MobileFaceNet

Introduction

• This repository is the pytorch implement of the paper: MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices and I almost follow the implement details of the paper.
• I train the model on CASIA-WebFace dataset, and evaluate on LFW dataset.

Requirements

• Python 3.5
• pytorch 0.4+
• GPU memory

Usage

Part 1: Preprocessing

• All images of dataset are preprocessed following the and you can download the aligned images at [Align-CASIA-WebFace@BaiduDrive] and [Align-LFW@BaiduDrive]g).

Part 2: Train

1. Change the CAISIA_DATA_DIR and LFW_DATA_DAR in config.py to your data path.

2. Train the mobilefacenet model.

   Note: The default settings set the batch size of 512, use 2 gpus and train the model on 70 epochs. You can change the settings in config.py

   python3 train.py
   

Part 3: Test

1. Test the model on LFW.

   Note: I have tested lfw_eval.py on the caffe model at [SphereFace] it gets the same result.

   • --resume: path of saved model
   • --feature_save_dir: path to save the extracted features (must be .mat file)