DigitsInk is a project that demonstrates the use of PyTorch and the torchvision library to train a neural network on the MNIST dataset for handwritten digit recognition.
The goal of this project is to build a machine learning model that can accurately recognize handwritten digits using the MNIST dataset. The MNIST dataset is a collection of 70,000 images of handwritten digits (0-9) that has been widely used for training and testing in the field of machine learning.
To run this project, you need to have Python installed along with some specific libraries. You can install the necessary dependencies using the following commands:
pip install torch torchvision matplotlibEnsure you have a working environment with Jupyter Notebook to run the notebook.
-
Clone the repository:
git clone https://github.com/your-username/DigitsInk.git cd DigitsInk -
Open the Jupyter Notebook:
jupyter notebook DigitsInk.ipynb
-
Run the cells in the notebook sequentially to load the data, train the model, and evaluate its performance.
The project contains the following files:
DigitsInk.ipynb: The main Jupyter Notebook file containing the code for loading data, training the model, and evaluating its performance.README.md: This README file.
The MNIST dataset is automatically downloaded when you run the notebook. It consists of:
- 60,000 training images
- 10,000 test images
Each image is a 28x28 grayscale image of a handwritten digit.
After running the notebook, the trained model's performance will be evaluated on the test dataset. The results, including accuracy and sample predictions, will be displayed within the notebook.
Contributions are welcome! If you have any improvements or suggestions, feel free to open an issue or submit a pull request.
This project is licensed under the MIT License. See the LICENSE file for more details.