MobileFaceNets
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.pyTrain
$ python train.pyTo visualize the training process：
$ tensorboard --logdir=runs