{"id":30713933,"url":"https://github.com/tasninanika/convolutional_neural_network-cnn","last_synced_at":"2026-05-06T18:32:05.043Z","repository":{"id":311708478,"uuid":"1044672563","full_name":"tasninanika/Convolutional_Neural_Network-CNN","owner":"tasninanika","description":"A deep learning project to classify handwritten digits (0–9) using a Convolutional Neural Network (CNN). This project builds a CNN model with TensorFlow/Keras to classify digits with high accuracy.","archived":false,"fork":false,"pushed_at":"2025-08-26T03:53:41.000Z","size":144,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-26T05:36:54.363Z","etag":null,"topics":["keras","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tasninanika.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":"2025-08-26T03:36:48.000Z","updated_at":"2025-08-26T03:55:05.000Z","dependencies_parsed_at":"2025-08-26T05:48:09.372Z","dependency_job_id":null,"html_url":"https://github.com/tasninanika/Convolutional_Neural_Network-CNN","commit_stats":null,"previous_names":["tasninanika/convolutional_neural_network-cnn"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/tasninanika/Convolutional_Neural_Network-CNN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tasninanika%2FConvolutional_Neural_Network-CNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tasninanika%2FConvolutional_Neural_Network-CNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tasninanika%2FConvolutional_Neural_Network-CNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tasninanika%2FConvolutional_Neural_Network-CNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tasninanika","download_url":"https://codeload.github.com/tasninanika/Convolutional_Neural_Network-CNN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tasninanika%2FConvolutional_Neural_Network-CNN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273387410,"owners_count":25096362,"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":["keras","tensorflow"],"created_at":"2025-09-03T04:09:30.449Z","updated_at":"2026-05-06T18:32:05.001Z","avatar_url":"https://github.com/tasninanika.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🔢 MNIST Digit Classification using CNN\n\nA deep learning project to classify **handwritten digits (0–9)** using a **Convolutional Neural Network (CNN)**. The model is trained on the **MNIST dataset**.\n\n---\n\n## 📌 Project Overview\n\nThe **MNIST dataset** is a benchmark dataset in machine learning and computer vision. It consists of grayscale images of handwritten digits.\n\nThis project builds a **CNN model with TensorFlow/Keras** to classify digits with high accuracy.\n\n---\n\n## 📂 Dataset\n\n* **Source:** [MNIST Dataset](http://yann.lecun.com/exdb/mnist/) (also available via `keras.datasets.mnist`)\n* **Training Samples:** 60,000\n* **Test Samples:** 10,000\n* **Image Size:** 28 × 28 pixels (grayscale)\n* **Classes:** 10 (digits 0–9)\n\n---\n\n## ⚙️ Tech Stack\n\n![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge\\\u0026logo=python\\\u0026logoColor=white)\n![NumPy](https://img.shields.io/badge/Numpy-013243?style=for-the-badge\\\u0026logo=numpy\\\u0026logoColor=white)\n![Matplotlib](https://img.shields.io/badge/Matplotlib-11557c?style=for-the-badge\\\u0026logo=plotly\\\u0026logoColor=white)\n![TensorFlow](https://img.shields.io/badge/TensorFlow-FF6F00?style=for-the-badge\\\u0026logo=tensorflow\\\u0026logoColor=white)\n![Keras](https://img.shields.io/badge/Keras-D00000?style=for-the-badge\\\u0026logo=keras\\\u0026logoColor=white)\n\n---\n\n## 🛠️ Project Workflow\n\n### 🔹 Data Preprocessing\n\n* Loaded MNIST dataset from `keras.datasets`\n* Normalized pixel values (0–255 → 0–1)\n* Reshaped data for CNN input (`28x28x1`)\n* One-hot encoded target labels\n\n### 🔹 CNN Architecture\n\n* **Conv2D + ReLU + MaxPooling** layers\n* **Flatten** layer\n* **Dense (Fully Connected)** layers\n* **Output layer** with Softmax activation\n\n### 🔹 Model Training\n\n* **Optimizer:** Adam\n* **Loss Function:** Categorical Crossentropy\n* **Metrics:** Accuracy\n* Trained for multiple epochs with batch size tuning\n\n### 🔹 Evaluation\n\n* Achieved **\\~99% training accuracy**\n* Achieved **\\~98% test accuracy**\n* Visualized predictions with sample test images\n\n---\n\n## 📊 Results\n\n✔️ High accuracy (\u003e98%) on test data\n\n✔️ Robust CNN architecture with minimal overfitting\n\n✔️ Correctly classifies handwritten digits\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftasninanika%2Fconvolutional_neural_network-cnn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftasninanika%2Fconvolutional_neural_network-cnn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftasninanika%2Fconvolutional_neural_network-cnn/lists"}