VGGFace 是牛津大学视觉组于2015年发表， VGGNet 也是他们提出的，基于VGGNet的人脸识别，Deep Face Recognition，官网 主要思想 目标：构建最少的人为干预大规模人脸数据集，使训练的卷积神经网络进行人脸识别，可以与谷歌和Facebook等互联网巨头竞争。

VGGFace2 Dataset for Face Recognition The dataset contains 3.31 million images of 9131 subjects (identities), with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians).

This page contains the download links for the source code for computing the VGG-Face CNN descriptor, described in [1]. The VGG-Face CNN descriptors are computed using our CNN implementation based on the VGG-Very-Deep-16 CNN architecture as described in [1] and are evaluated on the Labeled Faces in the Wild [2] and the YouTube Faces [3] dataset.

Live Face Identification with pre-trained VGGFace2 model. How to Perform Face Recognition With VGGFace2 in Keras. An extremely small FaceRecog project for extreme beginners, and a few thoughts on the future

2019年6月4日 · In this tutorial, you will discover how to develop face recognition systems for face identification and verification using the VGGFace2 deep learning model. After completing this tutorial, you will know:

2022年5月10日 · VGGFace2数据集是由牛津大学视觉几何组（Visual Geometry Group, VGG）于2017年创建的，旨在推动人脸识别技术的研究。 该数据集包含了超过330万张图像，涵盖了9131个不同个体的面部图像，每个个体平均拥有362张图像。

The VGG Face dataset is face identity recognition dataset that consists of 2,622 identities. It contains over 2.6 million images.

2018年3月17日 · Face Recognition库是基于Dlib和OpenCV的Python接口，可以进行人脸检测（使用Haar级联分类器或HOG+SVM方法）、人脸识别（通过预训练的深度学习模型，如DeepID-2+或VGG-Face）和人脸比对。它提供了简单易用的API，...

2024年9月3日 · 本文档提供了一个实用的教程，展示了如何将预先训练好的VGG-Face模型（存储在MAT格式的vgg-face.mat文件中）迁移到PyTorch框架。VGG-Face是一种广泛用于人脸识别任务的深度学习模型，它基于VGG16网络结构，特别设计...

A VGG-Face CNN descriptor implemented in PyTorch. The VGG-Face CNN descriptors are computed using [1] authors' CNN implementation, based on the VGG-Very-Deep-16 CNN architecture (see [1]), and are evaluated on the Labeled Faces in the Wild [2] and the YouTube Faces [3] datasets.