tiny-dnn/tiny-dnn

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

6030 stars · 1385 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

tiny-dnn is a header-only, dependency-free deep learning framework written in C++14, designed for training and running neural networks on resource-constrained devices. It supports CPU vectorization (SSE/AVX) and TBB threading, making it suitable for embedded systems and IoT without GPU requirements.

Use cases

• train a neural network in C++ without dependencies
• run deep learning inference on embedded systems
• add a small neural network to an IoT device
• integrate deep learning into a C++ application with no install step
• train MNIST on CPU without a GPU
• embed a portable header-only ML library in my project

When to choose

• you need a dependency-free, header-only C++ neural network library
• you target embedded or resource-limited environments without GPU support
• you want easy integration into real applications with no stdout output or exceptions

When to avoid

• you need actively maintained software - the project is seeking new maintainers and may be abandoned
• you need GPU acceleration or modern deep learning features like transformers
• you want a large ecosystem of pretrained models and tooling

Facets

library · maturity abandoned

deep-learning machine-learning gpu-computing deep-learning machine-learning embedded-systems iot cpp cross-platform windows embedded header-only neural-networks dependency-free c-plus-plus-14 embedded-ml maintainers-wanted linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tiny-dnn/tiny-dnn")