harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
A PyTorch implementation of Siamese neural networks for facial image similarity and one-shot learning.
Velocity · 7d
+0.3
★ / day
Trend
→steady
star history
This repository implements Siamese networks with contrastive loss in PyTorch for facial similarity detection. The twin network architecture learns to distinguish image pairs by computing embedding distances. It includes notebook-based tutorials with support for datasets organized in class folders, compatible with PyTorch 0.4.0.