facenet
facenet copied to clipboard
Large Scale Face recognition
I have to create a face recognition application that can identified more than 1000 classes.
I try to create a classifier by using the facenet feature and passed it to SVM classfier but it takes large amount of time to train the SVM classifier.
Is there any ways to perform large scale face recognition faster and accurate.
Regardless of the performance and time-consuming, training a NN-based classifier is better than SVM classifier. Training a SVM multiclass classifier take large amount of time because it's breaking down to a multiple binary classification cases.
see this https://github.com/deepinsight/insightface/tree/master/recognition/arcface_torch