This is a digit recognizer app that utilizes artificial neural networks (ANN) and convolutional neural networks (CNN) for recognizing hand-written digits. The app is built with Next.js for the frontend, Flask for the backend, and includes components for training and testing the models.
- Handwritten digit recognition using ANN and CNN
- User-friendly web interface built with Next.js
- Backend server powered by Flask
- Model training and testing functionality
- Next.js
- Flask
- Python
- TensorFlow (for ANN and CNN models)
-
Clone the repository:
git clone https://github.com/shivam6862/Digit-Recognizer.git
-
Install dependencies:
cd digit-recognizer/frontend npm install
cd digit-recognizer/backend pip install -r requirements.txt
-
Run the development server:
npm run dev
cd backend python main.py
The app will be accessible at
http://localhost:3000
.
-
Navigate to the web interface in your browser.
-
Upload the image in my app.
-
Click the "Recognize" button to see the model's prediction.
-
Explore the training section to train and test new models.
To train new models, follow these steps:
-
Prepare a dataset of hand-written digits.
-
Place the dataset in the
data
directory.
If you'd like to contribute to this project, please follow the guidelines in CONTRIBUTING.md.
This project is licensed under the MIT License.
- Special thanks to shivam6862 for contributing to the project.