tiny-dnn
A header-only, dependency-free deep learning framework in C++14 for embedded systems and IoT devices.
What is tiny-dnn?
tiny-dnn is a header-only, dependency-free deep learning framework implemented in C++14. It enables developers to build and train neural networks directly in C++ without external dependencies, specifically targeting environments with limited computational resources like embedded systems and IoT devices.
C++ developers working on embedded systems, IoT applications, or any project requiring a lightweight, portable deep learning solution without GPU dependencies.
Its unique selling points are being entirely header-only with zero dependencies, offering easy integration into existing C++ applications, and providing reasonable performance on CPU through threading and vectorization optimizations.
Overview
header only, dependency-free deep learning framework in C++14
Use Cases
Best For
- Adding deep learning capabilities to C++ embedded applications
- Deploying neural networks on IoT devices with limited resources
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
