Skip to main content

Gluon FR Toolkit

Project description

Gluon FR Toolkit

Documentation Status

GluonFR is a toolkit based on MXnet-Gluon, provides SOTA deep learning algorithm and models in face recognition.


GluonFR supports Python 3.5 or later. To install this package you need install GluonCV and MXNet first:

pip install gluoncv --pre
pip install mxnet-mkl --pre --upgrade
# if cuda XX is installed
pip install mxnet-cuXXmkl --pre --upgrade

Then install gluonfr:

  • From Source(recommend)
pip install git+
  • Pip
pip install gluonfr

GluonFR Introduction:

GluonFR is based on MXnet-Gluon, if you are new to it, please check out dmlc 60-minute crash course.


This part provides input pipeline for training and validation, all datasets is aligned by mtcnn and cropped to (112, 112) by DeepInsight, they converted images to train.rec, train.idx and val_data.bin files, please check out [insightface/Dataset-Zoo] for more information. In data/, there is a simple example of Nvidia-DALI. It is worth trying when data augmentation with cpu can not satisfy the speed of gpu training,

The files should be prepared like:


We use ~/.mxnet/datasets as default dataset root to match mxnet setting.


mobile_facenet, res_attention_net, se_resnet...


GluonFR provides implement of losses in recent, including SoftmaxCrossEntropyLoss, ArcLoss, TripletLoss, RingLoss, CosLoss, L2Softmax, ASoftmax, CenterLoss, ContrastiveLoss, ... , and we will keep updating in future.
If there is any method we overlooked, please open an issue.


examples/ shows how to use gluonfr to train a face recognition model, and how to get Mnist 2-D feature embedding visualization.

Losses in GluonFR:

The last column of this chart is the best LFW accuracy reported in paper, they are trained with different data and networks, later we will give our results of these method with same train data and network.

Method Paper Visualization of MNIST LFW
Contrastive Loss ContrastiveLoss - -
Triplet 1503.03832 - 99.63±0.09
Center Loss CenterLoss 99.28
L2-Softmax 1703.09507 - 99.33
A-Softmax 1704.08063 - 99.42
CosLoss/AMSoftmax 1801.05599/1801.05599 99.17
Arcloss 1801.07698 99.82
Ring loss 1803.00130 99.52
LGM Loss 1803.02988 99.20±0.03

Pretrained Models

See Model Zoo in doc.


  • More pretrained models
  • IJB and Megaface Results
  • Other losses
  • Dataloader for loss depend on how to provide batches like Triplet, ContrastiveLoss, RangeLoss...
  • Try GluonCV resnetV1b/c/d/ to improve performance
  • Create hosted docs
  • Test module
  • Pypi package


Please checkout link.
For Chinese Version: link


{ haoxintong Yangxv Haoyadong Sunhao }


中文社区Gluon-Forum Feel free to use English here :D.


  1. MXNet Documentation and Tutorials

  2. NVIDIA DALI documentationNVIDIA DALI documentation

  3. Deepinsight insightface

Project details

Download files

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

Files for gluonfr, version 1.0.2
Filename, size File type Python version Upload date Hashes
Filename, size gluonfr-1.0.2.tar.gz (24.2 kB) File type Source Python version None Upload date Hashes View

Supported by

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