Face detection and recognition, articles in this area, our previous articles also have related introductions, mainly related to MediaPipe Face Detection , and face detection and recognition based on openCV , and we trained our own based on CNN convolutional neural network Face recognition model. In this issue, we share InsightFace, a python library that can be used for 2D and 3D face detection and recognition.
InsightFace is an integrated Python library for 2D and 3D face analysis. InsightFace efficiently implements various state-of-the-art face recognition, face detection, and face alignment algorithms, optimized for training and deployment. It supports a range of backbone architectures, including IResNet, RetinaNet, MobileFaceNet, InceptionResNet_v2, and DenseNet. In addition to models, it can also use facial datasets such as MS1M, VGG2, and CASIA-WebFace.
https://github.com/deepinsight/insightface
PyTorch 1.6+ and/or MXNet