dataset, a standard benchmark in the field of machine learning.
The MNIST dataset comprises numerical arrays of 70,000 grayscale images of handwritten digits, each sized at 28x28 pixels. It is divided into 60,000 training images and 10,000 testing images. Each image is labeled with the corresponding digit (0-9).
To run the code in this repository, follow these steps:
- Clone the repository:
git clone https://github.com/HMNS19/digit-classification.git
- Navigate to the project directory:
cd digit-classification- Install the required dependencies:
pip install numpy pandas matplotlib seaborn scikit-learn tensorflow- Open the Jupyter Notebook:
jupyter notebook main.ipynb- Run the Notebook
We welcome contributions to this repository! Follow the steps below to get started:
Click the Fork button in the top-right corner of the repository to create your copy.
Clone your forked repository to your local machine:
git clone https://github.com/<your-username>/digit-classification.git
cd digit-classificationInstall the required dependencies:
pip install numpy pandas matplotlib seaborn scikit-learn tensorflowCreate a new branch for your feature or bug fix:
git checkout -b <branch-name>Implement your changes or additions in the appropriate files.
Verify your changes work as intended. For example, rerun the Jupyter Notebook or relevant tests.
Commit your changes with a clear and descriptive message:
git add .
git commit -m "Description of the changes"
git push origin <branch-name>Navigate to the original repository on GitHub. Click on Pull Requests > New Pull Request. Select your branch and describe the changes in detail.
This project is licensed under the MIT License. See the LICENSE file for details