{"id":28576212,"url":"https://github.com/prodev717/handwritten_digit_classification","last_synced_at":"2025-07-25T18:40:42.471Z","repository":{"id":291763436,"uuid":"978698297","full_name":"prodev717/handwritten_digit_classification","owner":"prodev717","description":"Handwritten Digit Classification using CNN","archived":false,"fork":false,"pushed_at":"2025-05-06T11:49:01.000Z","size":339,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-10T23:08:49.408Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/prodev717.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":"2025-05-06T11:34:02.000Z","updated_at":"2025-05-06T11:49:04.000Z","dependencies_parsed_at":"2025-05-06T12:52:25.670Z","dependency_job_id":"8eb8c32c-c575-4b24-80f3-147eb09847dc","html_url":"https://github.com/prodev717/handwritten_digit_classification","commit_stats":null,"previous_names":["prodev717/handwritten_digit_classification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/prodev717/handwritten_digit_classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prodev717%2Fhandwritten_digit_classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prodev717%2Fhandwritten_digit_classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prodev717%2Fhandwritten_digit_classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prodev717%2Fhandwritten_digit_classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/prodev717","download_url":"https://codeload.github.com/prodev717/handwritten_digit_classification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/prodev717%2Fhandwritten_digit_classification/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267046662,"owners_count":24026905,"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":"2025-07-25T02:00:09.625Z","response_time":70,"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":[],"created_at":"2025-06-10T23:08:39.314Z","updated_at":"2025-07-25T18:40:42.460Z","avatar_url":"https://github.com/prodev717.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Handwritten Digit Classification using CNN\n\nA deep learning project that classifies handwritten digits (0–9) using a Convolutional Neural Network (CNN) trained on the MNIST dataset. This project demonstrates the power of CNNs in solving image classification problems and forms a foundation for Optical Character Recognition (OCR) systems.\n\n## Project Overview\n\nThis project aims to build a high-accuracy digit recognizer that can identify handwritten numbers regardless of variations in writing style. It applies Convolutional Neural Networks for feature extraction and classification.\n\n## Author\n\n* Ganesh M \n* April 5, 2025\n\n---\n\n## Dataset\n\n* **Source**: MNIST Dataset (CSV Format)\n* **Samples**: 70,000 grayscale images (28x28 pixels)\n\n  * Training: 56,000\n  * Testing: 14,000\n* **Classes**: 10 (Digits 0 through 9)\n\nEach image is a 784-dimensional flattened vector with an associated label.\n\n---\n\n## Model Architecture\n\nThe CNN model consists of the following layers:\n\n1. **Conv2D** (32 filters, 3×3) → ReLU\n2. **MaxPooling2D** (2×2)\n3. **Conv2D** (64 filters, 3×3) → ReLU\n4. **MaxPooling2D** (2×2)\n5. **Flatten**\n6. **Dense** (128 units) → ReLU\n7. **Output Dense** (10 units - Softmax)\n\n---\n\n## Training Details\n\n* **Optimizer**: Adam\n* **Loss Function**: Categorical Crossentropy\n* **Metrics**: Accuracy\n* **Epochs**: 5 (adjustable)\n* **Batch Size**: 64 (adjustable)\n\n---\n\n## Evaluation\n\nThe model was evaluated on various metrics:\n\n* **Accuracy**: \\~99.7%\n* **Loss**: Monitored during training to ensure convergence\n* **Confusion Matrix**: Used for understanding class-wise performance\n\n---\n\n## Visualizations\n\n* Training \u0026 Validation Loss vs. Epoch\n* Training \u0026 Validation Accuracy vs. Epoch\n* Confusion Matrix (Test Set)\n* Sample Predictions (Correct \u0026 Incorrect)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprodev717%2Fhandwritten_digit_classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprodev717%2Fhandwritten_digit_classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprodev717%2Fhandwritten_digit_classification/lists"}