Why use " labels.append(np.ones(dists.size(0)))" in training?

liorshk / facenet_pytorch

PyTorch implementation of the paper "FaceNet: A Unified Embedding for Face Recognition and Clustering"

MIT License

322 stars 90 forks source link

Open AlexLuya opened 5 years ago

AlexLuya commented 5 years ago

Hello, would you please tell why do it like this?

unanan commented 5 years ago