/MobileFaceNet

PyTorch implementation of MobileFaceNets

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

MobileFaceNets

apm

PyTorch implementation of MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices. paper.

Performance

Accuracy LFW MegaFace Download
paper 99.55% 92.59%
ours 99.48% 82.55% Link

Dataset

Introduction

Refined MS-Celeb-1M dataset for training, 3,804,846 faces over 85,164 identities. LFW and Megaface datasets for testing.

Dependencies

  • Python 3.6.8
  • PyTorch 1.3.0

Usage

Data preprocess

Extract images:

$ python extract.py
$ python pre_process.py

Train

$ python train.py

To visualize the training process:

$ tensorboard --logdir=runs