This project demonstrates handwritten digit recognition using a neural network model. The model is trained on the MNIST dataset, which consists of a large collection of labeled handwritten digits.
- Python 3.6+
- TensorFlow 2.0+
- NumPy
- Pandas
- Matplotlib
- seaborn
- Clone the repository: git clone https://github.com/astrophile481/Handwritten-Digit-Recognition-with-NN.git
- Change into the project directory: cd Handwritten-Digit-Recognition-with-NN
-
Run the Python script: python3 Model.py
-
The script will download the MNIST dataset, preprocess the data, train the neural network model, and evaluate its performance.
-
After the model is trained, you will be prompted to enter an index from 0 to 10000 to perform a prediction on a handwritten digit from the test set.
-
The predicted digit and the corresponding image will be displayed on the screen.
-
Finally, a confusion matrix will be generated, visualizing the performance of the model.
This project is licensed under the MIT License.
Feel free to use and modify the code as per your needs.
- The MNIST dataset used in this project is available at http://yann.lecun.com/exdb/mnist/.
- This project is inspired by the tutorial on TensorFlow's website: https://www.tensorflow.org/tutorials/quickstart/beginner.
you can also interprete the model in the jupyter notebook by opening the notebook file