Question about last layer in loss function

[brianw0924]

I know it have to normalize the weight

but why do we need this line:

x = F.normalize(x, p=2, dim=1)

why normalize feature?

[Charlyo]

The idea is to optimize the embedding for cosine similarity

https://arxiv.org/pdf/1811.12649.pdf

", we describe below techniques we used to achieve
SOTA on the retrieval tasks including L2 normalization of embedding to optimize for cosine
similarity"