FaceNet is a deep metric learning framework for face recognition and verification that maps face images into a compact embedding space where distances directly correspond to face similarity.

Original paper: FaceNet: A Unified Embedding for Face Recognition and Clustering

FaceNet

This model uses FaceNet with a MobileNetV1 backbone, providing a lightweight, efficient architecture suitable for real-time face recognition on mobile and embedded devices. It is well suited for applications such as authentication, access control, and edge-based identity verification.

Model Configuration:

• Reference implementation: FaceNet MobileNetV1 implementation
• Original Weight: FaceNet MobileNetV1 weight
  Extraction code: anv6
• Resolution: 3x160x160
• Support Cooper version:
  • Cooper SDK: [2.5.2]
  • Cooper Foundry: [2.2]

Model	Device	Model Link
FaceNet	N1-655	Model_Link
FaceNet	CV72	Model_Link
FaceNet	CV75	Model_Link