Get unlimited public & private packages + package-based permissions with npm Pro.Get started »


0.10.7 • Public • Published


Build Status NPM Version Downloads Join the chat at node TypeScript

A TensorFlow backed FaceNet implementation for Node.js, which can solve face verification, recognition and clustering problems.

Google Facenet

FaceNet is a deep convolutional network designed by Google, trained to solve face verification, recognition and clustering problem with efficiently at scale.

  1. directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity.
  2. optimize the embedding face recognition performance using only 128-bytes per face.
  3. achieves accuracy of 99.63% on Labeled Faces in the Wild (LFW) dataset, and 95.12% on YouTube Faces DB.


$ npm install facenet numjs flash-store

Peer Dependencies

  1. numjs
  2. flash-store


The follow examples will give you some intuitions for using the code.

  1. demo exmaple will show you how to do align for face alignment and embedding to get face feature vector.
  2. visualize example will calculate the similarity between faces and draw them on the photo.

1. Demo for API Usage

TL;DR: Talk is cheap, show me the code!

import { Facenet } from 'facenet'
const facenet = new Facenet()
// Do Face Alignment, return faces
const imageFile = `${__dirname}/../tests/fixtures/two-faces.jpg`
const faceList = await facenet.align(imageFile)
for (const face of faceList) {
  console.log('bounding box:',  face.boundingBox)
  console.log('landmarks:',     face.facialLandmark)
  // Calculate Face Embedding, return feature vector
  const embedding = await facenet.embedding(face)
  console.log('embedding:', embedding)
faceList[0].embedding = await facenet.embedding(faceList[0])
faceList[1].embedding = await facenet.embedding(faceList[1])
console.log('distance between the different face: ', faceList[0].distance(faceList[1]))
console.log('distance between the same face:      ', faceList[0].distance(faceList[0]))

Full source code can be found at here:

The output should be something like:

image file: /home/zixia/git/facenet/examples/../tests/fixtures/two-faces.jpg
face file: 1-1.jpg
bounding box: {
  p1: { x: 360, y: 95 }, 
  p2: { x: 589, y: 324 } 
landmarks: { 
  leftEye:  { x: 441, y: 181 },
  rightEye: { x: 515, y: 208 },
  nose:     { x: 459, y: 239 },
  leftMouthCorner:  { x: 417, y: 262 },
  rightMouthCorner: { x: 482, y: 285 } 
embedding: array([ 0.02453, 0.03973, 0.05397, ..., 0.10603, 0.15305,-0.07288])
face file: 1-2.jpg
bounding box: { 
  p1: { x: 142, y: 87 }, 
  p2: { x: 395, y: 340 } 
landmarks: { 
  leftEye:  { x: 230, y: 186 },
  rightEye: { x: 316, y: 197 },
  nose:     { x: 269, y: 257 },
  leftMouthCorner:  { x: 223, y: 273 },
  rightMouthCorner: { x: 303, y: 281 } 
embedding: array([ 0.03241, -0.0737,  0.0475, ..., 0.07235, 0.12581,-0.00817])

2. Visualize for Intuition

FaceNet Visualization

  1. Face is in the green rectangle.
  2. Similarity(distance) between faces showed as a number in the middle of the line.
  3. To identify if two faces belong to the same person, we could use an experiential threshold of distance: 0.75.
$ git clone
cd facenet
$ npm install
$ npm run example:visualize
01:15:43 INFO CLI Visualized image saved to:  facenet-visulized.jpg

3. Get the diffence of two face

Get the two face's distance, the smaller the number is, the similar of the two face

import { Facenet } from 'facenet'
const facenet = new Facenet()
const imageFile = `${__dirname}/../tests/fixtures/two-faces.jpg`
const faceList = await facenet.align(imageFile)
faceList[0].embedding = await facenet.embedding(faceList[0])
faceList[1].embedding = await facenet.embedding(faceList[1])
console.log('distance between the different face: ', faceList[0].distance(faceList[1]))
console.log('distance between the same face:      ', faceList[0].distance(faceList[0]))

distance between the different face: 1.2971515811057608
distance between the same face: 0

In the example,
faceList[0] is totally the same with faceList[0], so the number is 0
faceList[1] is different with faceList[1], so the number is big.
If the number is smaller than 0.75, maybe they are the same person.

