{"id":26753159,"url":"https://github.com/uni-creator/handwritten_number_recognition_system","last_synced_at":"2026-04-17T07:31:36.803Z","repository":{"id":284152979,"uuid":"953993808","full_name":"Uni-Creator/Handwritten_Number_Recognition_System","owner":"Uni-Creator","description":"A Handwritten Number Recognition System built from scratch using Deep Learning from Scratch. The model is trained on digit images and can classify handwritten numbers with high accuracy.","archived":false,"fork":false,"pushed_at":"2025-03-24T12:06:15.000Z","size":19866,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-24T13:23:49.422Z","etag":null,"topics":["computer-vision","deep-learning","handwritten-digit-recognition","image-processing","implementation-from-scratch","minst","nueral-networks","numpy","pandas","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Uni-Creator.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-24T12:01:08.000Z","updated_at":"2025-03-24T12:12:26.000Z","dependencies_parsed_at":"2025-03-24T13:33:58.483Z","dependency_job_id":null,"html_url":"https://github.com/Uni-Creator/Handwritten_Number_Recognition_System","commit_stats":null,"previous_names":["uni-creator/handwritten_number_recognition_system"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Uni-Creator%2FHandwritten_Number_Recognition_System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Uni-Creator%2FHandwritten_Number_Recognition_System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Uni-Creator%2FHandwritten_Number_Recognition_System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Uni-Creator%2FHandwritten_Number_Recognition_System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Uni-Creator","download_url":"https://codeload.github.com/Uni-Creator/Handwritten_Number_Recognition_System/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246034312,"owners_count":20712857,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["computer-vision","deep-learning","handwritten-digit-recognition","image-processing","implementation-from-scratch","minst","nueral-networks","numpy","pandas","pytorch"],"created_at":"2025-03-28T13:18:01.362Z","updated_at":"2026-04-17T07:31:36.747Z","avatar_url":"https://github.com/Uni-Creator.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Handwritten Number Recognition System\n![GitHub Repo stars](https://img.shields.io/github/stars/Uni-Creator/Handwritten_Number_Recognition_System?style=social)  ![GitHub forks](https://img.shields.io/github/forks/Uni-Creator/Handwritten_Number_Recognition_System?style=social)\n\n## 📌 Overview\nThe **Handwritten Number Recognition System** is a deep learning model built from scratch to classify handwritten digits using a custom neural network. It is trained on the MNIST dataset and utilizes NumPy-based implementation for forward and backward propagation.\n\n## 🚀 Features\n- **Custom-built Neural Network**: Implemented using NumPy without deep learning frameworks like TensorFlow or PyTorch.\n- **Forward \u0026 Backward Propagation**: Includes ReLU and Tanh activation functions for optimization.\n- **Model Training \u0026 Evaluation**: Supports training on both CPU and GPU.\n- **Manual \u0026 Automated Testing**: Test the model using predefined test images or random inputs.\n- **Performance Metrics**: Displays accuracy and prediction confidence.\n\n## 🏗️ Tech Stack\n- **Python**\n- **NumPy** (for matrix computations)\n- **Matplotlib** (for visualization)\n- **Pandas** (for data handling)\n- **GPU Support** (via CUDA for optimized training)\n\n## 📂 Project Structure\n```\nHandwritten_Number_Recognition_System/\n│── data/                     # Dataset storage\n│── main.py                   # Loads trained model and tests data\n│── model.npz                 # Saved model parameters\n│── trainer.py                # Trains the neural network model\n│── trainOnGPU.py             # Optimized training for GPU acceleration\n│── README.md                 # Project documentation\n```\n\n## 📦 Installation \u0026 Setup\n1. **Clone the repository**\n   ```sh\n   git clone https://github.com/Uni-Creator/Handwritten_Number_Recognition_System.git\n   cd Handwritten_Number_Recognition_System\n   ```\n2. **Install dependencies**\n   ```sh\n   pip install numpy pandas matplotlib\n   ```\n3. **Train the model (if needed)**\n   ```sh\n   python trainer.py\n   ```\n4. **Run the model for testing**\n   ```sh\n   python main.py\n   ```\n\n## 📊 How It Works\n1. The model loads pre-trained weights from `model.npz` or `model.pth`.\n2. A test image is provided for prediction.\n3. The model outputs a digit classification with confidence score.\n4. The prediction is displayed along with the corresponding test image.\n\n## 🛠️ Future Improvements\n- Implement CNN-based architecture for improved accuracy.\n- Add a web interface for user-uploaded handwritten digit classification.\n- Support for different datasets beyond MNIST.\n\n## 🤝 Contributing\nContributions are welcome! Feel free to open an **issue** or submit a **pull request**.\n\n## 📄 License\nThis project is licensed under the **Apache-2.0 license**.\n\n---\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funi-creator%2Fhandwritten_number_recognition_system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funi-creator%2Fhandwritten_number_recognition_system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funi-creator%2Fhandwritten_number_recognition_system/lists"}