Recognizing 330 million faces at a speed of 1500 photos/sec

Day 1 /  / Track 1  /  For practicing engineers

High-load face recognition on the photos of the social network users. We are no longer surprised by face recognition unless we have:

  • 330 millions of user accounts;
  • 20 millions of user photos uploaded every day;
  • max 0.2 seconds for one photo processing (spoiler: we've managed to do it even faster);
  • limited hardware.

In this talk we'll look at:

  • the pipeline for building users vectors and searching for users on the uploaded photos;
  • neural network training: building dataset > training > building dataset > cook until ready;
  • the facial detector on the neural networks cascade and its optimization;
  • building rescaled user vector on GPU;
  • hardware and optimizations, running in the cloud, fault tolerance.