{"id":22202477,"url":"https://github.com/ata-turhan/mnist-digit-classification-pytorch","last_synced_at":"2025-10-24T18:49:26.930Z","repository":{"id":263536249,"uuid":"890713909","full_name":"ata-turhan/MNIST-Digit-Classification-PyTorch","owner":"ata-turhan","description":"A complete solution for the MNIST handwritten digit classification challenge using PyTorch, including data exploration, model training, and Kaggle submission generation.","archived":false,"fork":false,"pushed_at":"2024-11-20T03:48:45.000Z","size":28,"stargazers_count":12,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-29T07:45:23.868Z","etag":null,"topics":["computer-vision","deep-learning","image-classification","python","pytorch"],"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/ata-turhan.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":"2024-11-19T03:42:09.000Z","updated_at":"2025-03-24T01:28:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"2ba6cc60-e934-4bd4-990a-c246f37a1615","html_url":"https://github.com/ata-turhan/MNIST-Digit-Classification-PyTorch","commit_stats":null,"previous_names":["ata-turhan/mnist-digit-classification-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ata-turhan/MNIST-Digit-Classification-PyTorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ata-turhan%2FMNIST-Digit-Classification-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ata-turhan%2FMNIST-Digit-Classification-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ata-turhan%2FMNIST-Digit-Classification-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ata-turhan%2FMNIST-Digit-Classification-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ata-turhan","download_url":"https://codeload.github.com/ata-turhan/MNIST-Digit-Classification-PyTorch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ata-turhan%2FMNIST-Digit-Classification-PyTorch/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259756871,"owners_count":22906678,"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","image-classification","python","pytorch"],"created_at":"2024-12-02T16:27:01.813Z","updated_at":"2025-10-24T18:49:21.884Z","avatar_url":"https://github.com/ata-turhan.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MNIST Digit Classification with PyTorch\n\nA complete PyTorch-based solution for the MNIST handwritten digit classification challenge, including data exploration, model training, evaluation, and Kaggle submission generation.\n\n## Overview\n\nThe MNIST dataset is a collection of 70,000 grayscale images of handwritten digits (0–9). This project solves the multi-class classification problem of identifying the correct digit for each image. It serves as an excellent introduction to deep learning concepts, particularly neural networks.\n\n## Features\n\n- **Data Preprocessing**: Includes normalization and custom PyTorch `Dataset` creation.\n- **Exploratory Data Analysis**: Visualizes sample images and provides statistical insights.\n- **Deep Learning Model**: Implements a fully connected neural network using PyTorch.\n- **Training and Evaluation**: Tracks loss and accuracy with a validation split.\n- **Kaggle Submission**: Generates predictions and prepares a CSV for Kaggle competition submission.\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.8+\n- PyTorch 1.12+\n- Jupyter Notebook or Kaggle environment\n\n### Installation\n\n1. Clone this repository:\n   ```bash\n   git clone https://github.com/ata-turhan/MNIST-Digit-Classification-PyTorch.git\n   ```\n2. Navigate to the project directory:\n   ```bash\n   cd MNIST-Digit-Classification-PyTorch\n   ```\n3. Install the required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n## Usage\n\n1. **Run the Notebook**:\n   Open `mnist_digit_classification.ipynb` in Jupyter Notebook or directly on Kaggle.\n   \n2. **Train the Model**:\n   Execute the notebook cells to preprocess data, train the model, and evaluate it.\n\n3. **Generate Kaggle Submission**:\n   Run the prediction step to create `submission.csv`, ready for upload to Kaggle.\n\n## Repository Structure\n\n```\nMNIST-Digit-Classification-PyTorch/\n│\n├── README.md                       # Project overview\n├── mnist_digit_classification.ipynb # Main notebook\n├── requirements.txt                # Python dependencies\n└── LICENSE                         # MIT License\n```\n\n## Results\n\nThe model achieves an accuracy of **96.95%** on the validation set and **96.89%** on Kaggle leaderboard submissions.\n\n## Contributing\n\nContributions are welcome! Please submit a pull request or raise an issue if you find a bug or have suggestions for improvement.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fata-turhan%2Fmnist-digit-classification-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fata-turhan%2Fmnist-digit-classification-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fata-turhan%2Fmnist-digit-classification-pytorch/lists"}