Skip to main content

A package wrapping the FaceNet embedding model

Project description


This is a simple wrapper around this wonderful implementation of FaceNet. I wanted something that could be used in other applications, that could use any of the four trained models provided in the linked repository, and that took care of all the setup required to get weights and load them. I prefer using Keras wherever possible because of its API, so I used the example provided here and implemented it as part of the code.

Enough background -- so how are you supposed to use this?


pip install keras-facenet


To get embeddings for the faces in an image, you can do something like the following.

from keras_facenet import FaceNet
embedder = FaceNet()

# Gets a detection dict for each face
# in an image. Each one has the bounding box and
# face landmarks (from mtcnn.MTCNN) along with
# the embedding from FaceNet.
detections = embedder.extract(image, threshold=0.95)

# If you have pre-cropped images, you can skip the
# detection step.
embeddings = embedder.embeddings(images)


To see what's going on under the hood, set logging to view INFO logs. If using in a Jupyter notebook, you can use the following.

import logging

log = logging.getLogger()

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

keras-facenet-0.3.2.tar.gz (10.3 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page