{"id":27926021,"url":"https://github.com/enesgunumdogdu/cnn.improvements","last_synced_at":"2026-05-03T23:31:35.736Z","repository":{"id":291470786,"uuid":"977220387","full_name":"enesgunumdogdu/CNN.Improvements","owner":"enesgunumdogdu","description":"This project implements a Convolutional Neural Network (CNN) for digit classification with an interactive web interface. Users can draw digits and get real-time predictions from the trained model.","archived":false,"fork":false,"pushed_at":"2025-05-04T20:35:18.000Z","size":2092,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-07T00:51:39.237Z","etag":null,"topics":["cnn","flask","keras","python"],"latest_commit_sha":null,"homepage":"https://enesgunumdogdu.com.tr/","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/enesgunumdogdu.png","metadata":{"files":{"readme":"Readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"zenodo":null}},"created_at":"2025-05-03T17:40:11.000Z","updated_at":"2025-05-04T20:35:21.000Z","dependencies_parsed_at":"2025-05-07T00:51:03.900Z","dependency_job_id":null,"html_url":"https://github.com/enesgunumdogdu/CNN.Improvements","commit_stats":null,"previous_names":["enesgunumdogdu/cnn.improvements"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/enesgunumdogdu/CNN.Improvements","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enesgunumdogdu%2FCNN.Improvements","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enesgunumdogdu%2FCNN.Improvements/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enesgunumdogdu%2FCNN.Improvements/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enesgunumdogdu%2FCNN.Improvements/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/enesgunumdogdu","download_url":"https://codeload.github.com/enesgunumdogdu/CNN.Improvements/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/enesgunumdogdu%2FCNN.Improvements/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273377153,"owners_count":25094528,"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","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cnn","flask","keras","python"],"created_at":"2025-05-07T00:51:00.839Z","updated_at":"2026-05-03T23:31:35.731Z","avatar_url":"https://github.com/enesgunumdogdu.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🎨 Interactive Digit Classifier with CNN\n\nA web-based digit recognition system powered by deep learning. This project implements a Convolutional Neural Network (CNN) trained on the MNIST dataset, featuring an interactive drawing canvas for real-time digit classification.\n\n![image](https://github.com/user-attachments/assets/3db0ee60-03d2-4b06-ab22-72a1e940685a)\n\n## 📋 Table of Contents\n- [Overview](#overview)\n- [Features](#features)\n- [Technology Stack](#technology-stack)\n- [Model Architecture](#model-architecture)\n- [Installation](#installation)\n- [Usage](#usage)\n- [Project Structure](#project-structure)\n- [License](#license)\n\n## 🎯 Overview\n\nThis project demonstrates handwritten digit recognition using deep learning. It uses a CNN model trained on the MNIST dataset with a Flask web interface where users can draw digits and get predictions.\n\n## ✨ Features\n\n- **Interactive Drawing Canvas**: Draw digits with your mouse\n- **CNN Model**: Trained on MNIST dataset for digit classification (0-9)\n- **Real-time Predictions**: Get instant predictions as you draw\n- **Confidence Scores**: Displays confidence percentage for each prediction\n- **Error Handling**: Returns a message when the drawing is not clear (confidence \u003c 50%)\n- **Clear Button**: Reset the canvas to draw again\n\n## 🛠️ Technology Stack\n\n- **Flask** - Web framework for the application\n- **TensorFlow/Keras** - Deep learning framework for model training\n- **NumPy** - Numerical operations\n- **Pillow** - Image processing\n- **HTML5 Canvas** - Drawing interface\n- **JavaScript** - Client-side interaction\n\n## 🏗️ Model Architecture\n\nThe CNN model consists of the following layers:\n\n```\nInput Layer (28x28x1)\n    ↓\nConv2D (32 filters, 3x3, ReLU)\n    ↓\nMaxPooling2D (2x2)\n    ↓\nConv2D (64 filters, 3x3, ReLU)\n    ↓\nMaxPooling2D (2x2)\n    ↓\nConv2D (64 filters, 3x3, ReLU)\n    ↓\nFlatten\n    ↓\nDense (64 units, ReLU)\n    ↓\nDropout (0.5)\n    ↓\nDense (10 units, Softmax)\n```\n\n**Training Configuration:**\n- Optimizer: Adam (learning_rate=0.001)\n- Loss: categorical_crossentropy\n- Epochs: 20\n- Batch Size: 64\n- Validation Split: 0.2\n\n## 📦 Installation\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/your-username/CNN.Improvements.git\ncd CNN.Improvements\n```\n\n2. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## 🚀 Usage\n\n1. Train the model:\n```bash\npython test.py\n```\nThis will train the CNN model and save it as `mnist_model.h5`.\n\n2. Start the Flask application:\n```bash\npython app.py\n```\n\n3. Open your browser and go to `http://localhost:5000`\n\n4. Draw a digit (0-9) on the canvas and see the prediction with confidence score. Click \"Clear\" to reset.\n\n## 📁 Project Structure\n\n```\nCNN.Improvements/\n│\n├── app.py                 # Flask web application\n├── test.py                # Model training script\n├── requirements.txt       # Python dependencies\n├── mnist_model.h5         # Trained model file (generated after running test.py)\n├── Readme.md              # Documentation\n│\n└── templates/\n    └── index.html         # Web interface with drawing canvas\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fenesgunumdogdu%2Fcnn.improvements","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fenesgunumdogdu%2Fcnn.improvements","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fenesgunumdogdu%2Fcnn.improvements/lists"}