Download
face.evoLVe is a high-performance face recognition library designed for research and real-world applications in computer vision. The project provides a comprehensive framework for building and training modern face recognition models using deep learning architectures. It includes components for face alignment, landmark localization, data preprocessing, and model training pipelines that allow developers to construct end-to-end facial recognition systems. The repository supports multiple neural network backbones such as ResNet, DenseNet, MobileNet, and ShuffleNet, enabling experimentation with different architectures depending on performance requirements. It also implements a wide range of loss functions commonly used in face recognition research, including ArcFace, CosFace, Triplet loss, and Softmax variants. To improve scalability, the library introduces distributed training techniques that allow large models to be trained efficiently across multiple GPUs.
Features
- Support for multiple deep neural network backbones including ResNet and MobileNet
- Face alignment and preprocessing pipelines for facial datasets
- Implementation of advanced face recognition losses such as ArcFace and CosFace
- Distributed multi-GPU training for large-scale recognition models
- Model zoo and dataset tools for face recognition experiments
- Training utilities for data augmentation, normalization, and optimization
Project Samples