Full source code can be found at here:

4. Save the face picture from a picture

Recognize the face and save the face to local file.

import { Facenet } from 'facenet'
const facenet = new Facenet()
const imageFile = `${__dirname}/../tests/fixtures/two-faces.jpg`
const faceList = await facenet.align(imageFile)
for (const face of faceList) {
  await + '.jpg')
  console.log(`save face ${face.md5} successfuly`)
console.log(`Save ${faceList.length} faces from the imageFile`)

Full source code can be found at here:



Roadmap: release facenet-manager on version 0.8


The above ascii recording is just for demo purpose. Will replace it with facenet-manager later.


See auto generated docs


$ npm install facenet



  • Linux
  • Mac
  • Windows


  1. Node.js >= 7 (8 is recommend)
  2. Tensorflow >= 1.2
  3. Python3 >=3.5 (3.6 is recommend)

Make sure you run those commands under Ubuntu 17.04:

sudo apt install python3-pip
pip3 install setuptools --upgrade


Neural Network Model Task Ram
MTCNN Facenet#align() 100MB
Facenet Facenet#embedding() 2GB

If you are dealing with very large images(like 3000x3000 pixels), there will need additional 1GB of memory.

So I believe that Facenet will need at least 2GB memory, and >=4GB is recommended.


Neural Network alone is not enough. It's Neural Network married with pre-trained model, married with easy to use APIs, that yield us the result that makes our APP sing.

Facenet is designed for bring the state-of-art neural network with bleeding-edge technology to full stack developers.


import { Facenet } from 'facenet'
const facenet = new Facenet()

1. Facenet#align(filename: string): Promise<Face[]>

Do face alignment for the image, return a list of faces.

2. Facenet#embedding(face: Face): Promise<FaceEmbedding>

Get the embedding for a face.

face.embedding = await facenet.embedding(face)


Get the 128 dim embedding vector for this face.(After alignment)

import { Face } from 'facenet'
console.log('bounding box:',  face.boundingBox)
console.log('landmarks:',     face.facialLandmark)
console.log('embedding:',     face.embedding)



FaceNet neural network model files, set to other version of model as you like.

Default is set to models/ directory inside project directory. The pre-trained models is come from 20170512-110547, 0.992, MS-Celeb-1M, Inception ResNet v1, which will be download & save automatically by postinstall script.

$ ls models/


Docker Pulls Docker Stars Docker Layers


Issue Stats Issue Stats Coverage Status Greenkeeper badge

$ git clone
cd facenet
$ npm install
$ npm test



Draw a rectangle with five landmarks on all faces in the input_image, save it to output_image.

$ ./node_modules/.bin/ts-node bin/align.ts input_image output_image


Output the 128 dim embedding vector of the face image.

$ ./node_modules/.bin/ts-node bin/embedding.ts face_image


Machine Learning


1. Typing

1. NumJS


  1. LFW - Labeled Faces in the Wild


  • NPM Module: facenet
  • Docker Image: zixia/facenet
  • Examples
    • API Usage Demo
    • Triple Distance Visulization Demo
    • Performance Test(Align/Embedding/Batch)
    • Validation Test(LFW Accuracy)
  • Neural Network Models
    • Facenet
    • Mtcnn
    • Batch Support
  • Python3 async & await
  • Divide Different Neural Network to seprate class files(e.g. Facenet/Mtcnn)
  • K(?)NN Alghorithm Chinese Whispers
  • TensorFlow Sereving
  • OpenAPI Specification(Swagger)


This repository is heavily inspired by the following implementations:


  1. Face alignment using MTCNN: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
  2. Face embedding using FaceNet: FaceNet: A Unified Embedding for Face Recognition and Clustering
  3. TensorFlow implementation of the face recognizer: Face recognition using Tensorflow


FaceNet Badge

Powered by FaceNet

[![Powered by FaceNet](](


v0.9 master unstable

v0.8 (Apr 2018)

