This project is a handwritten digit recognition model built using an Artificial Neural Network (ANN) trained on the MNIST dataset. The model predicts digits (0-9) from user-drawn images and is deployed using Streamlit for an interactive web application.
- ✅ Predicts digits (0-9) from handwritten input
- ✅ Interactive UI using Streamlit
- ✅ Pre-trained model for fast inference
- ✅ Simple and lightweight deployment
- Programming Language: Python
- Frameworks & Libraries: TensorFlow, Keras, NumPy, Pandas, Matplotlib
- Deployment: Streamlit
1️⃣ Clone the Repository
- git clone (https://github.com/Swami-Siva-Rama-Raju/MNIST-Handwritten-Digits-Prediction)
- cd mnist-digit-prediction\
2️⃣ Install Dependencies
- pip install -r requirements.txt
3️⃣ Run the Streamlit App
- streamlit run app.py
- Dataset: MNIST Handwritten Digits
- Model: ANN (Fully Connected Neural Network)
- Accuracy: ~98% on test data
- Loss: 0.05 (Cross Entropy Loss)
https://drive.google.com/file/d/1Q6Wh8ikJn4-AdX-ORfyYLJjELFT_V7J0/view?usp=sharing
- Want to improve this project? Follow these steps:
- Fork this repository
- Create a new branch: git checkout -b feature-name
- Commit your changes: git commit -m "Added a new feature"
- Push to the branch: git push origin feature-name
- Open a Pull Request
- 📧 Email: swamisivaramaraju@gmail.com
- 🔗 LinkedIn: www.linkedin.com/in/gorrela-swami-siva-rama-raju-07a570291