# Lightweight Backbone Network

A lightweight RDNet image classification model trained on the ImageNet-1k dataset, with 24M parameters and 82.8% top-1 accuracy.

RetinaFace is a lightweight face detection model based on MobileNet or ResNet50 backbone networks, capable of efficiently locating faces and providing facial keypoint coordinates.

Self-supervised image feature extraction model based on Vision Transformer (ViT), trained using the DINO method