  1. Added facenet-manager command line tool for demo/validate/sort photos
  2. Switch to FlashStore npm module as key-value database

v0.3 Sep 2017

  1. Added three cache classes: AlignmentCache & EmbeddingCache & FaceCache.
  2. Added cache manager utilities: embedding-cache-manager & alignment-cache-manager & face-cache-manager
  3. Added Dataset manager utility: lfw-manager (should be dataset-manager in future)
  4. BREAKING CHANGE: Face class refactoring.

v0.2 Aug 2017 (BREAKING CHANGES)

  1. Facenet#align() now accept a filename string as parameter.
  2. BREAKING CHANGE: FaceImage class had been removed.
  3. BREAKING CHANGE: Face class refactoring.

v0.1 Jul 2017

  1. npm run demo to visuliaze the face alignment and distance(embedding) in a three people photo.
  2. Facenet.align() to do face alignment
  3. Facenet.embedding() to calculate the 128 dim feature vector of face
  4. Initial workable version



OS Command
os x brew install pkg-config cairo pango libpng jpeg giflib
ubuntu sudo apt-get install libcairo2-dev libjpeg8-dev libpango1.0-dev libgif-dev build-essential g++
fedora sudo yum install cairo cairo-devel cairomm-devel libjpeg-turbo-devel pango pango-devel pangomm pangomm-devel giflib-devel
solaris pkgin install cairo pango pkg-config xproto renderproto kbproto xextproto
windows instructions on our wiki

more os see node-canvas Wiki.


  1. facenet-manager display not right under Windows

See: Running Terminal Dashboards on Windows

  1. Error when install: No package 'XXX' found

It's related with the NPM module canvas.

Error messages:

  1. No package 'pixman-1' found
  2. No package 'cairo' found
  3. No package 'pangocairo' found

Solution for Ubuntu 17.04:

sudo apt install -y libpixman-1-dev
sudo apt-get install -y libcairo2-dev
sudo apt-get install -y libpango1.0-dev

Solution for Mac:

brew install python3
brew install pkg-config
brew install cairo
brew install pango
brew install libpng
brew install libjpeg
  1. Error when install: fatal error: jpeglib.h: No such file or directory

It's related with the NPM module canvas.

Solution for Ubuntu 17.04:

sudo apt-get install -y libjpeg-dev
  1. Error when run: Error: error while reading from input stream

It is related with the libjpeg package

Solution for Mac:

brew install libjpeg
  1. Error when run:
Error: Cannot find module '../build/Release/canvas.node'
    at Function.Module._resolveFilename (module.js:527:15)
    at Function.Module._load (module.js:476:23)
    at Module.require (module.js:568:17)
    at require (internal/module.js:11:18)
    at Object.<anonymous> (/Users/jiaruili/git/node-facenet/node_modules/canvas/lib/bindings.js:3:18)
    at Module._compile (module.js:624:30)
    at Object.Module._extensions..js (module.js:635:10)
    at Module.load (module.js:545:32)
    at tryModuleLoad (module.js:508:12)
    at Function.Module._load (module.js:500:3)

It seems the package not installed in a right way, like sharp, canvas, remove the package and reinstall it.


rm -rf node node_modules/canvas
// if sharp, then remove sharp folder
npm install
  1. Error when install
> facenet@0.3.19 postinstall:models /Users/jiaruili/git/rui/node-facenet
> set -e && if [ ! -d models ]; then mkdir models; fi && cd models && if [ ! -f model.tar.bz2 ]; then curl --location --output model.tar.bz2.tmp; mv model.tar.bz2.tmp model.tar.bz2; fi && tar jxvf model.tar.bz2 && cd -

x 20170512-110547.pb
x (Empty error message)
tar: Error exit delayed from previous errors.

It seems this because not get the full model file successfully. See #issue63


download the file from
rename the file model.tar.bz2 and move it to the folder models try npm install again


  1. Face Blinder: Assitant Bot for Whom is Suffering form Face Blindess
  2. Wechaty Blinder: Face Blinder Bot Powered by Wechaty


Huan LI <> (

profile for zixia at Stack Overflow, Q&A for professional and enthusiast programmers


  • Code & Docs © 2017 Huan LI <>
  • Code released under the Apache-2.0 License
  • Docs released under Creative Commons


npm i facenet-wehaus-dist

DownloadsWeekly Downloads






Unpacked Size

498 kB

Total Files


Last publish


  • avatar