This project uses a PyTorch-based Convolutional Neural Network (CNN) trained on the MNIST dataset to recognise handwritten digits. It also provides a GUI where you can draw a digit and receive a prediction.
- CNN trained with PyTorch on MNIST.
- GUI for drawing digits using Tkinter.
- Model checkpoints saved for easy loading and inference.
pip install -r requirements.txt
python training.py
python gui.py
Draw a digit (0–9) in the canvas and click "Predict" to see the model’s prediction.