This repository contains a web application that demonstrates a deep learning model for handwritten digit recognition using TensorFlow.js and React.js. The model was trained with TensorFlow's Keras API on Python, and the resulting model was integrated into a React.js web application to provide a user-friendly interface for predicting handwritten digits.
You can try out the live demo of the MNIST-JS web application by visiting https://wasinuddy.github.io/MNIST-JS/.
- Handwritten digit recognition: Users can draw a digit on the canvas provided by the web application, and the deep learning model will predict the digit.
- TensorFlow.js integration: The trained model is deployed using TensorFlow.js, allowing it to run directly in the browser without the need for server-side computations.
- React.js user interface: The web application is built using React.js
Contributions to this project are highly encouraged and welcome. If you have ideas to improve the functionality or design of the web application, or if you want to fix any issues, please feel free to submit a pull request.
Here are some areas where contributions would be valuable:
- Improving the visual design: Enhancing the overall look and feel of the web application to make it more visually appealing and user-friendly.
- Adding new features: Introducing new functionalities to the web application to expand its capabilities and usefulness.
- Code optimization: Identifying and optimizing areas of the codebase to improve performance and maintainability.
- Bug fixes: Addressing any issues or bugs that may arise during usage.
This project is licensed under the MIT License.
