MaskedFace-Net is a dataset of human faces with a correctly and incorrectly worn mask based on the dataset Flickr-Faces-HQ (FFHQ).

Official repository for Self-restrained Triplet Loss for Accurate Masked Face Recognition

This is a project of Pattern Recognition course in Tsinghua University: Object detection task of masked face based on YOLO-LITE model. The model trains and infers both on CPU. The default parameters for anchor box are not so good and the mAP@.5 is just 15% for a small dataset, which means the overfitting is severe. You may change the parameters …

Datasets for multiclass facemask semantic segmentation and classification