# tiny-dnn/tiny-dnn

header only, dependency-free deep learning framework in C++14

Repository: https://github.com/tiny-dnn/tiny-dnn
Canonical: https://ross.abutalabs.com/products/tiny-dnn
Homepage: http://tiny-dnn.readthedocs.io
Language: C++
License: NOASSERTION
License Family: other
Topics: c-plus-plus, deep-learning, machine-learning, neural-network
Last push: 2022-04-17T02:48:05+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 5007, "days_push": 1599, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6030, forks 1385 (observed 2026-08-28T04:09:34.425868+00:00)

## What it is
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
- artifact type: library
- maturity: abandoned
- function: deep-learning, machine-learning, gpu-computing
- domain: deep-learning, machine-learning, embedded-systems, iot
- platform: cpp, cross-platform, windows, embedded
- tags: header-only, neural-networks, dependency-free, c-plus-plus-14, embedded-ml, maintainers-wanted, linux, macos

## Member repositories
- tiny-dnn/tiny-dnn (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.425868+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:49:13.771331+00:00, confidence not recorded.
  - readme: https://github.com/tiny-dnn/tiny-dnn (fetched 2026-08-28T04:09:34.425868+00:00, sha c6676e5c880c)
- Data as of 2026-08-30T08:39:29.467469+00:00.