{"id":24534381,"url":"https://github.com/codeofrahul/digit_classification_using_cnn","last_synced_at":"2026-04-19T10:33:15.193Z","repository":{"id":273674939,"uuid":"920502088","full_name":"CodeofRahul/Digit_Classification_using_CNN","owner":"CodeofRahul","description":"This project demonstrates the implementation of a Convolutional Neural Network (CNN) for classifying handwritten digits using the MNIST dataset. The model is built using Keras and TensorFlow, leveraging the power of deep learning for image recognition tasks.","archived":false,"fork":false,"pushed_at":"2025-01-22T09:37:09.000Z","size":1464,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-22T10:27:05.665Z","etag":null,"topics":["keras","matplotlib","python","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CodeofRahul.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":"2025-01-22T09:11:28.000Z","updated_at":"2025-01-22T09:38:34.000Z","dependencies_parsed_at":"2025-01-22T10:37:14.779Z","dependency_job_id":null,"html_url":"https://github.com/CodeofRahul/Digit_Classification_using_CNN","commit_stats":null,"previous_names":["codeofrahul/digit_classification_using_cnn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FDigit_Classification_using_CNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FDigit_Classification_using_CNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FDigit_Classification_using_CNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CodeofRahul%2FDigit_Classification_using_CNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CodeofRahul","download_url":"https://codeload.github.com/CodeofRahul/Digit_Classification_using_CNN/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243797610,"owners_count":20349432,"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":["keras","matplotlib","python","tensorflow"],"created_at":"2025-01-22T11:17:02.953Z","updated_at":"2026-04-19T10:33:15.139Z","avatar_url":"https://github.com/CodeofRahul.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Digit_Classification_using_CNN\nThis project demonstrates the implementation of a Convolutional Neural Network (CNN) for classifying handwritten digits using the MNIST dataset. The model is built using Keras and TensorFlow, leveraging the power of deep learning for image recognition tasks.\n\n## Key Features\n\n- **Data Preprocessing:** The MNIST dataset is loaded and preprocessed, including reshaping and min-max scaling, to optimize model training.\n- **CNN Architecture:** A carefully designed CNN architecture is employed, incorporating convolutional, pooling, and fully connected layers to extract features and perform classification.\n- **Model Training and Evaluation:** The model is trained on the training data and evaluated on the testing data to assess its performance. Accuracy and loss metrics are used to gauge the model's effectiveness.\n- **Visualization:** Matplotlib is used to visualize the handwritten digits and display the model's predictions.\n\n---\n\n## 📊 Dataset\n\nThe **MNIST dataset** consists of 70,000 grayscale images of handwritten digits (0-9):\n\n- **Training Set:** 60,000 images\n- **Test Set:** 10,000 images\n\nEach image is a 28x28 pixel matrix, with each pixel representing grayscale intensity.\n\n---\n\n## 🚀 Methodology\n\n1. **Data Preprocessing:**\n   - Normalized pixel values to a range of 0 to 1.\n   - Reshaped images to include the channel dimension (28x28x1).\n   - One-hot encoded the labels.\n\n2. **Model Architecture:**\n   - Convolutional Layers: Extract spatial features using 32 and 64 filters.\n   - Pooling Layers: Reduce spatial dimensions and computational complexity.\n   - Dense Layers: Perform high-level reasoning for classification.\n   - Softmax Output: Predicts probabilities for each class.\n\n3. **Training:**\n   - **Loss Function:** Categorical Cross-Entropy.\n   - **Optimizer:** sgd.\n   - **Metrics:** Accuracy.\n\n4. **Evaluation:**\n   - Assessed model performance on the test set.\n   - Visualized misclassified examples for deeper insights.\n\n---\n\n## 📈 Results\n\n- **Training Accuracy:** 99%\n- **Validation Accuracy:** 98%\n- **Test Accuracy:** 98%\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeofrahul%2Fdigit_classification_using_cnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcodeofrahul%2Fdigit_classification_using_cnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcodeofrahul%2Fdigit_classification_using_cnn/lists"}