CODEWITHSUNDEEP
c++face-recognitioncosine-similarityfaiss
Sabbir Talukdar
Sabbir Talukdar

Reputation: 125

What is the equivalent of python's faiss.normalize_L2() in C++?

I want to perfom similarity search using FAISS for 100k facial embeddings in C++. For the distance calculator I would like to use cosine similarity. For this purpose, I choose faiss::IndexFlatIP .But according to the documentation we need to normalize the vector prior to adding it to the index. The documentation suggested the following code in python:

index = faiss.IndexFlatIP(dimensions)
faiss.normalize_L2(embeddings)

But as I would like to implement the same thing in C++, I noticed I couldnot find any functions in C++ that is similar to the one in python faiss.normalize_L2(). Can anyone help? Thank's in advance.

Upvotes: 3

Views: 2674

Answers (1)

Shahriar
Shahriar

Reputation: 798

You can build and use the C++ interface of Faiss library (see this).

If you just want L2 normalization of a vector in C++:

std::vector<float> data;

float sum = 0;
for (auto item : data) sum += item * item;

float norm = std::sqrt(sum);
for (auto &item : data) item /= norm;

Upvotes: 3

Related Questions