cavaface.pytorch: A Pytorch Training Framework for Deep Face Recognition

By Yaobin Li and Liying Chi

Introduction

This repo provides a high-performance distribute parallel training framework for face recognition with pytorch, including various backbones (e.g., ResNet, IR, IR-SE, ResNeXt, AttentionNet-IR-SE, ResNeSt, HRNet, etc.), various losses (e.g., Softmax, Focal, SphereFace, CosFace, AmSoftmax, ArcFace, ArcNegFace, CurricularFace, Li-Arcface, QAMFace, etc.), various data augmentation(e.g., RandomErasing, Mixup, RandAugment, Cutout, CutMix, etc.) and bags of tricks for improving performance (e.g., FP16 training(apex), Label smooth, LR warmup, etc)

Main requirements

torch == 1.4.0
torchvision == 0.5.0
tensorboardX == 1.7
bcolz == 1.2.1
Python 3
Apex == 0.1

Features

(click to collapse)

Backbone
- ResNet(IR-SE)
- ResNeXt
- DenseNet
- MobileFaceNet
- MobileNetV3
- EfficientNet
- ProxylessNas
- GhostNet
- AttentionNet-IRSE
- ResNeSt
- ReXNet
- MobileNetV2
- MobileNeXt
Attention Module
- SE
- CBAM
- ECA
- GCT
Loss
- Softmax
- SphereFace
- Am_Softmax
- CosFace
- ArcFace
- Combined Loss
- AdaCos
- SV-X-Softmax
- CurricularFace
- ArcNegFace
- Li-Arcface
- QAMFace
- Circle Loss
Parallel Training
- Data Parallel
- Model Parallel
Automatic Mixed Precision
- Apex
Optimizer
- LR_Scheduler(faireq,rwightman)
- Optim(SGD,Adam,RAdam,LookAhead,Ranger,AdamP,SGDP)
Data Augmentation
- RandomErasing(官方版torchvision.transforms.RandomErasing)
- Mixup
- RandAugment
- Cutout
- CutMix
- Colorjitter
Distillation
- KnowledgeDistillation
- Multi Feature KD
Bag of Tricks
- Label smooth
- LR warmup
- Zero gamma

Installation

See INSTALL.md.

Quick start

See GETTING_STARTED.md.

Model Zoo and Baselines

See MODEL_ZOO.md.

License

cavaface.pytorch is released under the MIT license.

Acknowledgement

This repo is modified and adapted on these great repositories face.evoLVe.PyTorch, CurricularFace, insightface and imgclsmob
The evaluation tools is developed by Charrin

Contact

cavallyb@gmail.com

lrain-CN/cavaface.pytorch