{"id":15066252,"url":"https://github.com/allanotieno254/mnist-digit-classification","last_synced_at":"2026-02-04T02:08:36.182Z","repository":{"id":256571281,"uuid":"855780891","full_name":"AllanOtieno254/mnist-digit-classification","owner":"AllanOtieno254","description":"building a machine learning model to classify handwritten digits using the MNIST dataset. ","archived":false,"fork":false,"pushed_at":"2024-09-13T12:30:26.000Z","size":11593,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-03T02:32:47.431Z","etag":null,"topics":["computer-vision","deep-learning","imageclassification","machine-learning","minst-database","neural-networks","notebook-jupyter","python","pytorch","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/AllanOtieno254.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}},"created_at":"2024-09-11T13:04:15.000Z","updated_at":"2024-09-13T12:30:29.000Z","dependencies_parsed_at":"2024-09-14T00:04:58.661Z","dependency_job_id":null,"html_url":"https://github.com/AllanOtieno254/mnist-digit-classification","commit_stats":null,"previous_names":["allanotieno254/mnist-dataset","allanotieno254/mnist-digit-classification"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllanOtieno254%2Fmnist-digit-classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllanOtieno254%2Fmnist-digit-classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllanOtieno254%2Fmnist-digit-classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AllanOtieno254%2Fmnist-digit-classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AllanOtieno254","download_url":"https://codeload.github.com/AllanOtieno254/mnist-digit-classification/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239274850,"owners_count":19611788,"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","imageclassification","machine-learning","minst-database","neural-networks","notebook-jupyter","python","pytorch","tensorflow"],"created_at":"2024-09-25T01:04:23.514Z","updated_at":"2026-02-04T02:08:36.140Z","avatar_url":"https://github.com/AllanOtieno254.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MNIST Digit Classification\n\n## Description\nThis project focuses on building a machine learning model to classify handwritten digits using the MNIST dataset. The MNIST dataset is a well-known dataset in the field of image classification, containing 60,000 training images and 10,000 test images of handwritten digits from 0 to 9. The goal is to create a robust model capable of accurately predicting the digit in an unseen image.\n\n\n![img1_output](https://github.com/user-attachments/assets/0472bec3-30fe-4adb-aa2f-1403cd729dc7)\n\n![img2_output](https://github.com/user-attachments/assets/c3689d15-b90e-4b1a-b14d-0db965fc5009)\n\n## Table of Contents\n1. [Introduction](#introduction)\n2. [Project Structure](#project-structure)\n3. [Installation](#installation)\n4. [Usage](#usage)\n5. [Model Overview](#model-overview)\n6. [Results](#results)\n7. [Contributing](#contributing)\n8. [License](#license)\n\n## Introduction\nThe MNIST Digit Classification project is a deep learning-based approach to recognizing and classifying handwritten digits. Using various deep learning techniques, such as Convolutional Neural Networks (CNNs), the project demonstrates a step-by-step approach to achieving high accuracy in digit classification tasks.\n\n## Project Structure\n- **data/**: Contains the raw and processed dataset files.\n- **notebooks/**: Jupyter Notebooks that document the exploratory data analysis, preprocessing steps, model training, and evaluation processes.\n- **src/**: Python scripts for data processing, model building, training, and evaluation.\n- **models/**: Directory where trained models are saved.\n- **results/**: Plots and other outputs generated from the training and evaluation processes.\n- **README.md**: Overview and instructions for the project.\n- **requirements.txt**: Dependencies required to run the project.\n- **setup.py**: Installation script (if applicable).\n- **LICENSE**: License information for the project.\n\n## Installation\nTo run this project, you'll need to have Python 3.x installed. Clone the repository and install the required dependencies:\n\n```bash\ngit clone https://github.com/yourusername/mnist-digit-classification.git\ncd mnist-digit-classification\npip install -r requirements.txt\n\n## Usage\nYou can start by exploring the data and training the model using the Jupyter notebooks provided in the notebooks/ directory.\n\nFor instance, to run the data exploration notebook:\n\njupyter notebook notebooks/01_data_exploration.ipynb\n\nTo train the model, execute the following script:\npython src/train.py\n\n\n #Model Overview\nThe model used in this project is a Convolutional Neural Network (CNN) with the following layers:\n\nInput layer: Takes 28x28 pixel images as input.\nConvolutional layers: Extract features from the input images.\nPooling layers: Downsample the feature maps.\nFully connected layers: Map the features to the output space.\nOutput layer: A softmax layer with 10 units corresponding to the 10 digit classes (0-9)\n\n# Results\nThe model achieved an accuracy of X% on the test dataset. Below are some of the key metrics:\n\nAccuracy: X%\nPrecision: X%\nRecall: X%\n\n\n# Contributing\nContributions are welcome! Please fork the repository and submit a pull request if you have any improvements or new features to add.\n\n\n# License\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n### Explanation:\n- **Sections**: The `README.md` file is structured with various sections that cover the essential details of your project.\n- **Table of Contents**: It provides a quick navigation to different parts of the README.\n- **Usage Instructions**: Step-by-step instructions for running your project.\n- **Model Overview and Results**: These sections summarize the model architecture and key results from your project.\n\nYou can copy this text directly into your `README.md` file in your GitHub repository.\n\n**a.** Would you like to generate the `requirements.txt` file based on typical libraries used for MNIST projects?  \n**b.** Need help with setting up a specific part of the project (e.g., model architecture in `model.py`)?\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fallanotieno254%2Fmnist-digit-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fallanotieno254%2Fmnist-digit-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fallanotieno254%2Fmnist-digit-classification/lists"}