This repository contains a Jupyter Notebook demonstrating a handwritten digit recognition model trained using TensorFlow and Keras on the MNIST dataset.
The handwritten digit recognition model utilizes a convolutional neural network (CNN) architecture to classify images of handwritten digits into their respective numerical values (0-9). The model is trained on the MNIST dataset, which consists of 28x28 pixel grayscale images of handwritten digits.
- Training the Model: Users can train the model using the MNIST training dataset, adjusting hyperparameters such as the number of epochs and batch size.
- Evaluating Model Accuracy: After training, users can evaluate the model's accuracy on the MNIST test dataset to assess its performance on unseen data.
- Making Predictions: Users can upload their own handwritten digit images or use images from the MNIST test dataset to make predictions using the trained model.
- Clone the Repository: Clone this repository to your local machine using the command
git clone https://github.com/harshala334/Handwritten-digit-recognition.git. - Install Dependencies: Install the required dependencies (Python, TensorFlow, Keras, Jupyter Notebook) using
pip install tensorflow keras jupyter. - Open the Jupyter Notebook: Navigate to the cloned repository directory and run
jupyter notebook handwritten_digit_recognition.ipynb. - Interact with the Model: Follow the instructions in the notebook to train the model, evaluate its accuracy, and make predictions on handwritten digit images.
This project is licensed under the MIT License - see the LICENSE file for details.