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:
pip install git+https://github.com/THUFutureLab/[email protected]
pip install gluonfr
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
val_data.bin files, please check out
[insightface/Dataset-Zoo] for more information.
data/dali_utils.py, 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:
face/ emore/ train.rec train.idx property ms1m/ train.rec train.idx property lfw.bin agedb_30.bin ... vgg2_fp.bin
~/.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.
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|
See Model Zoo in doc.
中文社区Gluon-Forum Feel free to use English here :D.