# dlib

A toolkit for making real world machine learning and data analysis applications in C++

Repository: https://github.com/davisking/dlib
Canonical: https://ross.abutalabs.com/products/dlib
Homepage: http://dlib.net
Language: C++
License: BSL-1.0
License Family: other
Topics: machine-learning, deep-learning, c-plus-plus, python, computer-vision, machine-learning-library, dlib
Last push: 2026-08-11T03:03:36+00:00
Link (homepage): http://dlib.net
Link (site_page): https://dlib.net/rank_features_ex.cpp.html
Link (site_page): https://dlib.net/faq.html

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-07T02:58:08.109385+00:00)
- activity 96, release rhythm 64, longevity 100
- inputs: {"age_days": 4604, "days_push": 26, "days_rel": 161, "gap_med": 42.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 14436, forks 3441 (observed 2026-09-06T21:20:33.019334+00:00)

## What it is
Dlib is a modern C++ toolkit containing machine learning algorithms, deep learning tools, computer vision, linear algebra, and general-purpose utilities for building real-world applications. It also ships a Python API installable via pip and provides pretrained models for tasks like face detection and landmark estimation.

## Use cases
- detect faces and facial landmarks in images
- train object detection models in C++
- run deep learning inference without a heavy framework
- perform SVM classification and regression
- do linear algebra and matrix computations in C++
- build image processing pipelines
- use machine learning from Python via pip install dlib

## When to choose
- you need high-performance ML/computer vision in C++ with minimal dependencies
- you want face detection or landmark models that run on CPU
- you need a broad set of algorithms (SVM, clustering, optimization, geometry) in one library
- you want a permissive Boost license for commercial use

## When to avoid
- you need GPU-accelerated transformer or LLM workloads better served by PyTorch
- you want a Python-first ecosystem with extensive community tooling
- you need prebuilt wheels for every platform or quick prototyping over performance

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, computer-vision, image-processing, nlp, data-science, graphics, gui, http-server, math
- domain: machine-learning, computer-vision, deep-learning, data-science, image-processing, developer-tools
- platform: cpp, python, cross-platform, windows
- tags: face-detection, face-landmarks, svm, object-detection, linear-algebra, cmake, boost-license, pretrained-models, algorithms, linux, macos

## Member repositories
- davisking/dlib (main) score 86
- davisking/dlib-models (docs) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-09-06T21:20:33.019334+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 2026-08-29T17:12:34.548126+00:00, confidence not recorded.
  - readme: https://github.com/davisking/dlib (fetched 2026-09-06T21:20:33.019334+00:00, sha 94b0e54cb251)
  - homepage: http://dlib.net (fetched 2026-08-29T08:06:04.117144+00:00, sha 0c54511dd6a1)
  - site_page: https://dlib.net/rank_features_ex.cpp.html (fetched 2026-08-29T08:06:04.126696+00:00, sha 06c4c21353a6)
  - site_page: https://dlib.net/faq.html (fetched 2026-08-29T08:06:04.128886+00:00, sha ef0f727787f0)
- Data as of 2026-09-07T08:21:23.190159+00:00.